diff --git a/.doctrees/environment.pickle b/.doctrees/environment.pickle
index e2a6cdd698..1af76c3560 100644
Binary files a/.doctrees/environment.pickle and b/.doctrees/environment.pickle differ
diff --git a/latest/_sources/using_doctr/using_models.rst.txt b/latest/_sources/using_doctr/using_models.rst.txt
index e6e5006f2e..40a820cee5 100644
--- a/latest/_sources/using_doctr/using_models.rst.txt
+++ b/latest/_sources/using_doctr/using_models.rst.txt
@@ -92,12 +92,12 @@ Detection predictors
 
     import numpy as np
     from doctr.models import detection_predictor
-    predictor = detection_predictor('db_resnet50')
+    model = detection_predictor('db_resnet50')
     dummy_img = (255 * np.random.rand(800, 600, 3)).astype(np.uint8)
     out = model([dummy_img])
 
 You can pass specific boolean arguments to the predictor:
-
+* `pretrained`: if you want to use a model that has been pretrained on a specific dataset, setting `pretrained=True` this will load the corresponding weights. If `pretrained=False`, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
 * `assume_straight_pages`: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
 * `preserve_aspect_ratio`: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
 * `symmetric_pad`: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.
@@ -198,7 +198,7 @@ Recognition predictors
 
     import numpy as np
     from doctr.models import recognition_predictor
-    predictor = recognition_predictor('crnn_vgg16_bn')
+    model = recognition_predictor('crnn_vgg16_bn')
     dummy_img = (255 * np.random.rand(50, 150, 3)).astype(np.uint8)
     out = model([dummy_img])
 
diff --git a/latest/searchindex.js b/latest/searchindex.js
index bf69950388..fc06856ae0 100644
--- a/latest/searchindex.js
+++ b/latest/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": 2, "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
+Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17, 19], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "initi": 19, "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": [2, 19], "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18, 19], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11, 19], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "useless": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "weight": 19, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "would": 19, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
diff --git a/latest/using_doctr/using_models.html b/latest/using_doctr/using_models.html
index 9ead8498e1..2fd280b854 100644
--- a/latest/using_doctr/using_models.html
+++ b/latest/using_doctr/using_models.html
@@ -533,17 +533,16 @@ <h3>Detection predictors<a class="headerlink" href="#detection-predictors" title
 <p><a class="reference internal" href="../modules/models.html#doctr.models.detection.detection_predictor" title="doctr.models.detection.detection_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">detection_predictor</span></code></a> wraps your detection model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">800</span><span class="p">,</span> <span class="mi">600</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
 </div>
-<p>You can pass specific boolean arguments to the predictor:</p>
-<ul class="simple">
-<li><p><cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.</p></li>
-<li><p><cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.</p></li>
-<li><p><cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p></li>
-</ul>
+<p>You can pass specific boolean arguments to the predictor:
+* <cite>pretrained</cite>: if you want to use a model that has been pretrained on a specific dataset, setting <cite>pretrained=True</cite> this will load the corresponding weights. If <cite>pretrained=False</cite>, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
+* <cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
+* <cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
+* <cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p>
 <p>For instance, this snippet will instantiates a detection predictor able to detect text on rotated documents while preserving the aspect ratio:</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
 <span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">,</span> <span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">assume_straight_pages</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">preserve_aspect_ratio</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
@@ -767,7 +766,7 @@ <h3>Recognition predictors<a class="headerlink" href="#recognition-predictors" t
 <p><a class="reference internal" href="../modules/models.html#doctr.models.recognition.recognition_predictor" title="doctr.models.recognition.recognition_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">recognition_predictor</span></code></a> wraps your recognition model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">recognition_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">50</span><span class="p">,</span> <span class="mi">150</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
diff --git a/v0.1.0/_sources/using_doctr/using_models.rst.txt b/v0.1.0/_sources/using_doctr/using_models.rst.txt
index e6e5006f2e..40a820cee5 100644
--- a/v0.1.0/_sources/using_doctr/using_models.rst.txt
+++ b/v0.1.0/_sources/using_doctr/using_models.rst.txt
@@ -92,12 +92,12 @@ Detection predictors
 
     import numpy as np
     from doctr.models import detection_predictor
-    predictor = detection_predictor('db_resnet50')
+    model = detection_predictor('db_resnet50')
     dummy_img = (255 * np.random.rand(800, 600, 3)).astype(np.uint8)
     out = model([dummy_img])
 
 You can pass specific boolean arguments to the predictor:
-
+* `pretrained`: if you want to use a model that has been pretrained on a specific dataset, setting `pretrained=True` this will load the corresponding weights. If `pretrained=False`, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
 * `assume_straight_pages`: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
 * `preserve_aspect_ratio`: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
 * `symmetric_pad`: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.
@@ -198,7 +198,7 @@ Recognition predictors
 
     import numpy as np
     from doctr.models import recognition_predictor
-    predictor = recognition_predictor('crnn_vgg16_bn')
+    model = recognition_predictor('crnn_vgg16_bn')
     dummy_img = (255 * np.random.rand(50, 150, 3)).astype(np.uint8)
     out = model([dummy_img])
 
diff --git a/v0.1.0/searchindex.js b/v0.1.0/searchindex.js
index bf69950388..fc06856ae0 100644
--- a/v0.1.0/searchindex.js
+++ b/v0.1.0/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": 2, "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
+Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17, 19], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "initi": 19, "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": [2, 19], "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18, 19], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11, 19], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "useless": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "weight": 19, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "would": 19, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
diff --git a/v0.1.0/using_doctr/using_models.html b/v0.1.0/using_doctr/using_models.html
index 9ead8498e1..2fd280b854 100644
--- a/v0.1.0/using_doctr/using_models.html
+++ b/v0.1.0/using_doctr/using_models.html
@@ -533,17 +533,16 @@ <h3>Detection predictors<a class="headerlink" href="#detection-predictors" title
 <p><a class="reference internal" href="../modules/models.html#doctr.models.detection.detection_predictor" title="doctr.models.detection.detection_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">detection_predictor</span></code></a> wraps your detection model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">800</span><span class="p">,</span> <span class="mi">600</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
 </div>
-<p>You can pass specific boolean arguments to the predictor:</p>
-<ul class="simple">
-<li><p><cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.</p></li>
-<li><p><cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.</p></li>
-<li><p><cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p></li>
-</ul>
+<p>You can pass specific boolean arguments to the predictor:
+* <cite>pretrained</cite>: if you want to use a model that has been pretrained on a specific dataset, setting <cite>pretrained=True</cite> this will load the corresponding weights. If <cite>pretrained=False</cite>, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
+* <cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
+* <cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
+* <cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p>
 <p>For instance, this snippet will instantiates a detection predictor able to detect text on rotated documents while preserving the aspect ratio:</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
 <span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">,</span> <span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">assume_straight_pages</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">preserve_aspect_ratio</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
@@ -767,7 +766,7 @@ <h3>Recognition predictors<a class="headerlink" href="#recognition-predictors" t
 <p><a class="reference internal" href="../modules/models.html#doctr.models.recognition.recognition_predictor" title="doctr.models.recognition.recognition_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">recognition_predictor</span></code></a> wraps your recognition model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">recognition_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">50</span><span class="p">,</span> <span class="mi">150</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
diff --git a/v0.1.1/_sources/using_doctr/using_models.rst.txt b/v0.1.1/_sources/using_doctr/using_models.rst.txt
index e6e5006f2e..40a820cee5 100644
--- a/v0.1.1/_sources/using_doctr/using_models.rst.txt
+++ b/v0.1.1/_sources/using_doctr/using_models.rst.txt
@@ -92,12 +92,12 @@ Detection predictors
 
     import numpy as np
     from doctr.models import detection_predictor
-    predictor = detection_predictor('db_resnet50')
+    model = detection_predictor('db_resnet50')
     dummy_img = (255 * np.random.rand(800, 600, 3)).astype(np.uint8)
     out = model([dummy_img])
 
 You can pass specific boolean arguments to the predictor:
-
+* `pretrained`: if you want to use a model that has been pretrained on a specific dataset, setting `pretrained=True` this will load the corresponding weights. If `pretrained=False`, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
 * `assume_straight_pages`: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
 * `preserve_aspect_ratio`: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
 * `symmetric_pad`: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.
@@ -198,7 +198,7 @@ Recognition predictors
 
     import numpy as np
     from doctr.models import recognition_predictor
-    predictor = recognition_predictor('crnn_vgg16_bn')
+    model = recognition_predictor('crnn_vgg16_bn')
     dummy_img = (255 * np.random.rand(50, 150, 3)).astype(np.uint8)
     out = model([dummy_img])
 
diff --git a/v0.1.1/searchindex.js b/v0.1.1/searchindex.js
index bf69950388..fc06856ae0 100644
--- a/v0.1.1/searchindex.js
+++ b/v0.1.1/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": 2, "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
+Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17, 19], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "initi": 19, "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": [2, 19], "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18, 19], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11, 19], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "useless": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "weight": 19, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "would": 19, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
diff --git a/v0.1.1/using_doctr/using_models.html b/v0.1.1/using_doctr/using_models.html
index 9ead8498e1..2fd280b854 100644
--- a/v0.1.1/using_doctr/using_models.html
+++ b/v0.1.1/using_doctr/using_models.html
@@ -533,17 +533,16 @@ <h3>Detection predictors<a class="headerlink" href="#detection-predictors" title
 <p><a class="reference internal" href="../modules/models.html#doctr.models.detection.detection_predictor" title="doctr.models.detection.detection_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">detection_predictor</span></code></a> wraps your detection model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">800</span><span class="p">,</span> <span class="mi">600</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
 </div>
-<p>You can pass specific boolean arguments to the predictor:</p>
-<ul class="simple">
-<li><p><cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.</p></li>
-<li><p><cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.</p></li>
-<li><p><cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p></li>
-</ul>
+<p>You can pass specific boolean arguments to the predictor:
+* <cite>pretrained</cite>: if you want to use a model that has been pretrained on a specific dataset, setting <cite>pretrained=True</cite> this will load the corresponding weights. If <cite>pretrained=False</cite>, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
+* <cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
+* <cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
+* <cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p>
 <p>For instance, this snippet will instantiates a detection predictor able to detect text on rotated documents while preserving the aspect ratio:</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
 <span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">,</span> <span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">assume_straight_pages</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">preserve_aspect_ratio</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
@@ -767,7 +766,7 @@ <h3>Recognition predictors<a class="headerlink" href="#recognition-predictors" t
 <p><a class="reference internal" href="../modules/models.html#doctr.models.recognition.recognition_predictor" title="doctr.models.recognition.recognition_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">recognition_predictor</span></code></a> wraps your recognition model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">recognition_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">50</span><span class="p">,</span> <span class="mi">150</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
diff --git a/v0.2.0/_sources/using_doctr/using_models.rst.txt b/v0.2.0/_sources/using_doctr/using_models.rst.txt
index e6e5006f2e..40a820cee5 100644
--- a/v0.2.0/_sources/using_doctr/using_models.rst.txt
+++ b/v0.2.0/_sources/using_doctr/using_models.rst.txt
@@ -92,12 +92,12 @@ Detection predictors
 
     import numpy as np
     from doctr.models import detection_predictor
-    predictor = detection_predictor('db_resnet50')
+    model = detection_predictor('db_resnet50')
     dummy_img = (255 * np.random.rand(800, 600, 3)).astype(np.uint8)
     out = model([dummy_img])
 
 You can pass specific boolean arguments to the predictor:
-
+* `pretrained`: if you want to use a model that has been pretrained on a specific dataset, setting `pretrained=True` this will load the corresponding weights. If `pretrained=False`, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
 * `assume_straight_pages`: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
 * `preserve_aspect_ratio`: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
 * `symmetric_pad`: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.
@@ -198,7 +198,7 @@ Recognition predictors
 
     import numpy as np
     from doctr.models import recognition_predictor
-    predictor = recognition_predictor('crnn_vgg16_bn')
+    model = recognition_predictor('crnn_vgg16_bn')
     dummy_img = (255 * np.random.rand(50, 150, 3)).astype(np.uint8)
     out = model([dummy_img])
 
diff --git a/v0.2.0/searchindex.js b/v0.2.0/searchindex.js
index bf69950388..fc06856ae0 100644
--- a/v0.2.0/searchindex.js
+++ b/v0.2.0/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": 2, "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
+Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17, 19], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "initi": 19, "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": [2, 19], "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18, 19], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11, 19], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "useless": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "weight": 19, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "would": 19, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
diff --git a/v0.2.0/using_doctr/using_models.html b/v0.2.0/using_doctr/using_models.html
index 9ead8498e1..2fd280b854 100644
--- a/v0.2.0/using_doctr/using_models.html
+++ b/v0.2.0/using_doctr/using_models.html
@@ -533,17 +533,16 @@ <h3>Detection predictors<a class="headerlink" href="#detection-predictors" title
 <p><a class="reference internal" href="../modules/models.html#doctr.models.detection.detection_predictor" title="doctr.models.detection.detection_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">detection_predictor</span></code></a> wraps your detection model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">800</span><span class="p">,</span> <span class="mi">600</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
 </div>
-<p>You can pass specific boolean arguments to the predictor:</p>
-<ul class="simple">
-<li><p><cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.</p></li>
-<li><p><cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.</p></li>
-<li><p><cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p></li>
-</ul>
+<p>You can pass specific boolean arguments to the predictor:
+* <cite>pretrained</cite>: if you want to use a model that has been pretrained on a specific dataset, setting <cite>pretrained=True</cite> this will load the corresponding weights. If <cite>pretrained=False</cite>, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
+* <cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
+* <cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
+* <cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p>
 <p>For instance, this snippet will instantiates a detection predictor able to detect text on rotated documents while preserving the aspect ratio:</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
 <span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">,</span> <span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">assume_straight_pages</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">preserve_aspect_ratio</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
@@ -767,7 +766,7 @@ <h3>Recognition predictors<a class="headerlink" href="#recognition-predictors" t
 <p><a class="reference internal" href="../modules/models.html#doctr.models.recognition.recognition_predictor" title="doctr.models.recognition.recognition_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">recognition_predictor</span></code></a> wraps your recognition model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">recognition_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">50</span><span class="p">,</span> <span class="mi">150</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
diff --git a/v0.2.1/_sources/using_doctr/using_models.rst.txt b/v0.2.1/_sources/using_doctr/using_models.rst.txt
index e6e5006f2e..40a820cee5 100644
--- a/v0.2.1/_sources/using_doctr/using_models.rst.txt
+++ b/v0.2.1/_sources/using_doctr/using_models.rst.txt
@@ -92,12 +92,12 @@ Detection predictors
 
     import numpy as np
     from doctr.models import detection_predictor
-    predictor = detection_predictor('db_resnet50')
+    model = detection_predictor('db_resnet50')
     dummy_img = (255 * np.random.rand(800, 600, 3)).astype(np.uint8)
     out = model([dummy_img])
 
 You can pass specific boolean arguments to the predictor:
-
+* `pretrained`: if you want to use a model that has been pretrained on a specific dataset, setting `pretrained=True` this will load the corresponding weights. If `pretrained=False`, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
 * `assume_straight_pages`: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
 * `preserve_aspect_ratio`: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
 * `symmetric_pad`: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.
@@ -198,7 +198,7 @@ Recognition predictors
 
     import numpy as np
     from doctr.models import recognition_predictor
-    predictor = recognition_predictor('crnn_vgg16_bn')
+    model = recognition_predictor('crnn_vgg16_bn')
     dummy_img = (255 * np.random.rand(50, 150, 3)).astype(np.uint8)
     out = model([dummy_img])
 
diff --git a/v0.2.1/searchindex.js b/v0.2.1/searchindex.js
index bf69950388..fc06856ae0 100644
--- a/v0.2.1/searchindex.js
+++ b/v0.2.1/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": 2, "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
+Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17, 19], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "initi": 19, "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": [2, 19], "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18, 19], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11, 19], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "useless": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "weight": 19, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "would": 19, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
diff --git a/v0.2.1/using_doctr/using_models.html b/v0.2.1/using_doctr/using_models.html
index 9ead8498e1..2fd280b854 100644
--- a/v0.2.1/using_doctr/using_models.html
+++ b/v0.2.1/using_doctr/using_models.html
@@ -533,17 +533,16 @@ <h3>Detection predictors<a class="headerlink" href="#detection-predictors" title
 <p><a class="reference internal" href="../modules/models.html#doctr.models.detection.detection_predictor" title="doctr.models.detection.detection_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">detection_predictor</span></code></a> wraps your detection model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">800</span><span class="p">,</span> <span class="mi">600</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
 </div>
-<p>You can pass specific boolean arguments to the predictor:</p>
-<ul class="simple">
-<li><p><cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.</p></li>
-<li><p><cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.</p></li>
-<li><p><cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p></li>
-</ul>
+<p>You can pass specific boolean arguments to the predictor:
+* <cite>pretrained</cite>: if you want to use a model that has been pretrained on a specific dataset, setting <cite>pretrained=True</cite> this will load the corresponding weights. If <cite>pretrained=False</cite>, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
+* <cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
+* <cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
+* <cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p>
 <p>For instance, this snippet will instantiates a detection predictor able to detect text on rotated documents while preserving the aspect ratio:</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
 <span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">,</span> <span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">assume_straight_pages</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">preserve_aspect_ratio</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
@@ -767,7 +766,7 @@ <h3>Recognition predictors<a class="headerlink" href="#recognition-predictors" t
 <p><a class="reference internal" href="../modules/models.html#doctr.models.recognition.recognition_predictor" title="doctr.models.recognition.recognition_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">recognition_predictor</span></code></a> wraps your recognition model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">recognition_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">50</span><span class="p">,</span> <span class="mi">150</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
diff --git a/v0.3.0/_sources/using_doctr/using_models.rst.txt b/v0.3.0/_sources/using_doctr/using_models.rst.txt
index e6e5006f2e..40a820cee5 100644
--- a/v0.3.0/_sources/using_doctr/using_models.rst.txt
+++ b/v0.3.0/_sources/using_doctr/using_models.rst.txt
@@ -92,12 +92,12 @@ Detection predictors
 
     import numpy as np
     from doctr.models import detection_predictor
-    predictor = detection_predictor('db_resnet50')
+    model = detection_predictor('db_resnet50')
     dummy_img = (255 * np.random.rand(800, 600, 3)).astype(np.uint8)
     out = model([dummy_img])
 
 You can pass specific boolean arguments to the predictor:
-
+* `pretrained`: if you want to use a model that has been pretrained on a specific dataset, setting `pretrained=True` this will load the corresponding weights. If `pretrained=False`, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
 * `assume_straight_pages`: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
 * `preserve_aspect_ratio`: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
 * `symmetric_pad`: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.
@@ -198,7 +198,7 @@ Recognition predictors
 
     import numpy as np
     from doctr.models import recognition_predictor
-    predictor = recognition_predictor('crnn_vgg16_bn')
+    model = recognition_predictor('crnn_vgg16_bn')
     dummy_img = (255 * np.random.rand(50, 150, 3)).astype(np.uint8)
     out = model([dummy_img])
 
diff --git a/v0.3.0/searchindex.js b/v0.3.0/searchindex.js
index bf69950388..fc06856ae0 100644
--- a/v0.3.0/searchindex.js
+++ b/v0.3.0/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": 2, "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
+Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17, 19], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "initi": 19, "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": [2, 19], "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18, 19], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11, 19], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "useless": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "weight": 19, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "would": 19, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
diff --git a/v0.3.0/using_doctr/using_models.html b/v0.3.0/using_doctr/using_models.html
index 9ead8498e1..2fd280b854 100644
--- a/v0.3.0/using_doctr/using_models.html
+++ b/v0.3.0/using_doctr/using_models.html
@@ -533,17 +533,16 @@ <h3>Detection predictors<a class="headerlink" href="#detection-predictors" title
 <p><a class="reference internal" href="../modules/models.html#doctr.models.detection.detection_predictor" title="doctr.models.detection.detection_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">detection_predictor</span></code></a> wraps your detection model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">800</span><span class="p">,</span> <span class="mi">600</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
 </div>
-<p>You can pass specific boolean arguments to the predictor:</p>
-<ul class="simple">
-<li><p><cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.</p></li>
-<li><p><cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.</p></li>
-<li><p><cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p></li>
-</ul>
+<p>You can pass specific boolean arguments to the predictor:
+* <cite>pretrained</cite>: if you want to use a model that has been pretrained on a specific dataset, setting <cite>pretrained=True</cite> this will load the corresponding weights. If <cite>pretrained=False</cite>, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
+* <cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
+* <cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
+* <cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p>
 <p>For instance, this snippet will instantiates a detection predictor able to detect text on rotated documents while preserving the aspect ratio:</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
 <span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">,</span> <span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">assume_straight_pages</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">preserve_aspect_ratio</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
@@ -767,7 +766,7 @@ <h3>Recognition predictors<a class="headerlink" href="#recognition-predictors" t
 <p><a class="reference internal" href="../modules/models.html#doctr.models.recognition.recognition_predictor" title="doctr.models.recognition.recognition_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">recognition_predictor</span></code></a> wraps your recognition model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">recognition_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">50</span><span class="p">,</span> <span class="mi">150</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
diff --git a/v0.3.1/_sources/using_doctr/using_models.rst.txt b/v0.3.1/_sources/using_doctr/using_models.rst.txt
index e6e5006f2e..40a820cee5 100644
--- a/v0.3.1/_sources/using_doctr/using_models.rst.txt
+++ b/v0.3.1/_sources/using_doctr/using_models.rst.txt
@@ -92,12 +92,12 @@ Detection predictors
 
     import numpy as np
     from doctr.models import detection_predictor
-    predictor = detection_predictor('db_resnet50')
+    model = detection_predictor('db_resnet50')
     dummy_img = (255 * np.random.rand(800, 600, 3)).astype(np.uint8)
     out = model([dummy_img])
 
 You can pass specific boolean arguments to the predictor:
-
+* `pretrained`: if you want to use a model that has been pretrained on a specific dataset, setting `pretrained=True` this will load the corresponding weights. If `pretrained=False`, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
 * `assume_straight_pages`: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
 * `preserve_aspect_ratio`: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
 * `symmetric_pad`: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.
@@ -198,7 +198,7 @@ Recognition predictors
 
     import numpy as np
     from doctr.models import recognition_predictor
-    predictor = recognition_predictor('crnn_vgg16_bn')
+    model = recognition_predictor('crnn_vgg16_bn')
     dummy_img = (255 * np.random.rand(50, 150, 3)).astype(np.uint8)
     out = model([dummy_img])
 
diff --git a/v0.3.1/searchindex.js b/v0.3.1/searchindex.js
index bf69950388..fc06856ae0 100644
--- a/v0.3.1/searchindex.js
+++ b/v0.3.1/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": 2, "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
+Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17, 19], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "initi": 19, "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": [2, 19], "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18, 19], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11, 19], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "useless": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "weight": 19, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "would": 19, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
diff --git a/v0.3.1/using_doctr/using_models.html b/v0.3.1/using_doctr/using_models.html
index 9ead8498e1..2fd280b854 100644
--- a/v0.3.1/using_doctr/using_models.html
+++ b/v0.3.1/using_doctr/using_models.html
@@ -533,17 +533,16 @@ <h3>Detection predictors<a class="headerlink" href="#detection-predictors" title
 <p><a class="reference internal" href="../modules/models.html#doctr.models.detection.detection_predictor" title="doctr.models.detection.detection_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">detection_predictor</span></code></a> wraps your detection model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">800</span><span class="p">,</span> <span class="mi">600</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
 </div>
-<p>You can pass specific boolean arguments to the predictor:</p>
-<ul class="simple">
-<li><p><cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.</p></li>
-<li><p><cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.</p></li>
-<li><p><cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p></li>
-</ul>
+<p>You can pass specific boolean arguments to the predictor:
+* <cite>pretrained</cite>: if you want to use a model that has been pretrained on a specific dataset, setting <cite>pretrained=True</cite> this will load the corresponding weights. If <cite>pretrained=False</cite>, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
+* <cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
+* <cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
+* <cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p>
 <p>For instance, this snippet will instantiates a detection predictor able to detect text on rotated documents while preserving the aspect ratio:</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
 <span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">,</span> <span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">assume_straight_pages</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">preserve_aspect_ratio</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
@@ -767,7 +766,7 @@ <h3>Recognition predictors<a class="headerlink" href="#recognition-predictors" t
 <p><a class="reference internal" href="../modules/models.html#doctr.models.recognition.recognition_predictor" title="doctr.models.recognition.recognition_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">recognition_predictor</span></code></a> wraps your recognition model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">recognition_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">50</span><span class="p">,</span> <span class="mi">150</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
diff --git a/v0.4.0/_sources/using_doctr/using_models.rst.txt b/v0.4.0/_sources/using_doctr/using_models.rst.txt
index e6e5006f2e..40a820cee5 100644
--- a/v0.4.0/_sources/using_doctr/using_models.rst.txt
+++ b/v0.4.0/_sources/using_doctr/using_models.rst.txt
@@ -92,12 +92,12 @@ Detection predictors
 
     import numpy as np
     from doctr.models import detection_predictor
-    predictor = detection_predictor('db_resnet50')
+    model = detection_predictor('db_resnet50')
     dummy_img = (255 * np.random.rand(800, 600, 3)).astype(np.uint8)
     out = model([dummy_img])
 
 You can pass specific boolean arguments to the predictor:
-
+* `pretrained`: if you want to use a model that has been pretrained on a specific dataset, setting `pretrained=True` this will load the corresponding weights. If `pretrained=False`, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
 * `assume_straight_pages`: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
 * `preserve_aspect_ratio`: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
 * `symmetric_pad`: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.
@@ -198,7 +198,7 @@ Recognition predictors
 
     import numpy as np
     from doctr.models import recognition_predictor
-    predictor = recognition_predictor('crnn_vgg16_bn')
+    model = recognition_predictor('crnn_vgg16_bn')
     dummy_img = (255 * np.random.rand(50, 150, 3)).astype(np.uint8)
     out = model([dummy_img])
 
diff --git a/v0.4.0/searchindex.js b/v0.4.0/searchindex.js
index bf69950388..fc06856ae0 100644
--- a/v0.4.0/searchindex.js
+++ b/v0.4.0/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": 2, "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
+Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17, 19], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "initi": 19, "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": [2, 19], "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18, 19], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11, 19], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "useless": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "weight": 19, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "would": 19, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
diff --git a/v0.4.0/using_doctr/using_models.html b/v0.4.0/using_doctr/using_models.html
index 9ead8498e1..2fd280b854 100644
--- a/v0.4.0/using_doctr/using_models.html
+++ b/v0.4.0/using_doctr/using_models.html
@@ -533,17 +533,16 @@ <h3>Detection predictors<a class="headerlink" href="#detection-predictors" title
 <p><a class="reference internal" href="../modules/models.html#doctr.models.detection.detection_predictor" title="doctr.models.detection.detection_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">detection_predictor</span></code></a> wraps your detection model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">800</span><span class="p">,</span> <span class="mi">600</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
 </div>
-<p>You can pass specific boolean arguments to the predictor:</p>
-<ul class="simple">
-<li><p><cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.</p></li>
-<li><p><cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.</p></li>
-<li><p><cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p></li>
-</ul>
+<p>You can pass specific boolean arguments to the predictor:
+* <cite>pretrained</cite>: if you want to use a model that has been pretrained on a specific dataset, setting <cite>pretrained=True</cite> this will load the corresponding weights. If <cite>pretrained=False</cite>, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
+* <cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
+* <cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
+* <cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p>
 <p>For instance, this snippet will instantiates a detection predictor able to detect text on rotated documents while preserving the aspect ratio:</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
 <span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">,</span> <span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">assume_straight_pages</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">preserve_aspect_ratio</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
@@ -767,7 +766,7 @@ <h3>Recognition predictors<a class="headerlink" href="#recognition-predictors" t
 <p><a class="reference internal" href="../modules/models.html#doctr.models.recognition.recognition_predictor" title="doctr.models.recognition.recognition_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">recognition_predictor</span></code></a> wraps your recognition model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">recognition_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">50</span><span class="p">,</span> <span class="mi">150</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
diff --git a/v0.4.1/_sources/using_doctr/using_models.rst.txt b/v0.4.1/_sources/using_doctr/using_models.rst.txt
index e6e5006f2e..40a820cee5 100644
--- a/v0.4.1/_sources/using_doctr/using_models.rst.txt
+++ b/v0.4.1/_sources/using_doctr/using_models.rst.txt
@@ -92,12 +92,12 @@ Detection predictors
 
     import numpy as np
     from doctr.models import detection_predictor
-    predictor = detection_predictor('db_resnet50')
+    model = detection_predictor('db_resnet50')
     dummy_img = (255 * np.random.rand(800, 600, 3)).astype(np.uint8)
     out = model([dummy_img])
 
 You can pass specific boolean arguments to the predictor:
-
+* `pretrained`: if you want to use a model that has been pretrained on a specific dataset, setting `pretrained=True` this will load the corresponding weights. If `pretrained=False`, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
 * `assume_straight_pages`: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
 * `preserve_aspect_ratio`: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
 * `symmetric_pad`: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.
@@ -198,7 +198,7 @@ Recognition predictors
 
     import numpy as np
     from doctr.models import recognition_predictor
-    predictor = recognition_predictor('crnn_vgg16_bn')
+    model = recognition_predictor('crnn_vgg16_bn')
     dummy_img = (255 * np.random.rand(50, 150, 3)).astype(np.uint8)
     out = model([dummy_img])
 
diff --git a/v0.4.1/searchindex.js b/v0.4.1/searchindex.js
index bf69950388..fc06856ae0 100644
--- a/v0.4.1/searchindex.js
+++ b/v0.4.1/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": 2, "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
+Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17, 19], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "initi": 19, "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": [2, 19], "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18, 19], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11, 19], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "useless": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "weight": 19, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "would": 19, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
diff --git a/v0.4.1/using_doctr/using_models.html b/v0.4.1/using_doctr/using_models.html
index 9ead8498e1..2fd280b854 100644
--- a/v0.4.1/using_doctr/using_models.html
+++ b/v0.4.1/using_doctr/using_models.html
@@ -533,17 +533,16 @@ <h3>Detection predictors<a class="headerlink" href="#detection-predictors" title
 <p><a class="reference internal" href="../modules/models.html#doctr.models.detection.detection_predictor" title="doctr.models.detection.detection_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">detection_predictor</span></code></a> wraps your detection model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">800</span><span class="p">,</span> <span class="mi">600</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
 </div>
-<p>You can pass specific boolean arguments to the predictor:</p>
-<ul class="simple">
-<li><p><cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.</p></li>
-<li><p><cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.</p></li>
-<li><p><cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p></li>
-</ul>
+<p>You can pass specific boolean arguments to the predictor:
+* <cite>pretrained</cite>: if you want to use a model that has been pretrained on a specific dataset, setting <cite>pretrained=True</cite> this will load the corresponding weights. If <cite>pretrained=False</cite>, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
+* <cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
+* <cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
+* <cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p>
 <p>For instance, this snippet will instantiates a detection predictor able to detect text on rotated documents while preserving the aspect ratio:</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
 <span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">,</span> <span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">assume_straight_pages</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">preserve_aspect_ratio</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
@@ -767,7 +766,7 @@ <h3>Recognition predictors<a class="headerlink" href="#recognition-predictors" t
 <p><a class="reference internal" href="../modules/models.html#doctr.models.recognition.recognition_predictor" title="doctr.models.recognition.recognition_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">recognition_predictor</span></code></a> wraps your recognition model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">recognition_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">50</span><span class="p">,</span> <span class="mi">150</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
diff --git a/v0.5.0/_sources/using_doctr/using_models.rst.txt b/v0.5.0/_sources/using_doctr/using_models.rst.txt
index e6e5006f2e..40a820cee5 100644
--- a/v0.5.0/_sources/using_doctr/using_models.rst.txt
+++ b/v0.5.0/_sources/using_doctr/using_models.rst.txt
@@ -92,12 +92,12 @@ Detection predictors
 
     import numpy as np
     from doctr.models import detection_predictor
-    predictor = detection_predictor('db_resnet50')
+    model = detection_predictor('db_resnet50')
     dummy_img = (255 * np.random.rand(800, 600, 3)).astype(np.uint8)
     out = model([dummy_img])
 
 You can pass specific boolean arguments to the predictor:
-
+* `pretrained`: if you want to use a model that has been pretrained on a specific dataset, setting `pretrained=True` this will load the corresponding weights. If `pretrained=False`, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
 * `assume_straight_pages`: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
 * `preserve_aspect_ratio`: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
 * `symmetric_pad`: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.
@@ -198,7 +198,7 @@ Recognition predictors
 
     import numpy as np
     from doctr.models import recognition_predictor
-    predictor = recognition_predictor('crnn_vgg16_bn')
+    model = recognition_predictor('crnn_vgg16_bn')
     dummy_img = (255 * np.random.rand(50, 150, 3)).astype(np.uint8)
     out = model([dummy_img])
 
diff --git a/v0.5.0/searchindex.js b/v0.5.0/searchindex.js
index bf69950388..fc06856ae0 100644
--- a/v0.5.0/searchindex.js
+++ b/v0.5.0/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": 2, "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
+Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17, 19], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "initi": 19, "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": [2, 19], "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18, 19], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11, 19], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "useless": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "weight": 19, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "would": 19, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
diff --git a/v0.5.0/using_doctr/using_models.html b/v0.5.0/using_doctr/using_models.html
index 9ead8498e1..2fd280b854 100644
--- a/v0.5.0/using_doctr/using_models.html
+++ b/v0.5.0/using_doctr/using_models.html
@@ -533,17 +533,16 @@ <h3>Detection predictors<a class="headerlink" href="#detection-predictors" title
 <p><a class="reference internal" href="../modules/models.html#doctr.models.detection.detection_predictor" title="doctr.models.detection.detection_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">detection_predictor</span></code></a> wraps your detection model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">800</span><span class="p">,</span> <span class="mi">600</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
 </div>
-<p>You can pass specific boolean arguments to the predictor:</p>
-<ul class="simple">
-<li><p><cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.</p></li>
-<li><p><cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.</p></li>
-<li><p><cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p></li>
-</ul>
+<p>You can pass specific boolean arguments to the predictor:
+* <cite>pretrained</cite>: if you want to use a model that has been pretrained on a specific dataset, setting <cite>pretrained=True</cite> this will load the corresponding weights. If <cite>pretrained=False</cite>, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
+* <cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
+* <cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
+* <cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p>
 <p>For instance, this snippet will instantiates a detection predictor able to detect text on rotated documents while preserving the aspect ratio:</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
 <span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">,</span> <span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">assume_straight_pages</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">preserve_aspect_ratio</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
@@ -767,7 +766,7 @@ <h3>Recognition predictors<a class="headerlink" href="#recognition-predictors" t
 <p><a class="reference internal" href="../modules/models.html#doctr.models.recognition.recognition_predictor" title="doctr.models.recognition.recognition_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">recognition_predictor</span></code></a> wraps your recognition model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">recognition_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">50</span><span class="p">,</span> <span class="mi">150</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
diff --git a/v0.5.1/_sources/using_doctr/using_models.rst.txt b/v0.5.1/_sources/using_doctr/using_models.rst.txt
index e6e5006f2e..40a820cee5 100644
--- a/v0.5.1/_sources/using_doctr/using_models.rst.txt
+++ b/v0.5.1/_sources/using_doctr/using_models.rst.txt
@@ -92,12 +92,12 @@ Detection predictors
 
     import numpy as np
     from doctr.models import detection_predictor
-    predictor = detection_predictor('db_resnet50')
+    model = detection_predictor('db_resnet50')
     dummy_img = (255 * np.random.rand(800, 600, 3)).astype(np.uint8)
     out = model([dummy_img])
 
 You can pass specific boolean arguments to the predictor:
-
+* `pretrained`: if you want to use a model that has been pretrained on a specific dataset, setting `pretrained=True` this will load the corresponding weights. If `pretrained=False`, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
 * `assume_straight_pages`: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
 * `preserve_aspect_ratio`: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
 * `symmetric_pad`: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.
@@ -198,7 +198,7 @@ Recognition predictors
 
     import numpy as np
     from doctr.models import recognition_predictor
-    predictor = recognition_predictor('crnn_vgg16_bn')
+    model = recognition_predictor('crnn_vgg16_bn')
     dummy_img = (255 * np.random.rand(50, 150, 3)).astype(np.uint8)
     out = model([dummy_img])
 
diff --git a/v0.5.1/searchindex.js b/v0.5.1/searchindex.js
index bf69950388..fc06856ae0 100644
--- a/v0.5.1/searchindex.js
+++ b/v0.5.1/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": 2, "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
+Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17, 19], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "initi": 19, "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": [2, 19], "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18, 19], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11, 19], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "useless": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "weight": 19, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "would": 19, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
diff --git a/v0.5.1/using_doctr/using_models.html b/v0.5.1/using_doctr/using_models.html
index 9ead8498e1..2fd280b854 100644
--- a/v0.5.1/using_doctr/using_models.html
+++ b/v0.5.1/using_doctr/using_models.html
@@ -533,17 +533,16 @@ <h3>Detection predictors<a class="headerlink" href="#detection-predictors" title
 <p><a class="reference internal" href="../modules/models.html#doctr.models.detection.detection_predictor" title="doctr.models.detection.detection_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">detection_predictor</span></code></a> wraps your detection model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">800</span><span class="p">,</span> <span class="mi">600</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
 </div>
-<p>You can pass specific boolean arguments to the predictor:</p>
-<ul class="simple">
-<li><p><cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.</p></li>
-<li><p><cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.</p></li>
-<li><p><cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p></li>
-</ul>
+<p>You can pass specific boolean arguments to the predictor:
+* <cite>pretrained</cite>: if you want to use a model that has been pretrained on a specific dataset, setting <cite>pretrained=True</cite> this will load the corresponding weights. If <cite>pretrained=False</cite>, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
+* <cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
+* <cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
+* <cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p>
 <p>For instance, this snippet will instantiates a detection predictor able to detect text on rotated documents while preserving the aspect ratio:</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
 <span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">,</span> <span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">assume_straight_pages</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">preserve_aspect_ratio</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
@@ -767,7 +766,7 @@ <h3>Recognition predictors<a class="headerlink" href="#recognition-predictors" t
 <p><a class="reference internal" href="../modules/models.html#doctr.models.recognition.recognition_predictor" title="doctr.models.recognition.recognition_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">recognition_predictor</span></code></a> wraps your recognition model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">recognition_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">50</span><span class="p">,</span> <span class="mi">150</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
diff --git a/v0.6.0/_sources/using_doctr/using_models.rst.txt b/v0.6.0/_sources/using_doctr/using_models.rst.txt
index e6e5006f2e..40a820cee5 100644
--- a/v0.6.0/_sources/using_doctr/using_models.rst.txt
+++ b/v0.6.0/_sources/using_doctr/using_models.rst.txt
@@ -92,12 +92,12 @@ Detection predictors
 
     import numpy as np
     from doctr.models import detection_predictor
-    predictor = detection_predictor('db_resnet50')
+    model = detection_predictor('db_resnet50')
     dummy_img = (255 * np.random.rand(800, 600, 3)).astype(np.uint8)
     out = model([dummy_img])
 
 You can pass specific boolean arguments to the predictor:
-
+* `pretrained`: if you want to use a model that has been pretrained on a specific dataset, setting `pretrained=True` this will load the corresponding weights. If `pretrained=False`, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
 * `assume_straight_pages`: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
 * `preserve_aspect_ratio`: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
 * `symmetric_pad`: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.
@@ -198,7 +198,7 @@ Recognition predictors
 
     import numpy as np
     from doctr.models import recognition_predictor
-    predictor = recognition_predictor('crnn_vgg16_bn')
+    model = recognition_predictor('crnn_vgg16_bn')
     dummy_img = (255 * np.random.rand(50, 150, 3)).astype(np.uint8)
     out = model([dummy_img])
 
diff --git a/v0.6.0/searchindex.js b/v0.6.0/searchindex.js
index bf69950388..fc06856ae0 100644
--- a/v0.6.0/searchindex.js
+++ b/v0.6.0/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": 2, "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
+Search.setIndex({"alltitles": {"1. Correction": [[2, "correction"]], "2. Warning": [[2, "warning"]], "3. Temporary Ban": [[2, "temporary-ban"]], "4. Permanent Ban": [[2, "permanent-ban"]], "AWS Lambda": [[14, null]], "Advanced options": [[19, "advanced-options"]], "Artefact": [[8, "artefact"]], "ArtefactDetection": [[16, "artefactdetection"]], "Attribution": [[2, "attribution"]], "Available Datasets": [[17, "available-datasets"]], "Available architectures": [[19, "available-architectures"], [19, "id1"], [19, "id2"]], "Available contribution modules": [[16, "available-contribution-modules"]], "Block": [[8, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[17, null]], "Choosing the right model": [[19, null]], "Classification": [[15, "classification"]], "Code quality": [[3, "code-quality"]], "Code style verification": [[3, "code-style-verification"]], "Codebase structure": [[3, "codebase-structure"]], "Commits": [[3, "commits"]], "Community resources": [[1, null]], "Composing transformations": [[10, "composing-transformations"]], "Continuous Integration": [[3, "continuous-integration"]], "Contributing to docTR": [[3, null]], "Contributor Covenant Code of Conduct": [[2, null]], "Custom dataset loader": [[7, "custom-dataset-loader"]], "Custom orientation classification models": [[13, "custom-orientation-classification-models"]], "Data Loading": [[17, "data-loading"]], "Dataset utils": [[7, "dataset-utils"]], "Detection": [[15, "detection"], [17, "detection"]], "Detection predictors": [[19, "detection-predictors"]], "Developer mode installation": [[3, "developer-mode-installation"]], "Developing docTR": [[3, "developing-doctr"]], "Document": [[8, "document"]], "Document structure": [[8, "document-structure"]], "End-to-End OCR": [[19, "end-to-end-ocr"]], "Enforcement": [[2, "enforcement"]], "Enforcement Guidelines": [[2, "enforcement-guidelines"]], "Enforcement Responsibilities": [[2, "enforcement-responsibilities"]], "Export to ONNX": [[18, "export-to-onnx"]], "Feature requests & bug report": [[3, "feature-requests-bug-report"]], "Feedback": [[3, "feedback"]], "File reading": [[8, "file-reading"]], "Half-precision": [[18, "half-precision"]], "Installation": [[4, null]], "Integrate contributions into your pipeline": [[16, null]], "Let\u2019s connect": [[3, "let-s-connect"]], "Line": [[8, "line"]], "Loading from Huggingface Hub": [[15, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[13, "loading-your-custom-trained-model"]], "Loading your custom trained orientation classification model": [[13, "loading-your-custom-trained-orientation-classification-model"]], "Main Features": [[5, "main-features"]], "Model optimization": [[18, "model-optimization"]], "Model zoo": [[5, "model-zoo"]], "Modifying the documentation": [[3, "modifying-the-documentation"]], "Naming conventions": [[15, "naming-conventions"]], "OCR": [[17, "ocr"]], "Object Detection": [[17, "object-detection"]], "Our Pledge": [[2, "our-pledge"]], "Our Standards": [[2, "our-standards"]], "Page": [[8, "page"]], "Preparing your model for inference": [[18, null]], "Prerequisites": [[4, "prerequisites"]], "Pretrained community models": [[15, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[15, "pushing-to-the-huggingface-hub"]], "Questions": [[3, "questions"]], "Recognition": [[15, "recognition"], [17, "recognition"]], "Recognition predictors": [[19, "recognition-predictors"]], "Reconstitution": [[11, "reconstitution"]], "Scope": [[2, "scope"]], "Share your model with the community": [[15, null]], "Supported Vocabs": [[7, "supported-vocabs"]], "Supported contribution modules": [[6, "supported-contribution-modules"]], "Supported datasets": [[5, "supported-datasets"]], "Supported transformations": [[10, "supported-transformations"]], "Synthetic dataset generator": [[7, "synthetic-dataset-generator"], [17, "synthetic-dataset-generator"]], "Task evaluation": [[11, "task-evaluation"]], "Text Detection": [[19, "text-detection"]], "Text Recognition": [[19, "text-recognition"]], "Text detection models": [[5, "text-detection-models"]], "Text recognition models": [[5, "text-recognition-models"]], "Train your own model": [[13, null]], "Two-stage approaches": [[19, "two-stage-approaches"]], "Unit tests": [[3, "unit-tests"]], "Use your own datasets": [[17, "use-your-own-datasets"]], "Using your ONNX exported model": [[18, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[4, "via-conda-only-for-linux"]], "Via Git": [[4, "via-git"]], "Via Python Package": [[4, "via-python-package"]], "Visualization": [[11, "visualization"]], "What should I do with the output?": [[19, "what-should-i-do-with-the-output"]], "Word": [[8, "word"]], "docTR Notebooks": [[12, null]], "docTR Vocabs": [[7, "id6"]], "docTR: Document Text Recognition": [[5, null]], "doctr.contrib": [[6, null]], "doctr.datasets": [[7, null], [7, "datasets"]], "doctr.io": [[8, null]], "doctr.models": [[9, null]], "doctr.models.classification": [[9, "doctr-models-classification"]], "doctr.models.detection": [[9, "doctr-models-detection"]], "doctr.models.factory": [[9, "doctr-models-factory"]], "doctr.models.recognition": [[9, "doctr-models-recognition"]], "doctr.models.zoo": [[9, "doctr-models-zoo"]], "doctr.transforms": [[10, null]], "doctr.utils": [[11, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.10.0 (2024-10-21)": [[0, "v0-10-0-2024-10-21"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]], "v0.9.0 (2024-08-08)": [[0, "v0-9-0-2024-08-08"]]}, "docnames": ["changelog", "community/resources", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "community/resources.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[8, "doctr.io.Artefact", false]], "artefactdetector (class in doctr.contrib)": [[6, "doctr.contrib.ArtefactDetector", false]], "block (class in doctr.io)": [[8, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[7, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ColorInversion", false]], "convert_target_to_relative() (in module doctr.datasets)": [[7, "doctr.datasets.convert_target_to_relative", false]], "cord (class in doctr.datasets)": [[7, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_bboxes_from_image() (in module doctr.datasets)": [[7, "doctr.datasets.crop_bboxes_from_image", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.crop_orientation_predictor", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.decode_img_as_tensor", false]], "decode_sequence() (in module doctr.datasets)": [[7, "doctr.datasets.decode_sequence", false]], "detection_predictor() (in module doctr.models.detection)": [[9, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[7, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[7, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[8, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[8, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[7, "doctr.datasets.encode_sequences", false]], "encode_string() (in module doctr.datasets)": [[7, "doctr.datasets.encode_string", false]], "fast_base() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[9, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[8, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[7, "doctr.datasets.FUNSD", false]], "gaussiannoise (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[7, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[7, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[7, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[7, "doctr.datasets.IIITHWS", false]], "imagetransform (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.ImageTransform", false]], "imgur5k (class in doctr.datasets)": [[7, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[9, "doctr.models.kie_predictor", false]], "line (class in doctr.io)": [[8, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[9, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[7, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.mobilenet_v3_small_r", false]], "ocr_predictor() (in module doctr.models)": [[9, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[7, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.OneOf", false]], "page (class in doctr.io)": [[8, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[9, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.parseq", false]], "pre_transform_multiclass() (in module doctr.datasets)": [[7, "doctr.datasets.pre_transform_multiclass", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[9, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomApply", false]], "randomcrop (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomCrop", false]], "randomhorizontalflip (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomHorizontalFlip", false]], "randomresize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomResize", false]], "randomrotate (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomRotate", false]], "randomshadow (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.RandomShadow", false]], "read_html() (in module doctr.io)": [[8, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[8, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[8, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[8, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[7, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.Resize", false]], "resnet18() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[9, "doctr.models.classification.resnet50", false]], "samplecompose (class in doctr.transforms.modules)": [[10, "doctr.transforms.modules.SampleCompose", false]], "sar_resnet31() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[8, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[8, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[7, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[7, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[7, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.reconstitution)": [[11, "doctr.utils.reconstitution.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[7, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[11, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[9, "doctr.models.classification.textnet_tiny", false]], "translate() (in module doctr.datasets)": [[7, "doctr.datasets.translate", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[11, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[11, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[11, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[11, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[9, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[11, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[9, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[9, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[7, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[8, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[7, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.contrib": [[6, 0, 1, "", "ArtefactDetector"]], "doctr.datasets": [[7, 0, 1, "", "CORD"], [7, 0, 1, "", "CharacterGenerator"], [7, 0, 1, "", "DetectionDataset"], [7, 0, 1, "", "DocArtefacts"], [7, 0, 1, "", "FUNSD"], [7, 0, 1, "", "IC03"], [7, 0, 1, "", "IC13"], [7, 0, 1, "", "IIIT5K"], [7, 0, 1, "", "IIITHWS"], [7, 0, 1, "", "IMGUR5K"], [7, 0, 1, "", "MJSynth"], [7, 0, 1, "", "OCRDataset"], [7, 0, 1, "", "RecognitionDataset"], [7, 0, 1, "", "SROIE"], [7, 0, 1, "", "SVHN"], [7, 0, 1, "", "SVT"], [7, 0, 1, "", "SynthText"], [7, 0, 1, "", "WILDRECEIPT"], [7, 0, 1, "", "WordGenerator"], [7, 1, 1, "", "convert_target_to_relative"], [7, 1, 1, "", "crop_bboxes_from_image"], [7, 1, 1, "", "decode_sequence"], [7, 1, 1, "", "encode_sequences"], [7, 1, 1, "", "encode_string"], [7, 1, 1, "", "pre_transform_multiclass"], [7, 1, 1, "", "translate"]], "doctr.io": [[8, 0, 1, "", "Artefact"], [8, 0, 1, "", "Block"], [8, 0, 1, "", "Document"], [8, 0, 1, "", "DocumentFile"], [8, 0, 1, "", "Line"], [8, 0, 1, "", "Page"], [8, 0, 1, "", "Word"], [8, 1, 1, "", "decode_img_as_tensor"], [8, 1, 1, "", "read_html"], [8, 1, 1, "", "read_img_as_numpy"], [8, 1, 1, "", "read_img_as_tensor"], [8, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[8, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[8, 2, 1, "", "from_images"], [8, 2, 1, "", "from_pdf"], [8, 2, 1, "", "from_url"]], "doctr.io.Page": [[8, 2, 1, "", "show"]], "doctr.models": [[9, 1, 1, "", "kie_predictor"], [9, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[9, 1, 1, "", "crop_orientation_predictor"], [9, 1, 1, "", "magc_resnet31"], [9, 1, 1, "", "mobilenet_v3_large"], [9, 1, 1, "", "mobilenet_v3_large_r"], [9, 1, 1, "", "mobilenet_v3_small"], [9, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [9, 1, 1, "", "mobilenet_v3_small_page_orientation"], [9, 1, 1, "", "mobilenet_v3_small_r"], [9, 1, 1, "", "page_orientation_predictor"], [9, 1, 1, "", "resnet18"], [9, 1, 1, "", "resnet31"], [9, 1, 1, "", "resnet34"], [9, 1, 1, "", "resnet50"], [9, 1, 1, "", "textnet_base"], [9, 1, 1, "", "textnet_small"], [9, 1, 1, "", "textnet_tiny"], [9, 1, 1, "", "vgg16_bn_r"], [9, 1, 1, "", "vit_b"], [9, 1, 1, "", "vit_s"]], "doctr.models.detection": [[9, 1, 1, "", "db_mobilenet_v3_large"], [9, 1, 1, "", "db_resnet50"], [9, 1, 1, "", "detection_predictor"], [9, 1, 1, "", "fast_base"], [9, 1, 1, "", "fast_small"], [9, 1, 1, "", "fast_tiny"], [9, 1, 1, "", "linknet_resnet18"], [9, 1, 1, "", "linknet_resnet34"], [9, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[9, 1, 1, "", "from_hub"], [9, 1, 1, "", "login_to_hub"], [9, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[9, 1, 1, "", "crnn_mobilenet_v3_large"], [9, 1, 1, "", "crnn_mobilenet_v3_small"], [9, 1, 1, "", "crnn_vgg16_bn"], [9, 1, 1, "", "master"], [9, 1, 1, "", "parseq"], [9, 1, 1, "", "recognition_predictor"], [9, 1, 1, "", "sar_resnet31"], [9, 1, 1, "", "vitstr_base"], [9, 1, 1, "", "vitstr_small"]], "doctr.transforms.modules": [[10, 0, 1, "", "ChannelShuffle"], [10, 0, 1, "", "ColorInversion"], [10, 0, 1, "", "GaussianNoise"], [10, 0, 1, "", "ImageTransform"], [10, 0, 1, "", "OneOf"], [10, 0, 1, "", "RandomApply"], [10, 0, 1, "", "RandomCrop"], [10, 0, 1, "", "RandomHorizontalFlip"], [10, 0, 1, "", "RandomResize"], [10, 0, 1, "", "RandomRotate"], [10, 0, 1, "", "RandomShadow"], [10, 0, 1, "", "Resize"], [10, 0, 1, "", "SampleCompose"]], "doctr.utils.metrics": [[11, 0, 1, "", "DetectionMetric"], [11, 0, 1, "", "LocalizationConfusion"], [11, 0, 1, "", "OCRMetric"], [11, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[11, 2, 1, "", "summary"], [11, 2, 1, "", "update"]], "doctr.utils.reconstitution": [[11, 1, 1, "", "synthesize_page"]], "doctr.utils.visualization": [[11, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [2, 8, 9, 11, 15, 18], "0": [2, 4, 6, 7, 10, 11, 13, 16, 17, 19], "00": 19, "01": 19, "0123456789": 7, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "02562": 9, "03": 19, "035": 19, "0361328125": 19, "04": 19, "05": 19, "06": 19, "06640625": 19, "07": 19, "08": [10, 19], "09": 19, "0966796875": 19, "1": [7, 8, 9, 10, 11, 13, 17, 19], "10": [4, 7, 11, 19], "100": [7, 11, 17, 19], "1000": 19, "101": 7, "1024": [9, 13, 19], "104": 7, "106": 7, "108": 7, "1095": 17, "11": 19, "110": 11, "1107": 17, "114": 7, "115": 7, "1156": 17, "116": 7, "118": 7, "11800h": 19, "11th": 19, "12": 19, "120": 7, "123": 7, "126": 7, "1268": 17, "128": [9, 13, 18, 19], "13": 19, "130": 7, "13068": 17, "131": 7, "1337891": 17, "1357421875": 19, "1396484375": 19, "14": 19, "1420": 19, "149": 17, "15": 19, "150": [11, 19], "1552": 19, "16": [9, 18, 19], "1630859375": 19, "1684": 19, "16x16": 9, "17": 19, "1778": 19, "1782": 19, "18": [9, 19], "185546875": 19, "1900": 19, "1910": 9, "19342": 17, "19370": 17, "195": 7, "19598": 17, "199": 19, "1999": 19, "2": [4, 5, 6, 7, 8, 9, 10, 16, 19], "20": 19, "200": 11, "2000": 17, "2003": [5, 7], "2012": 7, "2013": [5, 7], "2015": 7, "2019": 5, "2023": 1, "207901": 17, "21": 19, "2186": 17, "21888": 17, "22": 19, "224": 9, "22672": 17, "229": 17, "23": 19, "233": 17, "236": 7, "24": 19, "246": 17, "249": 17, "25": 19, "2504": 19, "255": [8, 9, 11, 19], "256": 9, "257": 17, "26": 19, "26032": 17, "264": 13, "27": 19, "2700": 17, "2710": 19, "2749": 13, "28": 19, "287": 13, "29": 19, "296": 13, "299": 13, "2d": 19, "3": [4, 5, 8, 9, 10, 11, 18, 19], "30": [10, 19], "300": 17, "3000": 17, "301": 13, "30595": 19, "30ghz": 19, "31": 9, "32": [7, 9, 10, 13, 17, 18, 19], "3232421875": 19, "33": [10, 19], "33402": 17, "33608": 17, "34": [9, 19], "340": 19, "3456": 19, "3515625": 19, "36": 19, "360": 17, "37": [7, 19], "38": 19, "39": 19, "4": [7, 9, 10, 11, 19], "40": 19, "41": 19, "42": 19, "43": 19, "44": 19, "45": 19, "46": 19, "47": 19, "472": 17, "48": [7, 19], "49": 19, "49377": 17, "5": [6, 7, 10, 11, 16, 19], "50": [9, 11, 17, 19], "51": 19, "51171875": 19, "512": 9, "52": [7, 19], "529": 19, "53": 19, "54": 19, "540": 19, "5478515625": 19, "55": 19, "56": 19, "57": 19, "58": [7, 19], "580": 19, "5810546875": 19, "583": 19, "59": 19, "597": 19, "5k": [5, 7], "5m": 19, "6": [10, 19], "600": [9, 11, 19], "61": 19, "62": 19, "626": 17, "63": 19, "64": [9, 10, 19], "641": 19, "647": 17, "65": 19, "66": 19, "67": 19, "68": 19, "69": 19, "693": 13, "694": 13, "695": 13, "6m": 19, "7": 19, "70": [7, 11, 19], "707470": 17, "71": [7, 19], "7100000": 17, "7141797": 17, "7149": 17, "72": 19, "72dpi": 8, "73": 19, "73257": 17, "74": 19, "75": [10, 19], "7581382": 17, "76": 19, "77": 19, "772": 13, "772875": 17, "78": 19, "785": 13, "79": 19, "793533": 17, "796": 17, "798": 13, "7m": 19, "8": [9, 10, 11, 19], "80": 19, "800": [9, 11, 17, 19], "81": 19, "82": 19, "83": 19, "84": 19, "849": 17, "85": 19, "8564453125": 19, "857": 19, "85875": 17, "86": 19, "8603515625": 19, "87": 19, "8707": 17, "88": 19, "89": 19, "9": [10, 19], "90": 19, "90k": 7, "90kdict32px": 7, "91": 19, "914085328578949": 19, "92": 19, "93": 19, "94": [7, 19], "95": [11, 19], "9578408598899841": 19, "96": 19, "97": 19, "98": 19, "99": 19, "9949972033500671": 19, "A": [2, 3, 5, 6, 7, 8, 9, 12, 18], "As": 3, "Be": 19, "Being": 2, "By": 14, "For": [2, 3, 4, 13, 19], "If": [3, 8, 9, 13, 19], "In": [3, 7, 17], "It": [10, 15, 16, 18], "Its": [5, 9], "No": [2, 19], "Of": 7, "Or": [16, 18], "The": [2, 3, 7, 8, 11, 14, 16, 17, 18, 19], "Then": 9, "To": [3, 4, 14, 15, 16, 18, 19], "_": [2, 7, 9, 10], "__call__": 19, "_build": 3, "_i": 11, "abc": 18, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 7, "abdef": [7, 17], "abl": [17, 19], "about": [2, 17, 19], "abov": 19, "abstract": 1, "abstractdataset": 7, "abus": 2, "accept": 2, "access": [5, 8, 17, 19], "account": [2, 15], "accur": 19, "accuraci": 11, "achiev": 18, "act": 2, "action": 2, "activ": 5, "ad": [3, 9], "adapt": 2, "add": [10, 11, 15, 19], "add_hook": 19, "add_label": 11, "addit": [3, 4, 6, 8, 16, 19], "addition": [3, 19], "address": [2, 8], "advanc": 2, "advantag": 18, "advis": 3, "aesthet": [5, 7], "affect": 2, "after": [15, 19], "ag": 2, "again": 9, "aggreg": [11, 17], "aggress": 2, "align": [2, 8, 10], "all": [2, 3, 6, 7, 8, 10, 11, 16, 17, 19], "allow": [2, 18], "along": 19, "alreadi": [3, 18], "also": [2, 9, 15, 16, 17, 19], "alwai": 17, "an": [2, 3, 5, 7, 8, 9, 10, 11, 16, 18, 19], "analysi": [8, 16], "ancient_greek": 7, "andrej": 1, "angl": [8, 10], "ani": [2, 6, 7, 8, 9, 10, 11, 18, 19], "annot": 7, "anot": 17, "anoth": [9, 13, 17], "answer": 2, "anyascii": 11, "anyon": 5, "anyth": 16, "api": [3, 5], "apolog": 2, "apologi": 2, "app": 3, "appear": 2, "appli": [2, 7, 10], "applic": [5, 9], "appoint": 2, "appreci": 15, "appropri": [2, 3, 19], "ar": [2, 3, 4, 6, 7, 8, 10, 11, 12, 16, 17, 19], "arab": 7, "arabic_diacrit": 7, "arabic_lett": 7, "arabic_punctu": 7, "arbitrarili": [5, 9], "arch": [6, 9, 15], "architectur": [5, 6, 9, 15, 16], "area": 19, "arg": [7, 9], "argument": [6, 7, 8, 9, 11, 13, 19], "around": 2, "arrai": [7, 8, 10, 11], "art": [5, 16], "artefact": [6, 11, 16, 19], "artefact_typ": 8, "artefactdetector": 6, "articl": 1, "artifici": [5, 7], "arxiv": 9, "asarrai": 11, "ascii_lett": 7, "aspect": [5, 9, 10, 19], "assess": 11, "assign": 11, "associ": 8, "assum": 9, "assume_straight_pag": [9, 13, 19], "astyp": [9, 11, 19], "attack": 2, "attend": [5, 9], "attent": [2, 9], "autom": 5, "automat": 19, "autoregress": [5, 9], "avail": [2, 5, 6, 10], "averag": 19, "avoid": [2, 4], "aw": [5, 19], "awar": 19, "azur": 19, "b": [9, 11, 19], "b_j": 11, "back": 3, "backbon": 9, "backend": 19, "background": 17, "bangla": 7, "bar": 16, "bar_cod": 17, "baranovskij": 1, "base": [5, 9, 16], "baselin": [5, 9, 19], "batch": [6, 9, 10, 16, 17, 19], "batch_siz": [6, 9, 13, 16, 17, 18], "bblanchon": 4, "bbox": 19, "becaus": 14, "been": [3, 11, 17, 19], "befor": [9, 10, 19], "begin": 11, "behavior": [2, 19], "being": [11, 19], "belong": 19, "benchmark": 19, "best": [1, 2], "better": [12, 19], "between": [11, 19], "bgr": 8, "bilinear": 10, "bin_thresh": 19, "binar": [5, 9, 19], "binari": [8, 18, 19], "bit": 18, "blank": 11, "block": [11, 19], "block_1_1": 19, "blue": 11, "bmvc": 7, "bn": 15, "bodi": [2, 19], "bool": [7, 8, 9, 10, 11], "boolean": [9, 19], "both": [5, 7, 10, 17, 19], "bottom": [9, 19], "bound": [7, 8, 9, 11, 16, 17, 19], "box": [7, 8, 9, 10, 11, 16, 17, 19], "box_thresh": 19, "browser": [3, 5], "build": [3, 4, 18], "built": 3, "byte": [8, 19], "c": [4, 8, 11], "c_j": 11, "cach": [3, 7, 14], "cache_sampl": 7, "call": 18, "callabl": [7, 10], "can": [3, 4, 13, 14, 15, 16, 17, 19], "capabl": [3, 12, 19], "case": [7, 11], "cf": 19, "cfg": 19, "challeng": 7, "challenge2_test_task12_imag": 7, "challenge2_test_task1_gt": 7, "challenge2_training_task12_imag": 7, "challenge2_training_task1_gt": 7, "chang": [14, 19], "channel": [2, 3, 8, 10], "channel_prior": 4, "channelshuffl": 10, "charact": [5, 7, 8, 11, 17, 19], "charactergener": [7, 17], "characterist": 2, "charg": 19, "charset": 19, "chart": 8, "check": [3, 15, 19], "checkpoint": 9, "chip": 4, "christian": 1, "ci": 3, "clarifi": 2, "clariti": 2, "class": [2, 6, 7, 8, 10, 11, 19], "class_nam": 13, "classif": [17, 19], "classmethod": 8, "clear": 3, "clone": 4, "close": 3, "co": 15, "code": [5, 8, 16], "codecov": 3, "colab": 12, "collect": [8, 16], "color": [10, 11], "colorinvers": 10, "column": 8, "com": [2, 4, 8, 9, 15], "combin": 19, "command": [3, 16], "comment": 2, "commit": 2, "common": [2, 10, 11, 18], "commun": 2, "compar": 5, "comparison": [11, 19], "competit": 7, "compil": [12, 19], "complaint": 2, "complementari": 11, "complet": 3, "compon": 19, "compos": [7, 19], "comprehens": 19, "comput": [7, 11, 18, 19], "conf_threshold": [6, 16], "confid": [6, 8, 11, 19], "config": [4, 9], "configur": 9, "confus": 11, "consecut": [10, 19], "consequ": 2, "consid": [2, 3, 7, 8, 11, 19], "consist": 19, "consolid": [5, 7], "construct": 2, "contact": 2, "contain": [1, 6, 7, 12, 17, 19], "content": [7, 8, 11, 19], "context": 9, "contib": 4, "continu": 2, "contrib": [4, 16], "contribut": 2, "contributor": 3, "convers": 8, "convert": [7, 8, 10], "convert_target_to_rel": 7, "convolut": 9, "cool": 1, "coordin": [7, 8, 19], "cord": [5, 7, 17, 19], "core": [11, 19], "corner": 19, "correspond": [4, 8, 10, 19], "could": [2, 16], "counterpart": 11, "cover": 3, "coverag": 3, "cpu": [5, 13, 18], "creat": [1, 15], "crnn": [5, 9, 15], "crnn_mobilenet_v3_larg": [9, 15, 19], "crnn_mobilenet_v3_smal": [9, 18, 19], "crnn_vgg16_bn": [9, 13, 15, 19], "crop": [7, 8, 9, 10, 13, 17, 19], "crop_bboxes_from_imag": 7, "crop_orient": [8, 19], "crop_orientation_predictor": [9, 13], "crop_param": 13, "cuda": 18, "currenc": 7, "current": [3, 13, 19], "custom": [15, 16, 18, 19], "custom_crop_orientation_model": 13, "custom_page_orientation_model": 13, "customhook": 19, "cvit": 5, "czczup": 9, "czech": 7, "d": [7, 17], "danish": 7, "data": [5, 7, 8, 10, 11, 13, 15], "dataload": 17, "dataset": [9, 13, 19], "dataset_info": 7, "date": [13, 19], "db": 15, "db_mobilenet_v3_larg": [9, 15, 19], "db_resnet34": 19, "db_resnet50": [9, 13, 15, 19], "dbnet": [5, 9], "deal": [12, 19], "decis": 2, "decod": [7, 8], "decode_img_as_tensor": 8, "decode_sequ": 7, "dedic": 18, "deem": 2, "deep": [9, 19], "def": 19, "default": [4, 8, 13, 14, 19], "defer": 17, "defin": [11, 18], "degre": [8, 10, 19], "degress": 8, "delet": 3, "delimit": 19, "demo": [3, 5], "demonstr": 2, "depend": [3, 4, 5, 19], "deploi": 3, "deploy": 5, "derogatori": 2, "describ": 9, "descript": 12, "design": 10, "desir": 8, "det_arch": [9, 13, 15, 18], "det_b": 19, "det_model": [13, 15, 18], "det_param": 13, "det_predictor": [13, 19], "detail": [13, 19], "detect": [1, 6, 7, 8, 11, 12, 13, 16], "detect_languag": 9, "detect_orient": [9, 13, 19], "detection_predictor": [9, 19], "detection_task": [7, 17], "detectiondataset": [7, 17], "detectionmetr": 11, "detectionpredictor": [9, 13], "detector": [5, 6, 9, 16], "deterior": 9, "determin": 2, "dev": [3, 14], "develop": 4, "devic": 18, "dict": [7, 8, 11, 19], "dictionari": [7, 8, 11], "differ": 2, "differenti": [5, 9], "digit": [5, 7, 17], "dimens": [8, 11, 19], "direct": 7, "directli": [15, 19], "directori": [3, 14], "disabl": [2, 14, 19], "disable_crop_orient": 19, "disable_page_orient": 19, "disclaim": 19, "discuss": 3, "disparag": 2, "displai": [8, 11], "display_artefact": 11, "distribut": 10, "div": 19, "divers": 2, "divid": 8, "do": [3, 4, 9], "doc": [3, 6, 8, 16, 18, 19], "docartefact": [7, 17], "docstr": 3, "doctr": [1, 4, 13, 14, 15, 16, 17, 18, 19], "doctr_cache_dir": 14, "doctr_multiprocessing_dis": 14, "document": [1, 7, 9, 11, 12, 13, 16, 17, 18, 19], "documentbuild": 19, "documentfil": [6, 8, 13, 15, 16, 18], "doesn": 18, "don": [13, 19], "done": 10, "download": [7, 17], "download_from_url": 6, "downsiz": 9, "draw": [10, 11], "draw_proba": 11, "dtype": [8, 9, 10, 11, 18], "dual": [5, 7], "dummi": 15, "dummy_img": 19, "dummy_input": 18, "dure": 2, "dutch": 7, "dynam": [7, 16], "dynamic_seq_length": 7, "e": [2, 3, 4, 8, 9], "each": [5, 7, 8, 9, 11, 17, 19], "eas": 3, "easi": [5, 11, 15, 18], "easili": [8, 11, 13, 15, 17, 19], "econom": 2, "edit": 2, "educ": 2, "effect": 19, "effici": [3, 5, 7, 9], "either": [11, 19], "element": [7, 8, 9, 11, 19], "els": [3, 16], "email": 2, "empathi": 2, "en": 19, "enabl": [7, 8], "enclos": 8, "encod": [5, 7, 8, 9, 19], "encode_sequ": 7, "encode_str": 7, "encount": 3, "encrypt": 8, "end": [5, 7, 9, 11], "english": [7, 17], "enough": [3, 19], "ensur": 3, "entri": 7, "environ": [2, 14], "eo": 7, "equiv": 19, "estim": 9, "etc": [8, 16], "ethnic": 2, "evalu": [17, 19], "event": 2, "everyon": 2, "everyth": [3, 19], "exact": [11, 19], "exampl": [2, 3, 5, 7, 9, 15, 19], "exchang": 18, "execut": 19, "exist": 15, "expand": 10, "expect": [8, 10, 11], "experi": 2, "explan": [2, 19], "explicit": 2, "exploit": [5, 9], "export": [8, 9, 11, 12, 16, 19], "export_as_straight_box": [9, 19], "export_as_xml": 19, "export_model_to_onnx": 18, "express": [2, 10], "extens": 8, "extern": [2, 17], "extract": [1, 5, 7], "extractor": 9, "f_": 11, "f_a": 11, "factor": [10, 11], "fair": 2, "fairli": 2, "fals": [7, 8, 9, 10, 11, 13, 19], "famili": 11, "faq": 2, "fascan": 15, "fast": [5, 9], "fast_bas": [9, 19], "fast_smal": [9, 19], "fast_tini": [9, 19], "faster": [5, 9, 18], "fasterrcnn_mobilenet_v3_large_fpn": 9, "favorit": 19, "featur": [4, 9, 11, 12, 13, 16], "feedback": 2, "feel": [3, 15], "felix92": 15, "few": [18, 19], "figsiz": 11, "figur": [11, 16], "file": [3, 7], "final": 9, "find": [3, 17], "fine": 1, "finnish": 7, "first": [3, 7], "firsthand": 7, "fit": [9, 19], "flag": 19, "flip": 10, "float": [6, 8, 10, 11, 18], "float32": [8, 9, 10, 18], "focu": 15, "focus": [2, 7], "folder": 7, "follow": [2, 3, 4, 7, 10, 11, 13, 14, 15, 16, 19], "font": [7, 11], "font_famili": [7, 11], "foral": 11, "forc": 3, "forg": 4, "form": [5, 7, 19], "format": [8, 11, 13, 17, 18, 19], "forpost": [5, 7], "forum": 3, "found": 1, "fp16": 18, "frac": 11, "framework": [4, 15, 17, 19], "free": [2, 3, 15], "french": [7, 13, 15, 19], "friendli": 5, "from": [1, 2, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19], "from_hub": [9, 15], "from_imag": [6, 8, 15, 16, 18], "from_pdf": 8, "from_url": 8, "full": [11, 19], "function": [11, 16], "funsd": [5, 7, 17, 19], "further": 17, "futur": 7, "g": [8, 9], "g_": 11, "g_x": 11, "gallagh": 1, "gamma": 10, "gaussian": 10, "gaussiannois": 10, "gen": 19, "gender": 2, "gener": [3, 5, 8, 9], "generic_cyrillic_lett": 7, "geom": 7, "geometri": [5, 8, 19], "geq": 11, "german": [7, 13, 15], "get": [18, 19], "git": 15, "github": [3, 4, 9, 15], "give": [2, 16], "given": [7, 8, 10, 11, 19], "global": 9, "go": 19, "good": 18, "googl": 3, "googlevis": 5, "gpu": [5, 16, 18], "gracefulli": 2, "graph": [5, 7, 8], "grayscal": 10, "ground": 11, "groung": 11, "group": [5, 19], "gt": 11, "gt_box": 11, "gt_label": 11, "guid": 3, "guidanc": 17, "gvision": 19, "h": [8, 9, 10], "h_": 11, "ha": [3, 7, 11, 17, 19], "handl": [12, 17, 19], "handwrit": 7, "handwritten": 17, "harass": 2, "hardwar": 19, "harm": 2, "hat": 11, "have": [2, 3, 11, 13, 15, 17, 18, 19], "head": [9, 19], "healthi": 2, "hebrew": 7, "height": [8, 10], "hello": [11, 19], "help": 18, "here": [6, 10, 12, 16, 17, 19], "hf": 9, "hf_hub_download": 9, "high": 8, "higher": [4, 7, 19], "hindi": 7, "hindi_digit": 7, "hocr": 19, "hook": 19, "horizont": [8, 10, 19], "hous": 7, "how": [1, 3, 12, 13, 15, 17], "howev": 17, "html": [2, 3, 4, 8, 19], "http": [2, 4, 8, 9, 15, 19], "hub": 9, "huggingfac": 9, "hw": 7, "i": [2, 3, 7, 8, 9, 10, 11, 14, 15, 16, 17, 18], "i7": 19, "ibrahimov": 1, "ic03": [5, 7, 17], "ic13": [5, 7, 17], "icdar": [5, 7], "icdar2019": 7, "id": 19, "ident": 2, "identifi": 5, "iiit": [5, 7], "iiit5k": [7, 17], "iiithw": [5, 7, 17], "imag": [1, 5, 6, 7, 8, 9, 10, 11, 15, 16, 17, 19], "imagenet": 9, "imageri": 2, "images_90k_norm": 7, "imagetensor": 7, "imagetransform": 10, "img": [7, 17, 18], "img_cont": 8, "img_fold": [7, 17], "img_path": [7, 8], "img_transform": 7, "imgur5k": [5, 7, 17], "imgur5k_annot": 7, "imlist": 7, "impact": 2, "implement": [7, 8, 9, 10, 11, 19], "import": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "improv": 9, "inappropri": 2, "incid": 2, "includ": [2, 7, 17, 18], "inclus": 2, "independ": 10, "index": [3, 7, 8], "indic": 11, "individu": 2, "infer": [5, 9, 10, 16, 19], "inform": [1, 2, 3, 5, 7, 17], "initi": 19, "input": [3, 6, 7, 8, 9, 10, 18, 19], "input_crop": 9, "input_pag": [9, 11, 19], "input_seq": 7, "input_shap": [6, 18], "input_str": 7, "input_tensor": 9, "inspir": [2, 10], "instal": [15, 16, 18], "instanc": [2, 19], "instanti": [9, 19], "instead": [7, 8, 9], "insult": 2, "int": [6, 7, 8, 9, 10, 11], "int64": 11, "integ": 11, "integr": [1, 5, 15, 17], "intel": 19, "interact": [2, 8, 11], "interfac": [15, 18], "interoper": 18, "interpol": 10, "interpret": [7, 8], "intersect": [6, 11], "invert": 10, "investig": 2, "invis": 2, "involv": [2, 19], "io": [6, 13, 15, 16, 18], "iou": 11, "iou_thresh": 11, "iou_threshold": [6, 16], "irregular": [5, 9, 17], "issu": [2, 3, 15], "italian": 7, "iter": [7, 17, 19], "its": [8, 9, 10, 11, 17, 19], "itself": [9, 15], "j": 11, "jame": 1, "job": 3, "join": 3, "jpegqual": 10, "jpg": [6, 7, 8, 15, 18], "json": [7, 17, 19], "json_output": 19, "jump": 3, "just": 2, "kei": [5, 7], "kera": [9, 18], "kernel": [5, 9], "keywoard": 9, "keyword": [7, 8, 9, 11], "kie": [9, 13], "kie_predictor": [9, 13], "kiepredictor": 9, "kind": 2, "know": [3, 18], "kwarg": [6, 7, 8, 9, 11], "l": 11, "l_j": 11, "label": [6, 7, 11, 16, 17], "label_fil": [7, 17], "label_fold": 7, "label_path": [7, 17], "labels_path": [7, 17], "ladder": 2, "lang": 19, "languag": [2, 5, 7, 8, 9, 15, 19], "larg": [9, 15], "largest": 11, "last": 4, "latenc": 9, "later": 3, "latest": 19, "latin": 7, "layer": 18, "layout": 19, "lead": [2, 19], "leader": 2, "learn": [2, 5, 9, 18, 19], "least": 4, "left": [11, 19], "legacy_french": 7, "length": [7, 19], "less": [18, 19], "level": [2, 7, 11, 19], "leverag": 12, "lf": 15, "librari": [3, 4, 12, 13], "light": 5, "lightweight": 18, "like": 2, "limits_": 11, "line": [5, 9, 11, 19], "line_1_1": 19, "link": 13, "linknet": [5, 9], "linknet_resnet18": [9, 13, 18, 19], "linknet_resnet34": [9, 18, 19], "linknet_resnet50": [9, 19], "list": [6, 7, 8, 10, 11, 15], "ll": 11, "load": [5, 9, 16, 18, 19], "load_state_dict": 13, "load_weight": 13, "loc_pr": 19, "local": [3, 5, 7, 9, 11, 17, 19], "localis": 7, "localizationconfus": 11, "locat": [3, 8, 19], "login": 9, "login_to_hub": [9, 15], "logo": [8, 16, 17], "love": 15, "lower": [11, 19], "m": [3, 11, 19], "m1": 4, "macbook": 4, "machin": 18, "made": 5, "magc_resnet31": 9, "mai": [2, 3], "mail": 2, "main": 12, "maintain": 5, "mainten": 3, "make": [2, 3, 11, 13, 14, 15, 18, 19], "mani": [17, 19], "manipul": 19, "map": [7, 9], "map_loc": 13, "mask": 6, "mask_label": 6, "master": [5, 9, 19], "match": [11, 19], "mathcal": 11, "matplotlib": [8, 11], "max": [7, 11], "max_angl": 10, "max_area": 10, "max_char": [7, 17], "max_font_s": 11, "max_ratio": 10, "maximum": [7, 10, 11], "maxval": [9, 10], "mbox": 11, "mean": [10, 11, 13], "meaniou": 11, "meant": [8, 18], "measur": 19, "media": 2, "median": 9, "meet": 13, "member": 2, "memori": [14, 18], "mention": 19, "messag": 3, "meta": 19, "metadata": 18, "metal": 4, "method": [8, 10, 19], "metric": [11, 19], "middl": 19, "might": [18, 19], "min_area": 10, "min_char": [7, 17], "min_font_s": 11, "min_ratio": 10, "min_val": 10, "minde": [1, 2, 4, 5, 9], "minim": [3, 5], "minimalist": [5, 9], "minimum": [4, 7, 10, 11, 19], "minval": 10, "miss": 4, "mistak": 2, "mixed_float16": 18, "mixed_precis": 18, "mjsynth": [5, 7, 17], "mnt": 7, "mobilenet": [9, 15], "mobilenet_v3_larg": 9, "mobilenet_v3_large_r": 9, "mobilenet_v3_smal": [9, 13], "mobilenet_v3_small_crop_orient": [9, 13], "mobilenet_v3_small_page_orient": [9, 13], "mobilenet_v3_small_r": 9, "mobilenetv3": 9, "modal": [5, 7], "mode": 4, "model": [6, 7, 11, 14, 16, 17], "model_nam": [9, 15, 18], "model_path": [6, 16, 18], "moder": 2, "modif": 3, "modifi": [9, 14, 19], "modul": [4, 8, 9, 10, 11, 19], "more": [3, 17, 19], "moscardi": 1, "most": 19, "mozilla": 2, "multi": [5, 9], "multiclass": 7, "multilingu": [7, 15], "multipl": [7, 8, 19], "multiprocess": 14, "my": 9, "my_awesome_model": 15, "my_hook": 19, "n": [7, 11], "name": [7, 9, 18, 19], "nation": 2, "natur": [2, 5, 7], "ndarrai": [7, 8, 10, 11], "necessari": [4, 13, 14], "need": [3, 4, 7, 11, 13, 14, 15, 16, 19], "nest": 19, "netraj": 1, "network": [5, 7, 9, 18], "neural": [5, 7, 9, 18], "new": [3, 11], "next": 17, "nois": 10, "noisi": [5, 7], "non": [5, 7, 8, 9, 11], "none": [6, 7, 8, 9, 10, 11, 19], "normal": 9, "norwegian": 7, "note": [0, 3, 7, 9, 13, 15, 16, 18], "now": 3, "np": [9, 10, 11, 19], "num_sampl": [7, 17], "number": [7, 9, 11, 19], "numpi": [8, 9, 10, 11, 19], "o": 4, "obb": 16, "obj_detect": 15, "object": [7, 8, 11, 16, 19], "objectness_scor": [8, 19], "oblig": 2, "obtain": 19, "occupi": 18, "ocr": [1, 5, 7, 9, 11, 15], "ocr_carea": 19, "ocr_db_crnn": 11, "ocr_lin": 19, "ocr_pag": 19, "ocr_par": 19, "ocr_predictor": [9, 13, 15, 18, 19], "ocrdataset": [7, 17], "ocrmetr": 11, "ocrpredictor": [9, 13], "ocrx_word": 19, "offens": 2, "offici": [2, 9], "offlin": 2, "onc": 19, "one": [3, 7, 9, 10, 13, 15, 19], "oneof": 10, "ones": [7, 11], "onli": [3, 9, 10, 11, 13, 15, 17, 18, 19], "onlin": 2, "onnx": 16, "onnxruntim": [16, 18], "onnxtr": 18, "opac": 10, "opacity_rang": 10, "open": [1, 2, 3, 15, 18], "opinion": 2, "optic": [5, 19], "optim": [5, 19], "option": [7, 9, 13], "order": [3, 7, 8, 10], "org": [2, 9, 19], "organ": 8, "orient": [2, 8, 9, 12, 16, 19], "orientationpredictor": 9, "other": [2, 3], "otherwis": [2, 8, 11, 19], "our": [1, 3, 9, 19], "out": [3, 9, 10, 11, 19], "out_box": 10, "outpout": 19, "output": [8, 10, 18], "output_s": [8, 10], "outsid": 14, "over": [6, 7, 11, 19], "overal": [2, 9], "overlai": 8, "overview": 16, "overwrit": 13, "overwritten": 15, "own": 5, "p": [10, 11, 19], "packag": [3, 5, 11, 14, 16, 17, 18], "pad": [7, 9, 10, 19], "page": [4, 7, 9, 11, 13, 19], "page1": 8, "page2": 8, "page_1": 19, "page_idx": [8, 19], "page_orientation_predictor": [9, 13], "page_param": 13, "pair": 11, "paper": 9, "par_1_1": 19, "paragraph": 19, "paragraph_break": 19, "parallel": 9, "param": 19, "paramet": [5, 6, 7, 8, 9, 10, 11, 18], "pars": [5, 7], "parseq": [5, 9, 15, 18, 19], "part": [7, 10, 19], "parti": 4, "partial": 19, "particip": 2, "pass": [6, 8, 9, 13, 19], "password": 8, "patch": [9, 11], "path": [6, 7, 8, 16, 17, 18], "path_to_checkpoint": 13, "path_to_custom_model": 18, "path_to_pt": 13, "patil": 1, "pattern": 2, "pdf": [8, 9, 12], "pdfpage": 8, "peopl": 2, "per": 19, "perform": [5, 8, 9, 10, 11, 14, 18, 19], "period": 2, "permiss": 2, "permut": [5, 9], "persian_lett": 7, "person": [2, 17], "phase": 19, "photo": 17, "physic": [2, 8], "pick": 10, "pictur": 8, "pip": [3, 4, 16, 18], "pipelin": 19, "pixel": [8, 10, 19], "pleas": 3, "plot": 11, "plt": 11, "plug": 15, "plugin": 4, "png": 8, "point": 18, "polici": 14, "polish": 7, "polit": 2, "polygon": [7, 11, 19], "pool": 9, "portugues": 7, "posit": [2, 11], "possibl": [3, 11, 15, 19], "post": [2, 19], "postprocessor": 19, "potenti": 9, "power": 5, "ppageno": 19, "pre": [3, 9, 18], "pre_transform_multiclass": 7, "precis": [11, 19], "pred": 11, "pred_box": 11, "pred_label": 11, "predefin": [7, 17], "predict": [8, 9, 11, 19], "predictor": [5, 8, 9, 12, 13, 15, 18], "prefer": 17, "preinstal": 4, "preprocessor": [13, 19], "prerequisit": 15, "present": 12, "preserv": [9, 10, 19], "preserve_aspect_ratio": [8, 9, 10, 13, 19], "pretrain": [5, 9, 11, 13, 18, 19], "pretrained_backbon": [9, 13], "print": 19, "prior": 7, "privaci": 2, "privat": 2, "probabl": [1, 10], "problem": 3, "procedur": 10, "process": [3, 5, 8, 9, 13, 19], "processor": 19, "produc": [12, 19], "product": 18, "profession": 2, "project": [3, 17], "promptli": 2, "proper": 3, "properli": 7, "provid": [2, 3, 5, 15, 16, 17, 19], "public": [2, 5], "publicli": 19, "publish": 2, "pull": 15, "punctuat": 7, "pure": 7, "purpos": 3, "push_to_hf_hub": [9, 15], "py": 15, "pypdfium2": [4, 8], "pyplot": [8, 11], "python": [1, 3, 16], "python3": 15, "pytorch": [4, 5, 9, 10, 13, 15, 18, 19], "q": 3, "qr": [8, 16], "qr_code": 17, "question": 2, "quickli": 5, "quicktour": 12, "r": 19, "race": 2, "ramdisk": 7, "rand": [9, 10, 11, 18, 19], "random": [9, 10, 11, 19], "randomappli": 10, "randomcrop": 10, "randomhorizontalflip": 10, "randomli": 10, "randomres": 10, "randomrot": 10, "randomshadow": 10, "rang": 10, "rassi": 15, "ratio": [9, 10, 19], "raw": [8, 11], "re": 18, "read": [5, 7, 9], "read_html": 8, "read_img_as_numpi": 8, "read_img_as_tensor": 8, "read_pdf": 8, "readi": 18, "real": [1, 5, 9], "realli": 1, "reason": [2, 5, 7], "rebuild": 3, "rebuilt": 3, "recal": [11, 19], "receipt": [5, 7, 19], "reco_arch": [9, 13, 15, 18], "reco_b": 19, "reco_model": [13, 15, 18], "reco_param": 13, "reco_predictor": 13, "recogn": 19, "recognit": [7, 11, 12, 13], "recognition_predictor": [9, 19], "recognition_task": [7, 17], "recognitiondataset": [7, 17], "recognitionpredictor": [9, 13], "rectangular": 9, "red": 11, "reduc": 4, "refer": [3, 4, 13, 15, 16, 17, 19], "regardless": 2, "region": 19, "regroup": 11, "regular": 17, "reject": 2, "rel": [7, 8, 10, 11, 19], "relat": 8, "releas": [0, 4], "relev": 16, "religion": 2, "remov": 2, "render": [8, 19], "repo": 9, "repo_id": [9, 15], "report": 2, "repositori": [7, 9, 15], "repres": [2, 7, 11, 18, 19], "represent": [5, 9], "request": [2, 15], "requir": [4, 10, 18], "research": 5, "residu": 9, "resiz": [10, 19], "resnet": 9, "resnet18": [9, 15], "resnet31": 9, "resnet34": 9, "resnet50": [9, 15], "resolv": 8, "resolve_block": 19, "resolve_lin": 19, "resourc": 17, "respect": 2, "respons": 11, "rest": [3, 10, 11], "restrict": 14, "result": [3, 6, 7, 8, 12, 15, 18, 19], "return": [7, 8, 9, 11, 19], "reusabl": 19, "review": 2, "rgb": [8, 10], "rgb_mode": 8, "rgb_output": 8, "right": [2, 9, 11], "roboflow": 1, "robust": [5, 7], "root": 7, "rotat": [7, 8, 9, 10, 11, 12, 13, 17, 19], "run": [3, 4, 9], "same": [3, 8, 11, 17, 18, 19], "sampl": [7, 9, 17, 19], "sample_transform": 7, "samplecompos": 10, "sanjin": 1, "sar": [5, 9], "sar_resnet31": [9, 19], "save": [9, 17], "scale": [8, 9, 10, 11], "scale_rang": 10, "scan": [5, 7], "scene": [5, 7, 9], "score": [8, 11], "script": [3, 17], "seamless": 5, "seamlessli": [5, 19], "search": [1, 9], "searchabl": 12, "sec": 19, "second": 19, "section": [1, 13, 15, 16, 18, 19], "secur": [2, 14], "see": [2, 3], "seen": 19, "segment": [5, 9, 19], "self": 19, "semant": [5, 9], "send": 19, "sens": 11, "sensit": 17, "separ": 19, "sequenc": [5, 7, 8, 9, 11, 19], "sequenti": [10, 19], "seri": 2, "seriou": 2, "set": [2, 4, 7, 9, 11, 14, 16, 19], "set_global_polici": 18, "sever": [8, 10, 19], "sex": 2, "sexual": 2, "shade": 10, "shape": [5, 6, 7, 8, 9, 10, 11, 19], "share": [14, 17], "shift": 10, "shm": 14, "should": [3, 7, 8, 10, 11], "show": [5, 8, 9, 11, 13, 15, 16], "showcas": [3, 12], "shuffl": 10, "side": 11, "signatur": 8, "signific": 17, "simpl": [5, 9, 18], "simpler": 9, "sinc": [7, 17], "singl": [2, 3, 5, 7], "single_img_doc": 18, "size": [2, 6, 7, 8, 10, 11, 16, 19], "skew": 19, "slack": 3, "slightli": 9, "small": [3, 9, 19], "smallest": 8, "smooth": 11, "smoothing_factor": 11, "snapshot_download": 9, "snippet": 19, "so": [3, 4, 7, 9, 15, 17], "social": 2, "socio": 2, "some": [1, 4, 12, 15, 17], "someth": 3, "somewher": 3, "sort": 2, "sourc": [1, 6, 7, 8, 9, 10, 11, 15], "space": [2, 19], "span": 19, "spanish": 7, "spatial": [5, 7, 8], "specif": [3, 4, 11, 13, 17, 19], "specifi": [2, 7, 8], "speed": [5, 9, 19], "sphinx": 3, "sroie": [5, 7, 17], "stabl": 4, "stackoverflow": 3, "stage": 5, "standalon": 12, "start": 7, "state": [1, 5, 11, 16], "static": 11, "statist": 1, "statu": 2, "std": [10, 13], "step": 14, "still": 19, "str": [6, 7, 8, 9, 10, 11], "straight": [7, 9, 17, 19], "straighten": 19, "straighten_pag": [9, 13, 19], "straigten_pag": 13, "stream": 8, "street": [5, 7], "strict": 4, "strictli": 11, "string": [7, 8, 11, 19], "strive": 4, "strong": [5, 9], "structur": [18, 19], "subset": [7, 19], "suggest": [3, 15], "sum": 11, "summari": 11, "support": [4, 13, 16, 18, 19], "sustain": 2, "svhn": [5, 7, 17], "svt": [7, 17], "swedish": 7, "symmetr": [9, 10, 19], "symmetric_pad": [9, 10, 19], "synthes": 11, "synthesize_pag": 11, "synthet": 5, "synthtext": [5, 7, 17], "system": 19, "t": [3, 13, 18, 19], "tabl": [15, 16, 17], "take": [2, 7, 19], "target": [7, 8, 10, 11, 17], "target_s": 7, "task": [5, 7, 9, 15, 17, 19], "task2": 7, "team": 4, "techminde": 4, "templat": [3, 5], "tensor": [7, 8, 10, 19], "tensorflow": [4, 5, 8, 9, 10, 13, 15, 18, 19], "tensorspec": 18, "term": 2, "test": [7, 17], "test_set": 7, "text": [1, 7, 8, 9, 11, 17], "text_output": 19, "textmatch": 11, "textnet": 9, "textnet_bas": 9, "textnet_smal": 9, "textnet_tini": 9, "textract": [5, 19], "textstylebrush": [5, 7], "textual": [5, 7, 8, 9, 19], "tf": [4, 7, 8, 9, 10, 15, 18], "than": [3, 11, 15], "thank": 3, "thei": [2, 11], "them": [7, 19], "thi": [1, 2, 3, 4, 6, 7, 10, 11, 13, 14, 15, 17, 18, 19], "thing": [18, 19], "third": 4, "those": [2, 8, 19], "threaten": 2, "threshold": [6, 19], "through": [2, 10, 16, 17], "tilman": 15, "time": [1, 2, 5, 9, 11, 17], "tini": 9, "titl": [8, 19], "tm": 19, "tmp": 14, "togeth": [3, 8], "tool": [1, 17], "top": [11, 18, 19], "topic": 3, "torch": [4, 7, 10, 13, 15, 18], "torchvis": 10, "total": 13, "toward": [2, 4], "train": [3, 7, 9, 10, 15, 16, 17, 18, 19], "train_it": 17, "train_load": 17, "train_pytorch": 15, "train_set": [7, 17], "train_tensorflow": 15, "trainabl": [5, 9], "tranform": 10, "transcrib": 19, "transfer": [5, 7], "transfo": 10, "transform": [5, 7, 9], "translat": [2, 7], "troll": 2, "true": [7, 8, 9, 10, 11, 13, 14, 15, 17, 18, 19], "truth": 11, "tune": [1, 18], "tupl": [6, 7, 8, 10, 11], "turn": 10, "two": [8, 14], "txt": 7, "type": [8, 15, 18, 19], "typic": 19, "u": [2, 3], "ucsd": 7, "udac": 3, "uint8": [8, 9, 11, 19], "ukrainian": 7, "unaccept": 2, "underli": [17, 19], "underneath": 8, "understand": [5, 7, 19], "uniform": [9, 10], "uniformli": 10, "uninterrupt": [8, 19], "union": [6, 11], "unit": 1, "unittest": 3, "unknown": 7, "unknown_char": 7, "unlock": 8, "unoffici": 9, "unprofession": 2, "unsolicit": 2, "unsupervis": 5, "unwelcom": 2, "up": [9, 19], "updat": 11, "upgrad": 3, "upper": 7, "uppercas": 17, "url": 8, "us": [2, 3, 4, 6, 7, 9, 11, 12, 13, 14, 15, 16, 19], "usabl": 19, "usag": [14, 18], "use_polygon": [7, 11, 17], "useabl": 19, "useless": 19, "user": [5, 8, 12], "utf": 19, "util": 18, "v1": 15, "v3": [9, 15, 19], "valid": 17, "valu": [3, 8, 10, 19], "valuabl": 5, "variabl": 14, "varieti": 7, "veri": 9, "verma": 1, "version": [2, 3, 4, 18, 19], "vgg": 9, "vgg16": 15, "vgg16_bn_r": 9, "via": 2, "video": 1, "vietnames": 7, "view": [5, 7], "viewpoint": 2, "violat": 2, "visibl": 2, "vision": [5, 7, 9], "visiondataset": 7, "visiontransform": 9, "visual": [4, 5, 16], "visualize_pag": 11, "vit_": 9, "vit_b": 9, "vitstr": [5, 9, 18], "vitstr_bas": [9, 19], "vitstr_smal": [9, 13, 18, 19], "viz": 4, "vocab": [13, 15, 17, 18, 19], "vocab_nam": 7, "vocabulari": [7, 13, 15], "w": [8, 9, 10, 11], "w3": 19, "wa": 2, "wai": [2, 5, 17], "want": [3, 18, 19], "warmup": 19, "wasn": 3, "we": [1, 2, 3, 4, 5, 8, 10, 13, 15, 17, 18, 19], "weasyprint": 8, "web": [3, 8], "websit": 7, "weight": 19, "welcom": 2, "well": [1, 2, 18], "were": [2, 8, 19], "what": [1, 2], "when": [2, 3, 9], "whenev": 3, "where": [3, 8, 10, 11], "whether": [3, 7, 8, 10, 11, 17, 19], "which": [2, 9, 14, 16, 17, 19], "whichev": 4, "while": [10, 19], "why": 2, "width": [8, 10], "wiki": 2, "wildreceipt": [5, 7, 17], "window": [9, 11], "wish": 3, "within": 2, "without": [2, 7, 9], "wonder": 3, "word": [5, 7, 9, 11, 19], "word_1_1": 19, "word_1_2": 19, "word_1_3": 19, "wordgener": [7, 17], "words_onli": 11, "work": [1, 13, 14, 19], "workflow": 3, "worklow": 3, "world": [11, 19], "worth": 9, "would": 19, "wrap": [10, 19], "wrapper": 10, "write": 14, "written": [2, 8], "www": [2, 8, 19], "x": [8, 11], "x_ascend": 19, "x_descend": 19, "x_i": 11, "x_size": 19, "x_wconf": 19, "xhtml": 19, "xmax": 8, "xmin": 8, "xml": 19, "xml_bytes_str": 19, "xml_element": 19, "xml_output": 19, "xmln": 19, "y": 11, "y_i": 11, "y_j": 11, "yet": 16, "ymax": 8, "ymin": 8, "yolov8": 16, "yolov8_artefact": 6, "you": [3, 4, 7, 8, 9, 13, 14, 15, 16, 17, 18, 19], "your": [3, 5, 8, 11, 19], "yoursit": 8, "yugesh": 1, "zero": [10, 11], "zoo": 13, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 7, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 7, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 7, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 7, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 7, "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 7, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 7, "\u00e4\u00f6\u00e4\u00f6": 7, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 7, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 7, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 7, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 7, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": 7, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": 7, "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": 7, "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 7, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 7, "\u067e\u0686\u06a2\u06a4\u06af": 7, "\u0905": 7, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 7, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 7, "\u0950": 7, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 7, "\u09bd": 7, "\u09ce": 7, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 7}, "titles": ["Changelog", "Community resources", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 3, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 2], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 2], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": 0, "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 2], "31": 0, "4": [0, 2], "5": 0, "6": 0, "7": 0, "8": 0, "9": 0, "advanc": 19, "approach": 19, "architectur": 19, "artefact": 8, "artefactdetect": 16, "attribut": 2, "avail": [16, 17, 19], "aw": 14, "ban": 2, "block": 8, "bug": 3, "changelog": 0, "choos": [17, 19], "classif": [9, 13, 15], "code": [2, 3], "codebas": 3, "commit": 3, "commun": [1, 15], "compos": 10, "conda": 4, "conduct": 2, "connect": 3, "continu": 3, "contrib": 6, "contribut": [3, 6, 16], "contributor": 2, "convent": 15, "correct": 2, "coven": 2, "custom": [7, 13], "data": 17, "dataset": [5, 7, 17], "detect": [5, 9, 15, 17, 19], "develop": 3, "do": 19, "doctr": [3, 5, 6, 7, 8, 9, 10, 11, 12], "document": [3, 5, 8], "end": 19, "enforc": 2, "evalu": 11, "export": 18, "factori": 9, "featur": [3, 5], "feedback": 3, "file": 8, "from": 15, "gener": [7, 17], "git": 4, "guidelin": 2, "half": 18, "hub": 15, "huggingfac": 15, "i": 19, "infer": 18, "instal": [3, 4], "integr": [3, 16], "io": 8, "lambda": 14, "let": 3, "line": 8, "linux": 4, "load": [13, 15, 17], "loader": 7, "main": 5, "mode": 3, "model": [5, 9, 13, 15, 18, 19], "modifi": 3, "modul": [6, 16], "name": 15, "notebook": 12, "object": 17, "ocr": [17, 19], "onli": 4, "onnx": 18, "optim": 18, "option": 19, "orient": 13, "our": 2, "output": 19, "own": [13, 17], "packag": 4, "page": 8, "perman": 2, "pipelin": 16, "pledg": 2, "precis": 18, "predictor": 19, "prepar": 18, "prerequisit": 4, "pretrain": 15, "push": 15, "python": 4, "qualiti": 3, "question": 3, "read": 8, "readi": 17, "recognit": [5, 9, 15, 17, 19], "reconstitut": 11, "report": 3, "request": 3, "resourc": 1, "respons": 2, "right": 19, "scope": 2, "share": 15, "should": 19, "stage": 19, "standard": 2, "structur": [3, 8], "style": 3, "support": [5, 6, 7, 10], "synthet": [7, 17], "task": 11, "temporari": 2, "test": 3, "text": [5, 19], "train": 13, "transform": 10, "two": 19, "unit": 3, "us": [17, 18], "util": [7, 11], "v0": 0, "verif": 3, "via": 4, "visual": 11, "vocab": 7, "warn": 2, "what": 19, "word": 8, "your": [13, 15, 16, 17, 18], "zoo": [5, 9]}})
\ No newline at end of file
diff --git a/v0.6.0/using_doctr/using_models.html b/v0.6.0/using_doctr/using_models.html
index 9ead8498e1..2fd280b854 100644
--- a/v0.6.0/using_doctr/using_models.html
+++ b/v0.6.0/using_doctr/using_models.html
@@ -533,17 +533,16 @@ <h3>Detection predictors<a class="headerlink" href="#detection-predictors" title
 <p><a class="reference internal" href="../modules/models.html#doctr.models.detection.detection_predictor" title="doctr.models.detection.detection_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">detection_predictor</span></code></a> wraps your detection model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">800</span><span class="p">,</span> <span class="mi">600</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
 </div>
-<p>You can pass specific boolean arguments to the predictor:</p>
-<ul class="simple">
-<li><p><cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.</p></li>
-<li><p><cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.</p></li>
-<li><p><cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p></li>
-</ul>
+<p>You can pass specific boolean arguments to the predictor:
+* <cite>pretrained</cite>: if you want to use a model that has been pretrained on a specific dataset, setting <cite>pretrained=True</cite> this will load the corresponding weights. If <cite>pretrained=False</cite>, which is the default, would otherwise lead to a random initialization and would lead to no/useless results.
+* <cite>assume_straight_pages</cite>: if you work with straight documents only, it will fit straight bounding boxes to the text areas.
+* <cite>preserve_aspect_ratio</cite>: if you want to preserve the aspect ratio of your documents while resizing before sending them to the model.
+* <cite>symmetric_pad</cite>: if you choose to preserve the aspect ratio, it will pad the image symmetrically and not from the bottom-right.</p>
 <p>For instance, this snippet will instantiates a detection predictor able to detect text on rotated documents while preserving the aspect ratio:</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">detection_predictor</span>
 <span class="n">predictor</span> <span class="o">=</span> <span class="n">detection_predictor</span><span class="p">(</span><span class="s1">&#39;db_resnet50&#39;</span><span class="p">,</span> <span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">assume_straight_pages</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">preserve_aspect_ratio</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
@@ -767,7 +766,7 @@ <h3>Recognition predictors<a class="headerlink" href="#recognition-predictors" t
 <p><a class="reference internal" href="../modules/models.html#doctr.models.recognition.recognition_predictor" title="doctr.models.recognition.recognition_predictor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">recognition_predictor</span></code></a> wraps your recognition model to make it easily useable with your favorite deep learning framework seamlessly.</p>
 <div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">doctr.models</span> <span class="kn">import</span> <span class="n">recognition_predictor</span>
-<span class="n">predictor</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
+<span class="n">model</span> <span class="o">=</span> <span class="n">recognition_predictor</span><span class="p">(</span><span class="s1">&#39;crnn_vgg16_bn&#39;</span><span class="p">)</span>
 <span class="n">dummy_img</span> <span class="o">=</span> <span class="p">(</span><span class="mi">255</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">50</span><span class="p">,</span> <span class="mi">150</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span>
 <span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">([</span><span class="n">dummy_img</span><span class="p">])</span>
 </pre></div>
diff --git a/v0.7.0/searchindex.js b/v0.7.0/searchindex.js
index 23c213b0c9..ba92dfe1ad 100644
--- a/v0.7.0/searchindex.js
+++ b/v0.7.0/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"alltitles": {"1. Correction": [[1, "correction"]], "2. Warning": [[1, "warning"]], "3. Temporary Ban": [[1, "temporary-ban"]], "4. Permanent Ban": [[1, "permanent-ban"]], "AWS Lambda": [[12, null]], "Artefact": [[6, "artefact"]], "Attribution": [[1, "attribution"]], "Available Datasets": [[14, "available-datasets"]], "Available architectures": [[16, "available-architectures"], [16, "id1"], [16, "id2"]], "Block": [[6, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[14, null]], "Choosing the right model": [[16, null]], "Classification": [[13, "classification"]], "Code quality": [[2, "code-quality"]], "Code style verification": [[2, "code-style-verification"]], "Codebase structure": [[2, "codebase-structure"]], "Commits": [[2, "commits"]], "Composing transformations": [[8, "composing-transformations"]], "Continuous Integration": [[2, "continuous-integration"]], "Contributing to docTR": [[2, null]], "Contributor Covenant Code of Conduct": [[1, null]], "Custom dataset loader": [[5, "custom-dataset-loader"]], "Data Loading": [[14, "data-loading"]], "Dataloader": [[5, "dataloader"]], "Detection": [[13, "detection"], [14, "detection"]], "Detection predictors": [[16, "detection-predictors"]], "Developer mode installation": [[2, "developer-mode-installation"]], "Developing docTR": [[2, "developing-doctr"]], "Document": [[6, "document"]], "Document structure": [[6, "document-structure"]], "End-to-End OCR": [[16, "end-to-end-ocr"]], "Enforcement": [[1, "enforcement"]], "Enforcement Guidelines": [[1, "enforcement-guidelines"]], "Enforcement Responsibilities": [[1, "enforcement-responsibilities"]], "Export to ONNX": [[15, "export-to-onnx"]], "Feature requests & bug report": [[2, "feature-requests-bug-report"]], "Feedback": [[2, "feedback"]], "File reading": [[6, "file-reading"]], "Half-precision": [[15, "half-precision"]], "Installation": [[3, null]], "Let\u2019s connect": [[2, "let-s-connect"]], "Line": [[6, "line"]], "Loading from Huggingface Hub": [[13, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[11, "loading-your-custom-trained-model"]], "Main Features": [[4, "main-features"]], "Model optimization": [[15, "model-optimization"]], "Model zoo": [[4, "model-zoo"]], "Modifying the documentation": [[2, "modifying-the-documentation"]], "Naming conventions": [[13, "naming-conventions"]], "Object Detection": [[14, "object-detection"]], "Our Pledge": [[1, "our-pledge"]], "Our Standards": [[1, "our-standards"]], "Page": [[6, "page"]], "Preparing your model for inference": [[15, null]], "Prerequisites": [[3, "prerequisites"]], "Pretrained community models": [[13, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[13, "pushing-to-the-huggingface-hub"]], "Questions": [[2, "questions"]], "Recognition": [[13, "recognition"], [14, "recognition"]], "Recognition predictors": [[16, "recognition-predictors"]], "Scope": [[1, "scope"]], "Share your model with the community": [[13, null]], "Supported Vocabs": [[5, "supported-vocabs"]], "Supported datasets": [[4, "supported-datasets"]], "Supported transformations": [[8, "supported-transformations"]], "Synthetic dataset generator": [[5, "synthetic-dataset-generator"], [14, "synthetic-dataset-generator"]], "Task evaluation": [[9, "task-evaluation"]], "Text Detection": [[16, "text-detection"]], "Text Recognition": [[16, "text-recognition"]], "Text detection models": [[4, "text-detection-models"]], "Text recognition models": [[4, "text-recognition-models"]], "Train your own model": [[11, null]], "Two-stage approaches": [[16, "two-stage-approaches"]], "Unit tests": [[2, "unit-tests"]], "Use your own datasets": [[14, "use-your-own-datasets"]], "Using your ONNX exported model in docTR": [[15, "using-your-onnx-exported-model-in-doctr"]], "Via Git": [[3, "via-git"]], "Via Python Package": [[3, "via-python-package"]], "Visualization": [[9, "visualization"]], "What should I do with the output?": [[16, "what-should-i-do-with-the-output"]], "Word": [[6, "word"]], "docTR Notebooks": [[10, null]], "docTR Vocabs": [[5, "id5"]], "docTR: Document Text Recognition": [[4, null]], "doctr.datasets": [[5, null], [5, "datasets"]], "doctr.io": [[6, null]], "doctr.models": [[7, null]], "doctr.models.classification": [[7, "doctr-models-classification"]], "doctr.models.detection": [[7, "doctr-models-detection"]], "doctr.models.factory": [[7, "doctr-models-factory"]], "doctr.models.recognition": [[7, "doctr-models-recognition"]], "doctr.models.zoo": [[7, "doctr-models-zoo"]], "doctr.transforms": [[8, null]], "doctr.utils": [[9, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]]}, "docnames": ["changelog", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[6, "doctr.io.Artefact", false]], "block (class in doctr.io)": [[6, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms)": [[8, "doctr.transforms.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[5, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms)": [[8, "doctr.transforms.ColorInversion", false]], "compose (class in doctr.transforms)": [[8, "doctr.transforms.Compose", false]], "cord (class in doctr.datasets)": [[5, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[7, "doctr.models.classification.crop_orientation_predictor", false]], "dataloader (class in doctr.datasets.loader)": [[5, "doctr.datasets.loader.DataLoader", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[7, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[7, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[6, "doctr.io.decode_img_as_tensor", false]], "detection_predictor() (in module doctr.models.detection)": [[7, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[5, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[5, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[6, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[6, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[5, "doctr.datasets.encode_sequences", false]], "from_hub() (in module doctr.models.factory)": [[7, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[6, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[6, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[6, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[5, "doctr.datasets.FUNSD", false]], "gaussianblur (class in doctr.transforms)": [[8, "doctr.transforms.GaussianBlur", false]], "gaussiannoise (class in doctr.transforms)": [[8, "doctr.transforms.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[5, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[5, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[5, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[5, "doctr.datasets.IIITHWS", false]], "imgur5k (class in doctr.datasets)": [[5, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[7, "doctr.models.kie_predictor", false]], "lambdatransformation (class in doctr.transforms)": [[8, "doctr.transforms.LambdaTransformation", false]], "line (class in doctr.io)": [[6, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[7, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet18_rotation() (in module doctr.models.detection)": [[7, "doctr.models.detection.linknet_resnet18_rotation", false]], "linknet_resnet34() (in module doctr.models.detection)": [[7, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[7, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[7, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[7, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[5, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_orientation() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_small_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_small_r", false]], "normalize (class in doctr.transforms)": [[8, "doctr.transforms.Normalize", false]], "ocr_predictor() (in module doctr.models)": [[7, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[5, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms)": [[8, "doctr.transforms.OneOf", false]], "page (class in doctr.io)": [[6, "doctr.io.Page", false]], "parseq() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.parseq", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[7, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms)": [[8, "doctr.transforms.RandomApply", false]], "randombrightness (class in doctr.transforms)": [[8, "doctr.transforms.RandomBrightness", false]], "randomcontrast (class in doctr.transforms)": [[8, "doctr.transforms.RandomContrast", false]], "randomcrop (class in doctr.transforms)": [[8, "doctr.transforms.RandomCrop", false]], "randomgamma (class in doctr.transforms)": [[8, "doctr.transforms.RandomGamma", false]], "randomhorizontalflip (class in doctr.transforms)": [[8, "doctr.transforms.RandomHorizontalFlip", false]], "randomhue (class in doctr.transforms)": [[8, "doctr.transforms.RandomHue", false]], "randomjpegquality (class in doctr.transforms)": [[8, "doctr.transforms.RandomJpegQuality", false]], "randomrotate (class in doctr.transforms)": [[8, "doctr.transforms.RandomRotate", false]], "randomsaturation (class in doctr.transforms)": [[8, "doctr.transforms.RandomSaturation", false]], "randomshadow (class in doctr.transforms)": [[8, "doctr.transforms.RandomShadow", false]], "read_html() (in module doctr.io)": [[6, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[6, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[6, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[6, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[5, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms)": [[8, "doctr.transforms.Resize", false]], "resnet18() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet50", false]], "sar_resnet31() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[6, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[6, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[5, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[9, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[9, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[9, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[9, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[5, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[5, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.visualization)": [[9, "doctr.utils.visualization.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[5, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.TextMatch", false]], "togray (class in doctr.transforms)": [[8, "doctr.transforms.ToGray", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[9, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[9, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[9, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[9, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[7, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[9, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[7, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[7, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.vitstr_small", false]], "word (class in doctr.io)": [[6, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[5, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.datasets": [[5, 0, 1, "", "CORD"], [5, 0, 1, "", "CharacterGenerator"], [5, 0, 1, "", "DetectionDataset"], [5, 0, 1, "", "DocArtefacts"], [5, 0, 1, "", "FUNSD"], [5, 0, 1, "", "IC03"], [5, 0, 1, "", "IC13"], [5, 0, 1, "", "IIIT5K"], [5, 0, 1, "", "IIITHWS"], [5, 0, 1, "", "IMGUR5K"], [5, 0, 1, "", "MJSynth"], [5, 0, 1, "", "OCRDataset"], [5, 0, 1, "", "RecognitionDataset"], [5, 0, 1, "", "SROIE"], [5, 0, 1, "", "SVHN"], [5, 0, 1, "", "SVT"], [5, 0, 1, "", "SynthText"], [5, 0, 1, "", "WordGenerator"], [5, 1, 1, "", "encode_sequences"]], "doctr.datasets.loader": [[5, 0, 1, "", "DataLoader"]], "doctr.io": [[6, 0, 1, "", "Artefact"], [6, 0, 1, "", "Block"], [6, 0, 1, "", "Document"], [6, 0, 1, "", "DocumentFile"], [6, 0, 1, "", "Line"], [6, 0, 1, "", "Page"], [6, 0, 1, "", "Word"], [6, 1, 1, "", "decode_img_as_tensor"], [6, 1, 1, "", "read_html"], [6, 1, 1, "", "read_img_as_numpy"], [6, 1, 1, "", "read_img_as_tensor"], [6, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[6, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[6, 2, 1, "", "from_images"], [6, 2, 1, "", "from_pdf"], [6, 2, 1, "", "from_url"]], "doctr.io.Page": [[6, 2, 1, "", "show"]], "doctr.models": [[7, 1, 1, "", "kie_predictor"], [7, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[7, 1, 1, "", "crop_orientation_predictor"], [7, 1, 1, "", "magc_resnet31"], [7, 1, 1, "", "mobilenet_v3_large"], [7, 1, 1, "", "mobilenet_v3_large_r"], [7, 1, 1, "", "mobilenet_v3_small"], [7, 1, 1, "", "mobilenet_v3_small_orientation"], [7, 1, 1, "", "mobilenet_v3_small_r"], [7, 1, 1, "", "resnet18"], [7, 1, 1, "", "resnet31"], [7, 1, 1, "", "resnet34"], [7, 1, 1, "", "resnet50"], [7, 1, 1, "", "vgg16_bn_r"], [7, 1, 1, "", "vit_b"], [7, 1, 1, "", "vit_s"]], "doctr.models.detection": [[7, 1, 1, "", "db_mobilenet_v3_large"], [7, 1, 1, "", "db_resnet50"], [7, 1, 1, "", "detection_predictor"], [7, 1, 1, "", "linknet_resnet18"], [7, 1, 1, "", "linknet_resnet18_rotation"], [7, 1, 1, "", "linknet_resnet34"], [7, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[7, 1, 1, "", "from_hub"], [7, 1, 1, "", "login_to_hub"], [7, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[7, 1, 1, "", "crnn_mobilenet_v3_large"], [7, 1, 1, "", "crnn_mobilenet_v3_small"], [7, 1, 1, "", "crnn_vgg16_bn"], [7, 1, 1, "", "master"], [7, 1, 1, "", "parseq"], [7, 1, 1, "", "recognition_predictor"], [7, 1, 1, "", "sar_resnet31"], [7, 1, 1, "", "vitstr_base"], [7, 1, 1, "", "vitstr_small"]], "doctr.transforms": [[8, 0, 1, "", "ChannelShuffle"], [8, 0, 1, "", "ColorInversion"], [8, 0, 1, "", "Compose"], [8, 0, 1, "", "GaussianBlur"], [8, 0, 1, "", "GaussianNoise"], [8, 0, 1, "", "LambdaTransformation"], [8, 0, 1, "", "Normalize"], [8, 0, 1, "", "OneOf"], [8, 0, 1, "", "RandomApply"], [8, 0, 1, "", "RandomBrightness"], [8, 0, 1, "", "RandomContrast"], [8, 0, 1, "", "RandomCrop"], [8, 0, 1, "", "RandomGamma"], [8, 0, 1, "", "RandomHorizontalFlip"], [8, 0, 1, "", "RandomHue"], [8, 0, 1, "", "RandomJpegQuality"], [8, 0, 1, "", "RandomRotate"], [8, 0, 1, "", "RandomSaturation"], [8, 0, 1, "", "RandomShadow"], [8, 0, 1, "", "Resize"], [8, 0, 1, "", "ToGray"]], "doctr.utils.metrics": [[9, 0, 1, "", "DetectionMetric"], [9, 0, 1, "", "LocalizationConfusion"], [9, 0, 1, "", "OCRMetric"], [9, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.visualization": [[9, 1, 1, "", "synthesize_page"], [9, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [1, 6, 7, 9, 13], "0": [1, 3, 5, 8, 9, 11, 14, 16], "00": 16, "01": 16, "0123456789": 5, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 5, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 5, "02": 16, "02562": 7, "03": 16, "035": [], "0361328125": 16, "04": [], "05": 16, "06": 16, "06640625": 16, "07": 16, "08": [8, 16], "09": 16, "0966796875": 16, "1": [3, 5, 6, 7, 8, 9, 11, 14, 16], "10": [5, 9, 16], "100": [5, 8, 9, 14, 16], "1000": 16, "101": 5, "1024": [7, 9, 11, 16], "104": [], "106": [], "108": 5, "1095": 14, "11": 16, "110": 9, "1107": 14, "114": [], "115": [], "1156": 14, "116": 5, "118": [], "11800h": 16, "11th": 16, "12": [3, 16], "120": [], "123": 5, "126": 5, "1268": [], "128": [7, 11, 15, 16], "13": [9, 16], "130": 5, "13068": 14, "131": 5, "1337891": 14, "1357421875": 16, "1396484375": 16, "14": 16, "1420": 16, "149": 14, "15": 16, "150": [9, 16], "1552": 16, "16": [7, 15], "1630859375": 16, "1684": 16, "16x16": 7, "17": 16, "1778": 16, "1782": 16, "18": [7, 16], "185546875": 16, "1900": 16, "1910": 7, "19342": 14, "19370": 14, "195": [], "19598": [], "199": 16, "1999": 16, "2": [3, 4, 5, 6, 8, 16], "20": [], "200": 9, "2000": 14, "2003": [4, 5], "2012": 5, "2013": [4, 5], "2015": 5, "2019": 4, "2023": [], "207901": 14, "21": 16, "2186": 14, "21888": 14, "22": 16, "224": [7, 8], "225": 8, "22672": 14, "229": [8, 14], "23": 16, "233": 14, "234": 5, "236": [], "24": 16, "246": 14, "249": 14, "25": 16, "2504": 16, "255": [6, 7, 8, 9, 16], "256": 7, "257": 14, "26": [], "26032": 14, "264": 11, "27": 16, "2700": 14, "2710": 16, "2749": 11, "28": 16, "287": 11, "29": 16, "296": 11, "299": 11, "2d": 16, "3": [3, 4, 6, 7, 8, 9, 15, 16], "30": 16, "300": 14, "3000": 14, "301": 11, "30595": 16, "30ghz": 16, "31": [7, 16], "32": [5, 7, 8, 11, 14, 15, 16], "3232421875": 16, "33": 8, "33402": 14, "33608": 14, "34": [7, 16], "340": 16, "3456": 16, "35": 16, "3515625": 16, "36": [], "360": 14, "37": [5, 16], "38": 16, "39": [], "4": [7, 8, 9, 16], "40": 16, "406": 8, "41": 16, "42": 16, "43": 16, "44": 16, "45": 16, "456": 8, "46": 16, "47": 16, "472": [], "48": [5, 16], "485": 8, "49": [], "49377": [], "5": [5, 8, 9, 16], "50": [7, 14, 16], "51": 16, "51171875": 16, "512": 7, "52": [5, 16], "529": 16, "53": 16, "54": 16, "540": 16, "5478515625": 16, "55": 16, "56": 16, "57": 16, "58": 16, "580": 16, "5810546875": 16, "583": 16, "59": 16, "597": 16, "5k": [4, 5], "5m": [], "6": [8, 16], "60": 8, "600": [7, 9, 16], "61": 16, "62": 16, "626": 14, "63": 16, "64": [7, 8, 16], "641": 16, "647": 14, "65": 16, "66": 16, "67": 16, "68": 16, "69": 16, "693": 11, "694": 11, "695": 11, "6m": [], "7": 16, "70": [9, 16], "707470": 14, "71": 16, "7100000": 14, "7141797": 14, "7149": 14, "72": 16, "72dpi": 6, "73": 16, "73257": 14, "74": 16, "75": [8, 16], "7581382": 14, "76": 16, "77": 16, "772": 11, "772875": 14, "78": 16, "785": 11, "79": 16, "793533": 14, "796": 14, "798": 11, "7m": [], "8": [3, 7, 8, 16], "80": 16, "800": [7, 9, 14, 16], "81": 16, "82": 16, "83": 16, "84": 16, "849": 14, "85": 16, "8564453125": 16, "857": 16, "85875": 14, "86": 16, "8603515625": 16, "87": 16, "8707": 14, "88": 16, "89": 16, "9": 16, "90": 16, "90k": 5, "90kdict32px": 5, "91": 16, "914085328578949": 16, "92": 16, "93": 16, "94": [5, 16], "95": [9, 16], "9578408598899841": 16, "96": 16, "97": 16, "98": 16, "99": 16, "9949972033500671": 16, "A": [1, 2, 4, 5, 6, 7, 10, 15], "As": 2, "Be": [], "Being": 1, "By": 12, "For": [1, 2, 3, 11, 16], "If": [2, 3, 6, 7, 11, 16], "In": [2, 5, 14], "It": [8, 13, 15], "Its": [4, 7], "No": [1, 16], "Of": 5, "Or": [], "The": [1, 2, 5, 6, 9, 12, 16], "Then": [], "To": [2, 3, 12, 13, 16], "_": [1, 5, 7], "__call__": [], "_build": 2, "_i": 9, "abc": [], "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 5, "abdef": [5, 14], "abl": [14, 16], "about": [1, 14, 16], "abov": 16, "abstract": [], "abstractdataset": 5, "abus": 1, "accept": 1, "access": [4, 6, 14, 16], "account": [1, 13], "accur": [], "accuraci": 9, "achiev": 15, "act": 1, "action": 1, "activ": 4, "ad": [2, 7, 8], "adapt": 1, "add": [8, 9, 13], "add_hook": [], "add_label": 9, "addit": [2, 3, 6], "addition": [2, 16], "address": [1, 6], "adjust": 8, "advanc": 1, "advantag": 15, "advis": 2, "aesthet": [4, 5], "affect": 1, "after": [13, 16], "ag": 1, "again": [], "aggreg": [9, 14], "aggress": 1, "align": [1, 6], "all": [1, 2, 5, 6, 8, 9, 14, 16], "allow": 1, "along": 16, "alreadi": 2, "also": [1, 7, 13, 14, 16], "alwai": 14, "an": [1, 2, 4, 5, 6, 7, 9, 15, 16], "analysi": 6, "ancient_greek": 5, "andrej": [], "angl": [6, 8], "ani": [1, 5, 6, 7, 8, 9, 16], "annot": 5, "anot": 14, "anoth": [3, 7, 11, 14], "answer": 1, "anyascii": [], "anyon": 4, "anyth": [], "api": [2, 4], "apolog": 1, "apologi": 1, "app": 2, "appear": 1, "appli": [1, 5, 8], "applic": [4, 7], "appoint": 1, "appreci": 13, "appropri": [1, 2, 16], "ar": [1, 2, 3, 5, 6, 8, 9, 10, 14, 16], "arab": 5, "arabic_diacrit": 5, "arabic_lett": 5, "arabic_punctu": 5, "arbitrarili": [], "arch": [7, 13], "architectur": [4, 7, 13], "area": 16, "arg": [5, 7], "argument": [5, 7, 16], "around": 1, "arrai": [6, 8, 9], "art": 4, "artefact": [9, 10, 16], "artefact_typ": 6, "artefactdetector": [], "articl": [], "artifici": [4, 5], "arxiv": 7, "asarrai": 9, "ascii_lett": 5, "aspect": [4, 7, 8, 16], "assess": 9, "assign": 9, "associ": 6, "assum": 7, "assume_straight_pag": [7, 16], "astyp": [7, 9, 16], "attack": 1, "attend": [4, 7], "attent": [1, 7], "autom": 4, "automat": [], "autoregress": [4, 7], "avail": [1, 4, 8], "averag": [8, 16], "avoid": [1, 3], "aw": [4, 16], "awar": [], "azur": 16, "b": [7, 9, 16], "b_j": 9, "back": 2, "backbon": 7, "backend": 16, "background": 14, "bangla": [], "bar": [], "bar_cod": 14, "baranovskij": [], "base": [4, 7], "baselin": [4, 7, 16], "batch": [5, 7, 8, 14, 16], "batch_siz": [5, 11, 14, 15], "bblanchon": [], "bbox": 16, "becaus": 12, "been": [2, 9, 14, 16], "befor": [5, 7, 8, 16], "begin": 9, "behavior": 1, "being": [9, 16], "belong": 16, "benchmark": 16, "best": 1, "better": [10, 16], "between": [8, 9], "bgr": 6, "bilinear": 8, "bin_thresh": [], "binar": [4, 7], "binari": [6, 15, 16], "bit": 15, "blank": 9, "block": [9, 16], "block_1_1": 16, "blue": 9, "blur": 8, "bmvc": 5, "bn": 13, "bodi": [1, 16], "bool": [5, 6, 7, 8, 9], "boolean": [7, 16], "both": [4, 5, 8, 14, 16], "bottom": [7, 16], "bound": [5, 6, 7, 8, 9, 16], "box": [5, 6, 7, 8, 9, 14, 16], "box_thresh": [], "brew": 3, "bright": 8, "broadcast": 9, "browser": [2, 4], "build": [2, 3], "built": 2, "byte": [6, 16], "c": [6, 9], "c_j": 9, "cach": [2, 5, 12], "cache_sampl": 5, "cairo": 3, "call": [], "callabl": [5, 8], "can": [2, 3, 11, 12, 13, 14, 16], "capabl": [2, 10, 16], "case": [5, 9], "cf": 16, "cfg": 16, "challeng": 5, "challenge2_test_task12_imag": 5, "challenge2_test_task1_gt": 5, "challenge2_training_task12_imag": 5, "challenge2_training_task1_gt": 5, "chang": 12, "channel": [1, 2, 6, 8], "channel_prior": [], "channelshuffl": 8, "charact": [4, 5, 6, 9, 14, 16], "charactergener": [5, 14], "characterist": 1, "charg": 16, "charset": 16, "chart": 6, "check": [2, 13, 16], "checkpoint": 7, "chip": 3, "christian": [], "ci": 2, "clarifi": 1, "clariti": 1, "class": [1, 5, 6, 8, 9, 16], "class_nam": 11, "classif": 14, "classif_mobilenet_v3_smal": 7, "classmethod": 6, "clear": 2, "clone": 3, "close": 2, "co": 13, "code": [4, 6], "codecov": 2, "colab": 10, "collate_fn": 5, "collect": 6, "color": [8, 9], "colorinvers": 8, "column": 6, "com": [1, 3, 6, 13], "combin": 16, "come": 15, "command": 2, "comment": 1, "commit": 1, "common": [1, 8, 9, 15], "commun": 1, "compar": 4, "comparison": [9, 16], "competit": 5, "compil": [10, 16], "complaint": 1, "complementari": 9, "complet": 2, "compon": 16, "compos": [5, 16], "comprehens": 16, "comput": [5, 9, 15, 16], "conf_threshold": [], "confid": [6, 9, 16], "config": 7, "configur": 7, "confus": 9, "consecut": [8, 16], "consequ": 1, "consid": [1, 2, 5, 6, 9, 16], "consist": 16, "consolid": [4, 5], "constant": 8, "construct": 1, "consum": 9, "contact": 1, "contain": [5, 14], "content": [5, 6, 9, 16], "context": 7, "contib": [], "continu": 1, "contrast": 8, "contrast_factor": 8, "contrib": [], "contribut": 1, "contributor": 2, "convers": 6, "convert": [6, 8], "convert_target_to_rel": [], "convolut": 7, "cool": [], "coordin": [6, 16], "cord": [4, 5, 14, 16], "core": [9, 16], "corner": 16, "correct": 8, "correspond": [3, 6, 16], "could": 1, "counterpart": 9, "cover": 2, "coverag": 2, "cpu": [4, 11], "creat": 13, "crnn": [4, 7, 13], "crnn_mobilenet_v3_larg": [7, 13, 16], "crnn_mobilenet_v3_smal": [7, 15, 16], "crnn_vgg16_bn": [7, 11, 13, 16], "crop": [7, 8, 14, 16], "crop_bboxes_from_imag": [], "crop_orient": [], "crop_orientation_predictor": 7, "crop_param": [], "croporientationpredictor": 7, "cuda": 15, "currenc": 5, "current": [2, 16], "custom": 13, "custom_crop_orientation_model": [], "custom_page_orientation_model": [], "customhook": [], "cvit": 4, "czczup": [], "czech": 5, "d": [5, 14], "danish": [], "data": [4, 5, 6, 8, 9, 11, 13], "dataload": 14, "dataset": [7, 11, 16], "dataset_info": 5, "date": [11, 16], "db": 13, "db_mobilenet_v3_larg": [7, 13, 16], "db_resnet34": 16, "db_resnet50": [7, 11, 13, 16], "db_resnet50_rot": 16, "dbnet": [4, 7], "deal": [], "decis": 1, "decod": 6, "decode_img_as_tensor": 6, "decode_sequ": [], "dedic": [], "deem": 1, "deep": [7, 16], "def": [], "default": [6, 9, 11, 12], "defer": 14, "defin": [9, 15], "degre": 8, "degress": 6, "delet": 2, "delimit": 16, "delta": 8, "demo": [2, 4], "demonstr": 1, "depend": [2, 3, 4], "deploi": 2, "deploy": 4, "derogatori": 1, "describ": [7, 9], "descript": 10, "design": 8, "desir": 6, "det_arch": [7, 11, 13, 15], "det_b": [], "det_model": [11, 13], "det_param": 11, "det_predictor": 11, "detail": [11, 16], "detect": [5, 9, 10, 11], "detect_languag": 7, "detect_orient": 7, "detection_predictor": [7, 16], "detection_task": [], "detectiondataset": [5, 14], "detectionmetr": 9, "detectionpredictor": [7, 11], "detector": [], "deterior": 7, "determin": 1, "dev": [2, 12], "develop": 3, "deviat": 8, "devic": 15, "dict": [6, 9, 16], "dictionari": [6, 9], "differ": 1, "differenti": [4, 7], "digit": [4, 5, 14], "dimens": [6, 9, 16], "dimension": 8, "direct": 5, "directli": [13, 16], "directori": [2, 12], "disabl": [1, 12], "disable_crop_orient": [], "disable_page_orient": [], "disclaim": 16, "discuss": 2, "disparag": 1, "displai": [6, 9], "display_artefact": 9, "distribut": 8, "div": 16, "divers": 1, "divid": 6, "do": [2, 3, 7], "doc": [2, 6, 15, 16], "docartefact": [5, 14], "docstr": 2, "doctr": [3, 11, 12, 13, 14, 16], "doctr_cache_dir": 12, "doctr_multiprocessing_dis": 12, "document": [5, 7, 9, 10, 14, 16], "documentbuild": [], "documentfil": [6, 13], "doesn": [], "don": [11, 16], "done": 8, "download": [5, 14], "download_from_url": [], "downsiz": 7, "draw": [8, 9], "draw_proba": 9, "drop": 5, "drop_last": 5, "dtype": [6, 7, 8, 9, 15], "dual": [], "dummi": 13, "dummy_img": 16, "dummy_input": 15, "dure": 1, "dutch": [], "dynam": 5, "dynamic_seq_length": 5, "e": [1, 2, 3, 6, 7], "each": [4, 5, 6, 7, 8, 9, 14, 16], "eas": 2, "easi": [4, 9, 13], "easili": [6, 9, 11, 13, 14, 16], "econom": 1, "edit": 1, "educ": 1, "effect": [], "effici": [2, 4, 5, 7], "either": [9, 16], "element": [5, 6, 7, 9, 16], "els": 2, "email": 1, "empathi": 1, "en": 16, "enabl": [5, 6], "enclos": 6, "encod": [4, 5, 6, 7, 16], "encode_sequ": 5, "encode_str": [], "encount": 2, "encrypt": 6, "end": [4, 5, 7, 9], "english": [5, 14], "enough": [2, 16], "ensur": 2, "entri": 5, "environ": [1, 12], "eo": 5, "equiv": 16, "estim": 7, "etc": 6, "ethnic": 1, "evalu": [14, 16], "event": 1, "everyon": 1, "everyth": [2, 16], "exact": [9, 16], "exampl": [1, 2, 4, 5, 7, 13], "exchang": 15, "execut": [], "exist": 13, "expand": 8, "expect": [6, 8, 9], "experi": 1, "explan": [1, 16], "explicit": 1, "exploit": [4, 7], "export": [6, 7, 9, 10, 16], "export_as_straight_box": [7, 16], "export_as_xml": 16, "export_model_to_onnx": 15, "express": [1, 8], "extens": 6, "extern": [1, 14], "extra": 3, "extract": [4, 5], "extractor": 7, "f_": 9, "f_a": 9, "factor": 8, "fair": 1, "fairli": 1, "fals": [5, 6, 7, 8, 9, 11, 16], "famili": 9, "faq": 1, "fascan": [], "fast": [4, 5, 7], "fast_bas": [], "fast_smal": [], "fast_tini": [], "faster": 15, "fasterrcnn_mobilenet_v3_large_fpn": 7, "favorit": 16, "featur": [3, 7, 9, 10], "feedback": 1, "feel": [2, 13], "felix92": 13, "few": [3, 15], "figsiz": 9, "figur": 9, "file": [2, 5], "final": 7, "find": [2, 3, 14], "fine": [], "finnish": [], "first": 2, "firsthand": 5, "fit": [7, 16], "flag": 16, "flip": 8, "float": [6, 8, 9, 15], "float32": [6, 7, 8, 15], "fn": 8, "focu": 13, "focus": [1, 5], "folder": 5, "follow": [1, 2, 3, 5, 8, 9, 11, 12, 13, 16], "font": [5, 9], "font_famili": [5, 9], "font_siz": 9, "foral": 9, "forc": 2, "forg": [], "form": [4, 5, 16], "format": [6, 9, 11, 14, 15, 16], "forpost": [4, 5], "forum": 2, "found": [], "fp16": 15, "frac": 9, "framework": [3, 13, 14, 16], "free": [1, 2, 13], "french": [5, 11, 13, 16], "friendli": 4, "from": [1, 4, 5, 6, 7, 8, 9, 10, 11, 14, 15, 16], "from_hub": [7, 13], "from_imag": [6, 13], "from_pdf": 6, "from_url": 6, "full": [5, 9, 16], "function": [5, 8, 9], "funsd": [4, 5, 14, 16], "further": 14, "futur": 5, "g": [6, 7], "g_": 9, "g_x": 9, "gallagh": [], "gamma": 8, "gaussian": 8, "gaussianblur": 8, "gaussiannois": 8, "gdk": 3, "gen": 16, "gender": 1, "gener": [2, 4, 7], "generic_cyrillic_lett": [], "geom": [], "geometri": [4, 6, 16], "geq": 9, "german": [5, 11], "get": 16, "git": 13, "github": [2, 3, 13], "give": 1, "given": [5, 6, 8, 9, 16], "global": 7, "go": 16, "good": 15, "googl": 2, "googlevis": 4, "gpu": [4, 15], "gracefulli": 1, "graph": 6, "grayscal": 8, "ground": 9, "groung": 9, "group": 4, "gt": 9, "gt_box": 9, "gt_label": 9, "gtk": 3, "guid": 2, "guidanc": 14, "gvision": 16, "h": [6, 7, 8], "h_": 9, "ha": [2, 5, 9, 14], "handl": 14, "handwrit": 5, "handwritten": 14, "harass": 1, "hardwar": [], "harm": 1, "hat": 9, "have": [1, 2, 9, 11, 13, 14, 16], "head": [7, 16], "healthi": 1, "hebrew": [], "height": 6, "hello": [9, 16], "help": 15, "here": [3, 8, 10, 14, 16], "hf": 7, "hf_hub_download": 7, "high": 6, "higher": [3, 5], "hindi": [], "hindi_digit": 5, "hocr": 16, "homebrew": 3, "hook": [], "horizont": [6, 8], "hous": 5, "how": [2, 11, 13, 14], "howev": 14, "hsv": 8, "html": [1, 2, 16], "http": [1, 3, 6, 7, 13, 16], "hub": 7, "hue": 8, "huggingfac": 7, "hw": 5, "i": [1, 2, 5, 6, 7, 8, 9, 12, 13, 14, 15], "i7": 16, "ibrahimov": [], "ic03": [4, 5, 14], "ic13": [4, 5, 14], "icdar": [4, 5], "icdar2019": 5, "id": 16, "ident": 1, "identifi": 4, "iiit": [4, 5], "iiit5k": [5, 14], "iiithw": [4, 5, 14], "imag": [4, 5, 6, 7, 8, 9, 13, 14, 16], "imagenet": 7, "imageri": 1, "images_90k_norm": 5, "imagetensor": [], "imagetransform": [], "img": [5, 8, 14], "img_cont": 6, "img_fold": [5, 14], "img_path": 6, "img_transform": 5, "imgur5k": [4, 5, 14], "imgur5k_annot": 5, "imlist": 5, "impact": 1, "implement": [5, 6, 8, 9, 16], "import": [5, 6, 7, 8, 9, 11, 13, 14, 15, 16], "improv": [], "inappropri": 1, "incid": 1, "includ": [1, 3, 5, 14, 15], "inclus": 1, "increas": 8, "independ": [], "index": [2, 6], "indic": 9, "individu": 1, "infer": [4, 7, 8], "inform": [1, 2, 4, 5, 14], "input": [2, 6, 7, 8, 15, 16], "input_crop": 7, "input_pag": [7, 9, 16], "input_seq": [], "input_shap": 15, "input_str": [], "input_tensor": 7, "inspir": [1, 8], "instal": 13, "instanc": [1, 16], "instanti": [7, 16], "instead": [5, 6, 7], "insult": 1, "int": [5, 6, 8, 9], "int64": [8, 9], "integ": 9, "integr": [4, 13, 14], "intel": 16, "interact": [1, 6, 9], "interfac": 13, "interoper": 15, "interpol": 8, "interpret": [5, 6], "intersect": 9, "invert": 8, "investig": 1, "invis": 1, "involv": [1, 16], "io": 13, "iou": 9, "iou_thresh": 9, "iou_threshold": [], "irregular": [4, 7, 14], "isn": 5, "issu": [1, 2, 13], "italian": [], "iter": [5, 8, 14, 16], "its": [6, 7, 8, 9, 14, 16], "itself": [7, 13], "j": 9, "jame": [], "job": 2, "join": 2, "jpeg": 8, "jpegqual": 8, "jpg": [5, 6, 13], "json": [5, 14, 16], "json_output": 16, "jump": 2, "just": 1, "kei": [], "kera": [7, 15], "kernel": 8, "kernel_shap": 8, "keywoard": [], "keyword": [5, 7], "kie": [7, 11], "kie_predictor": [7, 11], "kiepredictor": 7, "kind": [1, 16], "know": 2, "kwarg": [5, 6, 7, 9], "l": 9, "l_j": 9, "label": [5, 8, 9, 14], "label_fil": [5, 14], "label_fold": 5, "label_path": [5, 14], "labels_path": [5, 14], "ladder": 1, "lambda": 8, "lambdatransform": 8, "lang": 16, "languag": [1, 4, 5, 6, 7, 13, 16], "larg": [7, 13], "largest": 9, "last": [3, 5], "latenc": 7, "later": 2, "latest": [3, 16], "latin": 5, "layer": 15, "layout": 16, "lead": 1, "leader": 1, "learn": [1, 4, 7, 15, 16], "least": 3, "left": [9, 16], "legacy_french": 5, "length": 5, "less": 15, "level": [1, 5, 9, 16], "leverag": 10, "lf": 13, "libffi": 3, "librari": [2, 3, 10, 11], "light": 4, "lightweight": [], "like": 1, "limits_": 9, "line": [4, 9, 16], "line_1_1": 16, "link": 11, "linknet": [4, 7], "linknet_resnet18": [7, 11, 16], "linknet_resnet18_rot": [7, 16], "linknet_resnet34": [7, 15, 16], "linknet_resnet50": [7, 16], "linux": 3, "list": [5, 6, 8, 9, 13], "ll": 9, "load": [4, 5, 7], "load_state_dict": 11, "load_weight": 11, "loc_pr": [], "local": [2, 4, 5, 7, 9, 14, 16], "localis": 5, "localizationconfus": 9, "locat": [2, 6], "login": 7, "login_to_hub": [7, 13], "logo": [6, 14], "love": 13, "lower": [8, 9], "m": [2, 9, 16], "m1": 3, "macbook": 3, "machin": 15, "maco": 3, "made": 4, "magc_resnet31": 7, "mai": [1, 2], "mail": 1, "main": 10, "maintain": 4, "mainten": 2, "make": [1, 2, 9, 12, 13, 15, 16], "mani": [14, 16], "manipul": [], "map": 5, "map_loc": 11, "mask": [], "mask_label": [], "mask_shap": 9, "master": [4, 7, 16], "match": [9, 16], "mathcal": 9, "matplotlib": 9, "max": [5, 8, 9], "max_angl": 8, "max_area": 8, "max_char": [5, 14], "max_delta": 8, "max_font_s": [], "max_gain": 8, "max_gamma": 8, "max_qual": 8, "max_ratio": 8, "maximum": [5, 8], "maxval": [7, 8], "mbox": 9, "mean": [8, 9, 11], "meaniou": 9, "meant": [6, 15], "measur": 16, "media": 1, "median": [], "meet": 11, "member": 1, "memori": [9, 12, 15], "mention": 16, "merg": 5, "messag": 2, "meta": 16, "metadata": 15, "metal": 3, "method": [8, 16], "metric": [9, 16], "middl": [], "might": [15, 16], "min": 8, "min_area": 8, "min_char": [5, 14], "min_font_s": [], "min_gain": 8, "min_gamma": 8, "min_qual": 8, "min_ratio": 8, "min_val": 8, "minde": [1, 3, 4, 7], "minim": [2, 4], "minimalist": [], "minimum": [3, 5, 8, 9], "minval": 8, "miss": 3, "mistak": 1, "mixed_float16": 15, "mixed_precis": 15, "mjsynth": [4, 5, 14], "mnt": 5, "mobilenet": [7, 13], "mobilenet_v3_larg": 7, "mobilenet_v3_large_r": 7, "mobilenet_v3_smal": 7, "mobilenet_v3_small_crop_orient": [], "mobilenet_v3_small_orient": 7, "mobilenet_v3_small_page_orient": [], "mobilenet_v3_small_r": 7, "mobilenetv3": 7, "modal": [], "mode": 3, "model": [5, 9, 12, 14], "model_nam": [7, 13, 15], "model_path": 15, "moder": 1, "modif": 2, "modifi": [7, 12], "modul": [6, 8, 9, 16], "moment": 16, "more": [2, 9, 14, 16], "moscardi": [], "most": 16, "mozilla": 1, "multi": [4, 7], "multiclass": [], "multilingu": [], "multipl": [5, 6, 8], "multipli": 8, "multiprocess": 12, "my": 7, "my_awesome_model": 13, "my_hook": [], "n": [5, 9], "name": [5, 7, 15, 16], "nation": 1, "natur": [1, 4, 5], "nb": 16, "ndarrai": [5, 6, 8, 9], "necessari": [3, 11, 12], "need": [2, 3, 5, 9, 11, 12, 13], "neg": 8, "nest": 16, "netraj": [], "network": [4, 5, 7, 15], "neural": [4, 5, 7, 15], "new": [2, 9], "next": [5, 14], "nois": 8, "noisi": [4, 5], "non": [4, 5, 6, 7, 8, 9], "none": [5, 6, 7, 8, 9, 16], "normal": [7, 8], "norwegian": [], "note": [0, 2, 5, 7, 13, 15], "now": 2, "np": [7, 8, 9, 16], "num_output_channel": 8, "num_sampl": [5, 14], "num_work": 5, "number": [5, 8, 9, 16], "numpi": [6, 7, 9, 16], "o": 3, "obb": [], "obj_detect": 13, "object": [5, 9, 10, 16], "objectness_scor": [], "oblig": 1, "obtain": 16, "occupi": 15, "ocr": [4, 5, 7, 9, 13, 14], "ocr_carea": 16, "ocr_db_crnn": 9, "ocr_lin": 16, "ocr_pag": 16, "ocr_par": 16, "ocr_predictor": [7, 11, 13, 15, 16], "ocrdataset": [5, 14], "ocrmetr": 9, "ocrpredictor": [7, 11], "ocrx_word": 16, "offens": 1, "offici": 1, "offlin": 1, "offset": 8, "onc": 16, "one": [2, 5, 7, 8, 11, 13, 16], "oneof": 8, "ones": [5, 8, 9], "onli": [2, 7, 8, 9, 13, 14, 15, 16], "onlin": 1, "onnx": [], "onnxruntim": [], "onnxtr": [], "opac": 8, "opacity_rang": 8, "open": [1, 2, 13, 15], "opinion": 1, "optic": [4, 16], "optim": 4, "option": [5, 11], "order": [2, 5, 6, 8], "org": [1, 7, 16], "organ": 6, "orient": [1, 6, 7, 16], "orientationpredictor": [], "other": [1, 2], "otherwis": [1, 6, 9], "our": [2, 7, 16], "out": [2, 7, 8, 9, 16], "out_box": [], "outpout": 16, "output": [6, 8, 15], "output_s": [6, 8], "outsid": 12, "over": [3, 5, 9, 16], "overal": [1, 7], "overlai": 6, "overview": [], "overwrit": [], "overwritten": 13, "own": 4, "p": [8, 9, 16], "packag": [2, 4, 9, 12, 14], "pad": [5, 7, 8, 16], "page": [3, 5, 7, 9, 16], "page1": 6, "page2": 6, "page_1": 16, "page_idx": [6, 16], "page_orientation_predictor": [], "page_param": [], "pair": 9, "pango": 3, "paper": 7, "par_1_1": 16, "paragraph": [], "paragraph_break": [], "parallel": [], "param": [8, 16], "paramet": [4, 5, 6, 7, 8, 9, 15], "pars": [4, 5], "parseq": [4, 7, 16], "part": [5, 8, 16], "parti": 3, "partial": 16, "particip": 1, "pass": [5, 6, 7, 16], "password": 6, "patch": 7, "path": [5, 6, 14], "path_to_checkpoint": 11, "path_to_custom_model": [], "path_to_pt": 11, "patil": [], "pattern": 1, "pdf": [6, 7, 10], "pdfpage": 6, "peopl": 1, "per": [8, 16], "perform": [4, 6, 8, 9, 12, 15, 16], "period": 1, "permiss": 1, "permut": [4, 7], "persian_lett": 5, "person": [1, 14], "phase": 16, "photo": 14, "physic": [1, 6], "pick": 8, "pictur": 6, "pip": [2, 3], "pipelin": [], "pixbuf": 3, "pixel": [6, 8, 16], "pleas": 2, "plot": 9, "plt": 9, "plug": 13, "plugin": 3, "png": 6, "point": 15, "polici": 12, "polish": [], "polit": 1, "polygon": [5, 16], "pool": 7, "portugues": 5, "posit": [1, 9], "possibl": [2, 9, 13], "post": [1, 16], "postprocessor": [], "potenti": 7, "power": 4, "ppageno": 16, "pre": [2, 7], "pre_transform_multiclass": [], "precis": [9, 16], "pred": 9, "pred_box": 9, "pred_label": 9, "predefin": 14, "predict": [6, 7, 9], "predictor": [4, 6, 7, 11, 13, 15], "prefer": 14, "preinstal": [], "preprocessor": [11, 16], "prerequisit": 13, "present": 10, "preserv": [7, 8, 16], "preserve_aspect_ratio": [6, 7, 8, 11, 16], "pretrain": [4, 7, 9, 11, 15, 16], "pretrained_backbon": [7, 11], "print": 16, "prior": 5, "privaci": 1, "privat": 1, "probabl": 8, "problem": 2, "procedur": 8, "process": [2, 4, 6, 11, 16], "processor": 16, "produc": [10, 16], "product": 15, "profession": 1, "project": [2, 14], "promptli": 1, "proper": 2, "properli": 5, "provid": [1, 2, 4, 13, 14, 16], "public": [1, 4], "publicli": 16, "publish": 1, "pull": 13, "punctuat": 5, "pure": 5, "purpos": 2, "push_to_hf_hub": [7, 13], "py": 13, "pypdfium2": 6, "pyplot": 9, "python": 2, "python3": 13, "pytorch": [3, 4, 7, 8, 11, 13, 15, 16], "q": 2, "qr": 6, "qr_code": 14, "qualiti": 8, "question": 1, "quickli": 4, "quicktour": 10, "r": 16, "race": 1, "ramdisk": 5, "rand": [7, 8, 9, 15, 16], "random": [7, 8, 9, 16], "randomappli": 8, "randombright": 8, "randomcontrast": 8, "randomcrop": 8, "randomgamma": 8, "randomhorizontalflip": 8, "randomhu": 8, "randomjpegqu": 8, "randomli": 8, "randomres": [], "randomrot": 8, "randomsatur": 8, "randomshadow": 8, "rang": 8, "rassi": [], "ratio": [7, 8, 16], "raw": [6, 9], "re": 15, "read": [4, 5, 7], "read_html": 6, "read_img": 6, "read_img_as_numpi": 6, "read_img_as_tensor": 6, "read_pdf": 6, "readi": 15, "real": [4, 7, 8], "realli": [], "reason": 1, "rebuild": 2, "rebuilt": 2, "recal": [9, 16], "receipt": [4, 5, 16], "reco_arch": [7, 11, 13, 15], "reco_b": [], "reco_model": [11, 13], "reco_param": 11, "reco_predictor": 11, "recogn": 16, "recognit": [5, 9, 11], "recognition_predictor": [7, 16], "recognition_task": [5, 14], "recognitiondataset": [5, 14], "recognitionpredictor": [7, 11], "rectangular": 7, "red": 9, "reduc": [3, 8], "refer": [2, 3, 11, 13, 14, 16], "regardless": 1, "region": [], "regroup": 9, "regular": 14, "reject": 1, "rel": [6, 8, 9], "relat": 6, "releas": [0, 3], "relev": [], "religion": 1, "remov": 1, "render": 6, "repo": 7, "repo_id": [7, 13], "report": 1, "repositori": [5, 7, 13], "repres": [1, 9, 15, 16], "represent": [4, 7], "request": [1, 13], "requir": [3, 8], "research": 4, "residu": 7, "resiz": [8, 16], "resnet": 7, "resnet18": [7, 13], "resnet31": 7, "resnet34": 7, "resnet50": [7, 13], "resolv": 6, "resolve_block": [], "resolve_lin": [], "resourc": 14, "respect": 1, "respons": 9, "rest": [2, 8, 9], "restrict": 12, "result": [2, 5, 6, 10, 13, 16], "return": [5, 6, 7, 9, 16], "reusabl": 16, "review": 1, "rgb": [6, 8], "rgb_mode": 6, "rgb_output": 6, "right": [1, 7, 9], "roboflow": [], "robust": [4, 5], "root": 5, "rotat": [5, 6, 7, 8, 9, 14, 16], "run": [2, 3, 7], "same": [2, 6, 9, 14, 16], "sampl": [5, 14, 16], "sample_transform": 5, "samplecompos": [], "sanjin": [], "sar": [4, 7], "sar_resnet31": [7, 16], "satur": 8, "save": [7, 14], "scale": [6, 7, 8, 9], "scale_rang": [], "scan": [4, 5], "scene": [4, 5, 7], "score": 9, "script": [2, 14], "seamless": 4, "seamlessli": [4, 16], "search": 7, "searchabl": 10, "sec": 16, "second": 16, "section": [11, 13, 15, 16], "secur": [1, 12], "see": [1, 2], "seen": 16, "segment": [4, 7, 16], "self": [], "semant": [4, 7], "send": 16, "sens": 9, "sensit": 14, "separ": 16, "sequenc": [4, 5, 6, 7, 9, 16], "sequenti": 8, "seri": 1, "seriou": 1, "set": [1, 5, 7, 9, 12, 16], "set_global_polici": 15, "sever": [6, 8, 16], "sex": 1, "sexual": 1, "shade": 8, "shape": [6, 7, 8, 9, 16], "share": [12, 14], "shift": 8, "shm": 12, "should": [2, 5, 6, 8, 9], "show": [4, 6, 7, 9, 11, 13], "showcas": 2, "shuffl": [5, 8], "side": 9, "signatur": 6, "signific": 14, "simpl": [4, 7], "simpler": 7, "sinc": [5, 14], "singl": [1, 2, 4, 5], "single_img_doc": [], "size": [1, 5, 6, 8, 9, 16], "skew": 16, "slack": 2, "slightli": 7, "small": [2, 7], "smallest": 6, "smooth": [], "smoothing_factor": [], "snapshot_download": 7, "snippet": 16, "so": [2, 3, 5, 7, 13, 14], "social": 1, "socio": 1, "some": [3, 10, 13, 14], "someth": 2, "somewher": 2, "soon": 15, "sort": 1, "sourc": [5, 6, 7, 8, 9, 13], "space": 1, "span": 16, "spanish": 5, "spatial": [6, 9], "specif": [2, 3, 9, 11, 14, 16], "specifi": [1, 5, 6], "speed": [4, 7], "sphinx": 2, "sroie": [4, 5, 14], "stabl": 3, "stackoverflow": 2, "stage": 4, "standalon": [], "standard": 8, "start": 5, "state": [4, 9], "static": 9, "statist": [], "statu": 1, "std": [8, 11], "step": 12, "still": 16, "str": [5, 6, 7, 8, 9], "straight": [5, 7, 14, 16], "straighten": [], "straighten_pag": [], "straigten_pag": [], "stream": 6, "street": [4, 5], "strict": [], "strictli": 9, "string": [5, 6, 9, 16], "strive": 3, "strong": [4, 7], "structur": [15, 16], "subset": [5, 16], "suggest": [2, 13], "sum": 9, "summari": 9, "support": [15, 16], "sustain": 1, "svhn": [4, 5, 14], "svt": [5, 14], "swedish": [], "symmetr": [7, 8, 16], "symmetric_pad": [7, 8, 16], "synthes": 9, "synthesize_pag": 9, "synthet": 4, "synthtext": [4, 5, 14], "system": 16, "t": [2, 5, 11, 16], "tabl": 13, "take": [1, 5, 16], "target": [5, 6, 8, 9, 14], "target_s": 5, "task": [4, 5, 7, 13, 14, 16], "task2": 5, "team": [], "techminde": [], "templat": [2, 4], "tensor": [5, 6, 8, 16], "tensorflow": [3, 4, 6, 7, 8, 11, 13, 15, 16], "tensorspec": 15, "term": 1, "test": 14, "test_set": 5, "text": [5, 6, 7, 9, 14], "text_output": [], "textmatch": 9, "textnet": [], "textnet_bas": [], "textnet_smal": [], "textnet_tini": [], "textract": [4, 16], "textstylebrush": [4, 5], "textual": [4, 5, 6, 7, 16], "tf": [3, 6, 7, 8, 13, 15], "than": [2, 3, 9, 13], "thank": 2, "thei": [1, 9], "them": [3, 5, 16], "thi": [1, 2, 3, 5, 9, 11, 12, 13, 14, 15, 16], "thing": [15, 16], "third": 3, "those": [1, 3, 6, 16], "threaten": 1, "threshold": [], "through": [1, 8, 14], "tilman": [], "time": [1, 4, 7, 9, 14], "tini": [], "titl": [6, 16], "tm": 16, "tmp": 12, "togeth": [2, 6], "tograi": 8, "tool": 14, "top": [9, 16], "topic": 2, "torch": [3, 8, 11, 13, 15], "torchvis": 8, "total": 11, "toward": [1, 3], "train": [2, 5, 7, 8, 13, 14, 15, 16], "train_it": [5, 14], "train_load": [5, 14], "train_pytorch": 13, "train_set": [5, 14], "train_tensorflow": 13, "trainabl": [4, 7], "tranform": 8, "transcrib": 16, "transfer": [4, 5], "transfo": 8, "transform": [4, 5, 7], "translat": 1, "troll": 1, "true": [5, 6, 7, 8, 9, 11, 12, 13, 14, 15, 16], "truth": 9, "tune": 15, "tupl": [5, 6, 8, 9], "turn": [], "two": [6, 12], "txt": 5, "type": [6, 13, 15, 16], "typic": 16, "u": [1, 2], "ucsd": 5, "udac": 2, "uint8": [6, 7, 9, 16], "ukrainian": [], "unaccept": 1, "underli": 14, "underneath": 6, "understand": [4, 5, 16], "unidecod": 9, "uniform": [7, 8], "uniformli": 8, "uninterrupt": [6, 16], "union": 9, "unit": [], "unittest": 2, "unknown": [], "unknown_char": [], "unlock": 6, "unoffici": 7, "unprofession": 1, "unsolicit": 1, "unsupervis": 4, "unwelcom": 1, "up": [7, 16], "updat": 9, "upgrad": 2, "upper": [5, 8], "uppercas": 14, "url": 6, "us": [1, 2, 3, 5, 7, 9, 11, 12, 13, 16], "usabl": 16, "usag": [12, 15], "use_broadcast": 9, "use_polygon": [5, 9, 14], "useabl": 16, "user": [3, 4, 6, 10], "utf": 16, "util": 15, "v1": 13, "v3": [7, 13, 16], "valid": 14, "valu": [2, 6, 8, 16], "valuabl": 4, "variabl": 12, "varieti": 5, "veri": 7, "verma": [], "version": [1, 2, 3, 15, 16], "vgg": 7, "vgg16": 13, "vgg16_bn_r": 7, "via": 1, "video": [], "vietnames": 5, "view": [4, 5], "viewpoint": 1, "violat": 1, "visibl": 1, "vision": [4, 5, 7], "visiondataset": 5, "visiontransform": 7, "visual": 4, "visualize_pag": 9, "vit_": 7, "vit_b": 7, "vitstr": [4, 7, 15], "vitstr_bas": [7, 16], "vitstr_smal": [7, 11, 15, 16], "viz": [], "vocab": [11, 13, 14, 16], "vocab_nam": [], "vocabulari": [5, 11, 13], "w": [6, 7, 8, 9], "w3": 16, "wa": 1, "wai": [1, 4, 14], "want": [2, 15, 16], "warmup": 16, "wasn": 2, "we": [1, 2, 3, 4, 6, 8, 13, 14, 15, 16], "weasyprint": [], "web": [2, 6], "websit": 5, "weight": 11, "welcom": 1, "well": [1, 15], "were": [1, 6, 16], "what": 1, "when": [1, 2, 7], "whenev": 2, "where": [2, 6, 8, 9], "whether": [2, 5, 6, 8, 9, 14], "which": [1, 7, 12, 14, 16], "whichev": 3, "while": [8, 16], "why": 1, "width": 6, "wiki": 1, "wildreceipt": [], "window": [3, 7, 9], "wish": 2, "within": 1, "without": [1, 5, 7], "wonder": 2, "word": [4, 5, 7, 9, 16], "word_1_1": 16, "word_1_2": 16, "word_1_3": 16, "wordgener": [5, 14], "words_onli": 9, "work": [12, 16], "worker": 5, "workflow": 2, "worklow": 2, "world": [9, 16], "worth": 7, "wrap": 16, "wrapper": [5, 8], "write": 12, "written": [1, 6], "www": [1, 6, 16], "x": [6, 8, 9], "x_ascend": 16, "x_descend": 16, "x_i": 9, "x_size": 16, "x_wconf": 16, "xhtml": 16, "xmax": 6, "xmin": 6, "xml": 16, "xml_bytes_str": 16, "xml_element": 16, "xml_output": 16, "xmln": 16, "y": 9, "y_i": 9, "y_j": 9, "yet": [], "ymax": 6, "ymin": 6, "yolov8": [], "yolov8_artefact": [], "you": [2, 3, 5, 6, 7, 11, 12, 13, 14, 15, 16], "your": [2, 4, 6, 9, 16], "yoursit": 6, "yugesh": [], "zero": [8, 9], "zoo": [], "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 5, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 5, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": [], "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 5, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 5, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": [], "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 5, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 5, "\u00e4\u00f6\u00e4\u00f6": [], "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 5, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": [], "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": [], "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": [], "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 5, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": [], "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": [], "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": [], "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": [], "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 5, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 5, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 5, "\u067e\u0686\u06a2\u06a4\u06af": 5, "\u0905": [], "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": [], "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": [], "\u0950": [], "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": [], "\u09bd": [], "\u09ce": [], "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": []}, "titles": ["Changelog", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 2, "0": 0, "01": 0, "02": 0, "03": 0, "04": [], "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 1], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 1], "2021": 0, "2022": 0, "2023": [], "2024": [], "21": [], "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 1], "31": 0, "4": [0, 1], "5": 0, "6": 0, "7": [], "8": [], "9": [], "advanc": [], "approach": 16, "architectur": 16, "artefact": 6, "artefactdetect": [], "attribut": 1, "avail": [14, 16], "aw": 12, "ban": 1, "block": 6, "bug": 2, "changelog": 0, "choos": [14, 16], "classif": [7, 13], "code": [1, 2], "codebas": 2, "commit": 2, "commun": 13, "compos": 8, "conda": [], "conduct": 1, "connect": 2, "continu": 2, "contrib": [], "contribut": 2, "contributor": 1, "convent": 13, "correct": 1, "coven": 1, "custom": [5, 11], "data": 14, "dataload": 5, "dataset": [4, 5, 14], "detect": [4, 7, 13, 14, 16], "develop": 2, "do": 16, "doctr": [2, 4, 5, 6, 7, 8, 9, 10, 15], "document": [2, 4, 6], "end": 16, "enforc": 1, "evalu": 9, "export": 15, "factori": 7, "featur": [2, 4], "feedback": 2, "file": 6, "from": 13, "gener": [5, 14], "git": 3, "guidelin": 1, "half": 15, "hub": 13, "huggingfac": 13, "i": 16, "infer": 15, "instal": [2, 3], "integr": 2, "io": 6, "lambda": 12, "let": 2, "line": 6, "linux": [], "load": [11, 13, 14], "loader": 5, "main": 4, "mode": 2, "model": [4, 7, 11, 13, 15, 16], "modifi": 2, "modul": [], "name": 13, "notebook": 10, "object": 14, "ocr": 16, "onli": [], "onnx": 15, "optim": 15, "option": [], "orient": [], "our": 1, "output": 16, "own": [11, 14], "packag": 3, "page": 6, "perman": 1, "pipelin": [], "pledg": 1, "precis": 15, "predictor": 16, "prepar": 15, "prerequisit": 3, "pretrain": 13, "push": 13, "python": 3, "qualiti": 2, "question": 2, "read": 6, "readi": 14, "recognit": [4, 7, 13, 14, 16], "reconstitut": [], "report": 2, "request": 2, "resourc": [], "respons": 1, "right": 16, "scope": 1, "share": 13, "should": 16, "stage": 16, "standard": 1, "structur": [2, 6], "style": 2, "support": [4, 5, 8], "synthet": [5, 14], "task": 9, "temporari": 1, "test": 2, "text": [4, 16], "train": 11, "transform": 8, "two": 16, "unit": 2, "us": [14, 15], "util": 9, "v0": 0, "verif": 2, "via": 3, "visual": 9, "vocab": 5, "warn": 1, "what": 16, "word": 6, "your": [11, 13, 14, 15], "zoo": [4, 7]}})
\ No newline at end of file
+Search.setIndex({"alltitles": {"1. Correction": [[1, "correction"]], "2. Warning": [[1, "warning"]], "3. Temporary Ban": [[1, "temporary-ban"]], "4. Permanent Ban": [[1, "permanent-ban"]], "AWS Lambda": [[12, null]], "Artefact": [[6, "artefact"]], "Attribution": [[1, "attribution"]], "Available Datasets": [[14, "available-datasets"]], "Available architectures": [[16, "available-architectures"], [16, "id1"], [16, "id2"]], "Block": [[6, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[14, null]], "Choosing the right model": [[16, null]], "Classification": [[13, "classification"]], "Code quality": [[2, "code-quality"]], "Code style verification": [[2, "code-style-verification"]], "Codebase structure": [[2, "codebase-structure"]], "Commits": [[2, "commits"]], "Composing transformations": [[8, "composing-transformations"]], "Continuous Integration": [[2, "continuous-integration"]], "Contributing to docTR": [[2, null]], "Contributor Covenant Code of Conduct": [[1, null]], "Custom dataset loader": [[5, "custom-dataset-loader"]], "Data Loading": [[14, "data-loading"]], "Dataloader": [[5, "dataloader"]], "Detection": [[13, "detection"], [14, "detection"]], "Detection predictors": [[16, "detection-predictors"]], "Developer mode installation": [[2, "developer-mode-installation"]], "Developing docTR": [[2, "developing-doctr"]], "Document": [[6, "document"]], "Document structure": [[6, "document-structure"]], "End-to-End OCR": [[16, "end-to-end-ocr"]], "Enforcement": [[1, "enforcement"]], "Enforcement Guidelines": [[1, "enforcement-guidelines"]], "Enforcement Responsibilities": [[1, "enforcement-responsibilities"]], "Export to ONNX": [[15, "export-to-onnx"]], "Feature requests & bug report": [[2, "feature-requests-bug-report"]], "Feedback": [[2, "feedback"]], "File reading": [[6, "file-reading"]], "Half-precision": [[15, "half-precision"]], "Installation": [[3, null]], "Let\u2019s connect": [[2, "let-s-connect"]], "Line": [[6, "line"]], "Loading from Huggingface Hub": [[13, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[11, "loading-your-custom-trained-model"]], "Main Features": [[4, "main-features"]], "Model optimization": [[15, "model-optimization"]], "Model zoo": [[4, "model-zoo"]], "Modifying the documentation": [[2, "modifying-the-documentation"]], "Naming conventions": [[13, "naming-conventions"]], "Object Detection": [[14, "object-detection"]], "Our Pledge": [[1, "our-pledge"]], "Our Standards": [[1, "our-standards"]], "Page": [[6, "page"]], "Preparing your model for inference": [[15, null]], "Prerequisites": [[3, "prerequisites"]], "Pretrained community models": [[13, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[13, "pushing-to-the-huggingface-hub"]], "Questions": [[2, "questions"]], "Recognition": [[13, "recognition"], [14, "recognition"]], "Recognition predictors": [[16, "recognition-predictors"]], "Scope": [[1, "scope"]], "Share your model with the community": [[13, null]], "Supported Vocabs": [[5, "supported-vocabs"]], "Supported datasets": [[4, "supported-datasets"]], "Supported transformations": [[8, "supported-transformations"]], "Synthetic dataset generator": [[5, "synthetic-dataset-generator"], [14, "synthetic-dataset-generator"]], "Task evaluation": [[9, "task-evaluation"]], "Text Detection": [[16, "text-detection"]], "Text Recognition": [[16, "text-recognition"]], "Text detection models": [[4, "text-detection-models"]], "Text recognition models": [[4, "text-recognition-models"]], "Train your own model": [[11, null]], "Two-stage approaches": [[16, "two-stage-approaches"]], "Unit tests": [[2, "unit-tests"]], "Use your own datasets": [[14, "use-your-own-datasets"]], "Using your ONNX exported model in docTR": [[15, "using-your-onnx-exported-model-in-doctr"]], "Via Git": [[3, "via-git"]], "Via Python Package": [[3, "via-python-package"]], "Visualization": [[9, "visualization"]], "What should I do with the output?": [[16, "what-should-i-do-with-the-output"]], "Word": [[6, "word"]], "docTR Notebooks": [[10, null]], "docTR Vocabs": [[5, "id5"]], "docTR: Document Text Recognition": [[4, null]], "doctr.datasets": [[5, null], [5, "datasets"]], "doctr.io": [[6, null]], "doctr.models": [[7, null]], "doctr.models.classification": [[7, "doctr-models-classification"]], "doctr.models.detection": [[7, "doctr-models-detection"]], "doctr.models.factory": [[7, "doctr-models-factory"]], "doctr.models.recognition": [[7, "doctr-models-recognition"]], "doctr.models.zoo": [[7, "doctr-models-zoo"]], "doctr.transforms": [[8, null]], "doctr.utils": [[9, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]]}, "docnames": ["changelog", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[6, "doctr.io.Artefact", false]], "block (class in doctr.io)": [[6, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms)": [[8, "doctr.transforms.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[5, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms)": [[8, "doctr.transforms.ColorInversion", false]], "compose (class in doctr.transforms)": [[8, "doctr.transforms.Compose", false]], "cord (class in doctr.datasets)": [[5, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[7, "doctr.models.classification.crop_orientation_predictor", false]], "dataloader (class in doctr.datasets.loader)": [[5, "doctr.datasets.loader.DataLoader", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[7, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[7, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[6, "doctr.io.decode_img_as_tensor", false]], "detection_predictor() (in module doctr.models.detection)": [[7, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[5, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[5, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[6, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[6, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[5, "doctr.datasets.encode_sequences", false]], "from_hub() (in module doctr.models.factory)": [[7, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[6, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[6, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[6, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[5, "doctr.datasets.FUNSD", false]], "gaussianblur (class in doctr.transforms)": [[8, "doctr.transforms.GaussianBlur", false]], "gaussiannoise (class in doctr.transforms)": [[8, "doctr.transforms.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[5, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[5, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[5, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[5, "doctr.datasets.IIITHWS", false]], "imgur5k (class in doctr.datasets)": [[5, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[7, "doctr.models.kie_predictor", false]], "lambdatransformation (class in doctr.transforms)": [[8, "doctr.transforms.LambdaTransformation", false]], "line (class in doctr.io)": [[6, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[7, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet18_rotation() (in module doctr.models.detection)": [[7, "doctr.models.detection.linknet_resnet18_rotation", false]], "linknet_resnet34() (in module doctr.models.detection)": [[7, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[7, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[7, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[7, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[5, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_orientation() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_small_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_small_r", false]], "normalize (class in doctr.transforms)": [[8, "doctr.transforms.Normalize", false]], "ocr_predictor() (in module doctr.models)": [[7, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[5, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms)": [[8, "doctr.transforms.OneOf", false]], "page (class in doctr.io)": [[6, "doctr.io.Page", false]], "parseq() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.parseq", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[7, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms)": [[8, "doctr.transforms.RandomApply", false]], "randombrightness (class in doctr.transforms)": [[8, "doctr.transforms.RandomBrightness", false]], "randomcontrast (class in doctr.transforms)": [[8, "doctr.transforms.RandomContrast", false]], "randomcrop (class in doctr.transforms)": [[8, "doctr.transforms.RandomCrop", false]], "randomgamma (class in doctr.transforms)": [[8, "doctr.transforms.RandomGamma", false]], "randomhorizontalflip (class in doctr.transforms)": [[8, "doctr.transforms.RandomHorizontalFlip", false]], "randomhue (class in doctr.transforms)": [[8, "doctr.transforms.RandomHue", false]], "randomjpegquality (class in doctr.transforms)": [[8, "doctr.transforms.RandomJpegQuality", false]], "randomrotate (class in doctr.transforms)": [[8, "doctr.transforms.RandomRotate", false]], "randomsaturation (class in doctr.transforms)": [[8, "doctr.transforms.RandomSaturation", false]], "randomshadow (class in doctr.transforms)": [[8, "doctr.transforms.RandomShadow", false]], "read_html() (in module doctr.io)": [[6, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[6, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[6, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[6, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[5, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms)": [[8, "doctr.transforms.Resize", false]], "resnet18() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet50", false]], "sar_resnet31() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[6, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[6, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[5, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[9, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[9, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[9, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[9, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[5, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[5, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.visualization)": [[9, "doctr.utils.visualization.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[5, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.TextMatch", false]], "togray (class in doctr.transforms)": [[8, "doctr.transforms.ToGray", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[9, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[9, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[9, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[9, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[7, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[9, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[7, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[7, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.vitstr_small", false]], "word (class in doctr.io)": [[6, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[5, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.datasets": [[5, 0, 1, "", "CORD"], [5, 0, 1, "", "CharacterGenerator"], [5, 0, 1, "", "DetectionDataset"], [5, 0, 1, "", "DocArtefacts"], [5, 0, 1, "", "FUNSD"], [5, 0, 1, "", "IC03"], [5, 0, 1, "", "IC13"], [5, 0, 1, "", "IIIT5K"], [5, 0, 1, "", "IIITHWS"], [5, 0, 1, "", "IMGUR5K"], [5, 0, 1, "", "MJSynth"], [5, 0, 1, "", "OCRDataset"], [5, 0, 1, "", "RecognitionDataset"], [5, 0, 1, "", "SROIE"], [5, 0, 1, "", "SVHN"], [5, 0, 1, "", "SVT"], [5, 0, 1, "", "SynthText"], [5, 0, 1, "", "WordGenerator"], [5, 1, 1, "", "encode_sequences"]], "doctr.datasets.loader": [[5, 0, 1, "", "DataLoader"]], "doctr.io": [[6, 0, 1, "", "Artefact"], [6, 0, 1, "", "Block"], [6, 0, 1, "", "Document"], [6, 0, 1, "", "DocumentFile"], [6, 0, 1, "", "Line"], [6, 0, 1, "", "Page"], [6, 0, 1, "", "Word"], [6, 1, 1, "", "decode_img_as_tensor"], [6, 1, 1, "", "read_html"], [6, 1, 1, "", "read_img_as_numpy"], [6, 1, 1, "", "read_img_as_tensor"], [6, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[6, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[6, 2, 1, "", "from_images"], [6, 2, 1, "", "from_pdf"], [6, 2, 1, "", "from_url"]], "doctr.io.Page": [[6, 2, 1, "", "show"]], "doctr.models": [[7, 1, 1, "", "kie_predictor"], [7, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[7, 1, 1, "", "crop_orientation_predictor"], [7, 1, 1, "", "magc_resnet31"], [7, 1, 1, "", "mobilenet_v3_large"], [7, 1, 1, "", "mobilenet_v3_large_r"], [7, 1, 1, "", "mobilenet_v3_small"], [7, 1, 1, "", "mobilenet_v3_small_orientation"], [7, 1, 1, "", "mobilenet_v3_small_r"], [7, 1, 1, "", "resnet18"], [7, 1, 1, "", "resnet31"], [7, 1, 1, "", "resnet34"], [7, 1, 1, "", "resnet50"], [7, 1, 1, "", "vgg16_bn_r"], [7, 1, 1, "", "vit_b"], [7, 1, 1, "", "vit_s"]], "doctr.models.detection": [[7, 1, 1, "", "db_mobilenet_v3_large"], [7, 1, 1, "", "db_resnet50"], [7, 1, 1, "", "detection_predictor"], [7, 1, 1, "", "linknet_resnet18"], [7, 1, 1, "", "linknet_resnet18_rotation"], [7, 1, 1, "", "linknet_resnet34"], [7, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[7, 1, 1, "", "from_hub"], [7, 1, 1, "", "login_to_hub"], [7, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[7, 1, 1, "", "crnn_mobilenet_v3_large"], [7, 1, 1, "", "crnn_mobilenet_v3_small"], [7, 1, 1, "", "crnn_vgg16_bn"], [7, 1, 1, "", "master"], [7, 1, 1, "", "parseq"], [7, 1, 1, "", "recognition_predictor"], [7, 1, 1, "", "sar_resnet31"], [7, 1, 1, "", "vitstr_base"], [7, 1, 1, "", "vitstr_small"]], "doctr.transforms": [[8, 0, 1, "", "ChannelShuffle"], [8, 0, 1, "", "ColorInversion"], [8, 0, 1, "", "Compose"], [8, 0, 1, "", "GaussianBlur"], [8, 0, 1, "", "GaussianNoise"], [8, 0, 1, "", "LambdaTransformation"], [8, 0, 1, "", "Normalize"], [8, 0, 1, "", "OneOf"], [8, 0, 1, "", "RandomApply"], [8, 0, 1, "", "RandomBrightness"], [8, 0, 1, "", "RandomContrast"], [8, 0, 1, "", "RandomCrop"], [8, 0, 1, "", "RandomGamma"], [8, 0, 1, "", "RandomHorizontalFlip"], [8, 0, 1, "", "RandomHue"], [8, 0, 1, "", "RandomJpegQuality"], [8, 0, 1, "", "RandomRotate"], [8, 0, 1, "", "RandomSaturation"], [8, 0, 1, "", "RandomShadow"], [8, 0, 1, "", "Resize"], [8, 0, 1, "", "ToGray"]], "doctr.utils.metrics": [[9, 0, 1, "", "DetectionMetric"], [9, 0, 1, "", "LocalizationConfusion"], [9, 0, 1, "", "OCRMetric"], [9, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.visualization": [[9, 1, 1, "", "synthesize_page"], [9, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [1, 6, 7, 9, 13], "0": [1, 3, 5, 8, 9, 11, 14, 16], "00": 16, "01": 16, "0123456789": 5, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 5, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 5, "02": 16, "02562": 7, "03": 16, "035": [], "0361328125": 16, "04": [], "05": 16, "06": 16, "06640625": 16, "07": 16, "08": [8, 16], "09": 16, "0966796875": 16, "1": [3, 5, 6, 7, 8, 9, 11, 14, 16], "10": [5, 9, 16], "100": [5, 8, 9, 14, 16], "1000": 16, "101": 5, "1024": [7, 9, 11, 16], "104": [], "106": [], "108": 5, "1095": 14, "11": 16, "110": 9, "1107": 14, "114": [], "115": [], "1156": 14, "116": 5, "118": [], "11800h": 16, "11th": 16, "12": [3, 16], "120": [], "123": 5, "126": 5, "1268": [], "128": [7, 11, 15, 16], "13": [9, 16], "130": 5, "13068": 14, "131": 5, "1337891": 14, "1357421875": 16, "1396484375": 16, "14": 16, "1420": 16, "149": 14, "15": 16, "150": [9, 16], "1552": 16, "16": [7, 15], "1630859375": 16, "1684": 16, "16x16": 7, "17": 16, "1778": 16, "1782": 16, "18": [7, 16], "185546875": 16, "1900": 16, "1910": 7, "19342": 14, "19370": 14, "195": [], "19598": [], "199": 16, "1999": 16, "2": [3, 4, 5, 6, 8, 16], "20": [], "200": 9, "2000": 14, "2003": [4, 5], "2012": 5, "2013": [4, 5], "2015": 5, "2019": 4, "2023": [], "207901": 14, "21": 16, "2186": 14, "21888": 14, "22": 16, "224": [7, 8], "225": 8, "22672": 14, "229": [8, 14], "23": 16, "233": 14, "234": 5, "236": [], "24": 16, "246": 14, "249": 14, "25": 16, "2504": 16, "255": [6, 7, 8, 9, 16], "256": 7, "257": 14, "26": [], "26032": 14, "264": 11, "27": 16, "2700": 14, "2710": 16, "2749": 11, "28": 16, "287": 11, "29": 16, "296": 11, "299": 11, "2d": 16, "3": [3, 4, 6, 7, 8, 9, 15, 16], "30": 16, "300": 14, "3000": 14, "301": 11, "30595": 16, "30ghz": 16, "31": [7, 16], "32": [5, 7, 8, 11, 14, 15, 16], "3232421875": 16, "33": 8, "33402": 14, "33608": 14, "34": [7, 16], "340": 16, "3456": 16, "35": 16, "3515625": 16, "36": [], "360": 14, "37": [5, 16], "38": 16, "39": [], "4": [7, 8, 9, 16], "40": 16, "406": 8, "41": 16, "42": 16, "43": 16, "44": 16, "45": 16, "456": 8, "46": 16, "47": 16, "472": [], "48": [5, 16], "485": 8, "49": [], "49377": [], "5": [5, 8, 9, 16], "50": [7, 14, 16], "51": 16, "51171875": 16, "512": 7, "52": [5, 16], "529": 16, "53": 16, "54": 16, "540": 16, "5478515625": 16, "55": 16, "56": 16, "57": 16, "58": 16, "580": 16, "5810546875": 16, "583": 16, "59": 16, "597": 16, "5k": [4, 5], "5m": [], "6": [8, 16], "60": 8, "600": [7, 9, 16], "61": 16, "62": 16, "626": 14, "63": 16, "64": [7, 8, 16], "641": 16, "647": 14, "65": 16, "66": 16, "67": 16, "68": 16, "69": 16, "693": 11, "694": 11, "695": 11, "6m": [], "7": 16, "70": [9, 16], "707470": 14, "71": 16, "7100000": 14, "7141797": 14, "7149": 14, "72": 16, "72dpi": 6, "73": 16, "73257": 14, "74": 16, "75": [8, 16], "7581382": 14, "76": 16, "77": 16, "772": 11, "772875": 14, "78": 16, "785": 11, "79": 16, "793533": 14, "796": 14, "798": 11, "7m": [], "8": [3, 7, 8, 16], "80": 16, "800": [7, 9, 14, 16], "81": 16, "82": 16, "83": 16, "84": 16, "849": 14, "85": 16, "8564453125": 16, "857": 16, "85875": 14, "86": 16, "8603515625": 16, "87": 16, "8707": 14, "88": 16, "89": 16, "9": 16, "90": 16, "90k": 5, "90kdict32px": 5, "91": 16, "914085328578949": 16, "92": 16, "93": 16, "94": [5, 16], "95": [9, 16], "9578408598899841": 16, "96": 16, "97": 16, "98": 16, "99": 16, "9949972033500671": 16, "A": [1, 2, 4, 5, 6, 7, 10, 15], "As": 2, "Be": [], "Being": 1, "By": 12, "For": [1, 2, 3, 11, 16], "If": [2, 3, 6, 7, 11, 16], "In": [2, 5, 14], "It": [8, 13, 15], "Its": [4, 7], "No": [1, 16], "Of": 5, "Or": [], "The": [1, 2, 5, 6, 9, 12, 16], "Then": [], "To": [2, 3, 12, 13, 16], "_": [1, 5, 7], "__call__": [], "_build": 2, "_i": 9, "abc": [], "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 5, "abdef": [5, 14], "abl": [14, 16], "about": [1, 14, 16], "abov": 16, "abstract": [], "abstractdataset": 5, "abus": 1, "accept": 1, "access": [4, 6, 14, 16], "account": [1, 13], "accur": [], "accuraci": 9, "achiev": 15, "act": 1, "action": 1, "activ": 4, "ad": [2, 7, 8], "adapt": 1, "add": [8, 9, 13], "add_hook": [], "add_label": 9, "addit": [2, 3, 6], "addition": [2, 16], "address": [1, 6], "adjust": 8, "advanc": 1, "advantag": 15, "advis": 2, "aesthet": [4, 5], "affect": 1, "after": [13, 16], "ag": 1, "again": [], "aggreg": [9, 14], "aggress": 1, "align": [1, 6], "all": [1, 2, 5, 6, 8, 9, 14, 16], "allow": 1, "along": 16, "alreadi": 2, "also": [1, 7, 13, 14, 16], "alwai": 14, "an": [1, 2, 4, 5, 6, 7, 9, 15, 16], "analysi": 6, "ancient_greek": 5, "andrej": [], "angl": [6, 8], "ani": [1, 5, 6, 7, 8, 9, 16], "annot": 5, "anot": 14, "anoth": [3, 7, 11, 14], "answer": 1, "anyascii": [], "anyon": 4, "anyth": [], "api": [2, 4], "apolog": 1, "apologi": 1, "app": 2, "appear": 1, "appli": [1, 5, 8], "applic": [4, 7], "appoint": 1, "appreci": 13, "appropri": [1, 2, 16], "ar": [1, 2, 3, 5, 6, 8, 9, 10, 14, 16], "arab": 5, "arabic_diacrit": 5, "arabic_lett": 5, "arabic_punctu": 5, "arbitrarili": [], "arch": [7, 13], "architectur": [4, 7, 13], "area": 16, "arg": [5, 7], "argument": [5, 7, 16], "around": 1, "arrai": [6, 8, 9], "art": 4, "artefact": [9, 10, 16], "artefact_typ": 6, "artefactdetector": [], "articl": [], "artifici": [4, 5], "arxiv": 7, "asarrai": 9, "ascii_lett": 5, "aspect": [4, 7, 8, 16], "assess": 9, "assign": 9, "associ": 6, "assum": 7, "assume_straight_pag": [7, 16], "astyp": [7, 9, 16], "attack": 1, "attend": [4, 7], "attent": [1, 7], "autom": 4, "automat": [], "autoregress": [4, 7], "avail": [1, 4, 8], "averag": [8, 16], "avoid": [1, 3], "aw": [4, 16], "awar": [], "azur": 16, "b": [7, 9, 16], "b_j": 9, "back": 2, "backbon": 7, "backend": 16, "background": 14, "bangla": [], "bar": [], "bar_cod": 14, "baranovskij": [], "base": [4, 7], "baselin": [4, 7, 16], "batch": [5, 7, 8, 14, 16], "batch_siz": [5, 11, 14, 15], "bblanchon": [], "bbox": 16, "becaus": 12, "been": [2, 9, 14, 16], "befor": [5, 7, 8, 16], "begin": 9, "behavior": 1, "being": [9, 16], "belong": 16, "benchmark": 16, "best": 1, "better": [10, 16], "between": [8, 9], "bgr": 6, "bilinear": 8, "bin_thresh": [], "binar": [4, 7], "binari": [6, 15, 16], "bit": 15, "blank": 9, "block": [9, 16], "block_1_1": 16, "blue": 9, "blur": 8, "bmvc": 5, "bn": 13, "bodi": [1, 16], "bool": [5, 6, 7, 8, 9], "boolean": [7, 16], "both": [4, 5, 8, 14, 16], "bottom": [7, 16], "bound": [5, 6, 7, 8, 9, 16], "box": [5, 6, 7, 8, 9, 14, 16], "box_thresh": [], "brew": 3, "bright": 8, "broadcast": 9, "browser": [2, 4], "build": [2, 3], "built": 2, "byte": [6, 16], "c": [6, 9], "c_j": 9, "cach": [2, 5, 12], "cache_sampl": 5, "cairo": 3, "call": [], "callabl": [5, 8], "can": [2, 3, 11, 12, 13, 14, 16], "capabl": [2, 10, 16], "case": [5, 9], "cf": 16, "cfg": 16, "challeng": 5, "challenge2_test_task12_imag": 5, "challenge2_test_task1_gt": 5, "challenge2_training_task12_imag": 5, "challenge2_training_task1_gt": 5, "chang": 12, "channel": [1, 2, 6, 8], "channel_prior": [], "channelshuffl": 8, "charact": [4, 5, 6, 9, 14, 16], "charactergener": [5, 14], "characterist": 1, "charg": 16, "charset": 16, "chart": 6, "check": [2, 13, 16], "checkpoint": 7, "chip": 3, "christian": [], "ci": 2, "clarifi": 1, "clariti": 1, "class": [1, 5, 6, 8, 9, 16], "class_nam": 11, "classif": 14, "classif_mobilenet_v3_smal": 7, "classmethod": 6, "clear": 2, "clone": 3, "close": 2, "co": 13, "code": [4, 6], "codecov": 2, "colab": 10, "collate_fn": 5, "collect": 6, "color": [8, 9], "colorinvers": 8, "column": 6, "com": [1, 3, 6, 13], "combin": 16, "come": 15, "command": 2, "comment": 1, "commit": 1, "common": [1, 8, 9, 15], "commun": 1, "compar": 4, "comparison": [9, 16], "competit": 5, "compil": [10, 16], "complaint": 1, "complementari": 9, "complet": 2, "compon": 16, "compos": [5, 16], "comprehens": 16, "comput": [5, 9, 15, 16], "conf_threshold": [], "confid": [6, 9, 16], "config": 7, "configur": 7, "confus": 9, "consecut": [8, 16], "consequ": 1, "consid": [1, 2, 5, 6, 9, 16], "consist": 16, "consolid": [4, 5], "constant": 8, "construct": 1, "consum": 9, "contact": 1, "contain": [5, 14], "content": [5, 6, 9, 16], "context": 7, "contib": [], "continu": 1, "contrast": 8, "contrast_factor": 8, "contrib": [], "contribut": 1, "contributor": 2, "convers": 6, "convert": [6, 8], "convert_target_to_rel": [], "convolut": 7, "cool": [], "coordin": [6, 16], "cord": [4, 5, 14, 16], "core": [9, 16], "corner": 16, "correct": 8, "correspond": [3, 6, 16], "could": 1, "counterpart": 9, "cover": 2, "coverag": 2, "cpu": [4, 11], "creat": 13, "crnn": [4, 7, 13], "crnn_mobilenet_v3_larg": [7, 13, 16], "crnn_mobilenet_v3_smal": [7, 15, 16], "crnn_vgg16_bn": [7, 11, 13, 16], "crop": [7, 8, 14, 16], "crop_bboxes_from_imag": [], "crop_orient": [], "crop_orientation_predictor": 7, "crop_param": [], "croporientationpredictor": 7, "cuda": 15, "currenc": 5, "current": [2, 16], "custom": 13, "custom_crop_orientation_model": [], "custom_page_orientation_model": [], "customhook": [], "cvit": 4, "czczup": [], "czech": 5, "d": [5, 14], "danish": [], "data": [4, 5, 6, 8, 9, 11, 13], "dataload": 14, "dataset": [7, 11, 16], "dataset_info": 5, "date": [11, 16], "db": 13, "db_mobilenet_v3_larg": [7, 13, 16], "db_resnet34": 16, "db_resnet50": [7, 11, 13, 16], "db_resnet50_rot": 16, "dbnet": [4, 7], "deal": [], "decis": 1, "decod": 6, "decode_img_as_tensor": 6, "decode_sequ": [], "dedic": [], "deem": 1, "deep": [7, 16], "def": [], "default": [6, 9, 11, 12], "defer": 14, "defin": [9, 15], "degre": 8, "degress": 6, "delet": 2, "delimit": 16, "delta": 8, "demo": [2, 4], "demonstr": 1, "depend": [2, 3, 4], "deploi": 2, "deploy": 4, "derogatori": 1, "describ": [7, 9], "descript": 10, "design": 8, "desir": 6, "det_arch": [7, 11, 13, 15], "det_b": [], "det_model": [11, 13], "det_param": 11, "det_predictor": 11, "detail": [11, 16], "detect": [5, 9, 10, 11], "detect_languag": 7, "detect_orient": 7, "detection_predictor": [7, 16], "detection_task": [], "detectiondataset": [5, 14], "detectionmetr": 9, "detectionpredictor": [7, 11], "detector": [], "deterior": 7, "determin": 1, "dev": [2, 12], "develop": 3, "deviat": 8, "devic": 15, "dict": [6, 9, 16], "dictionari": [6, 9], "differ": 1, "differenti": [4, 7], "digit": [4, 5, 14], "dimens": [6, 9, 16], "dimension": 8, "direct": 5, "directli": [13, 16], "directori": [2, 12], "disabl": [1, 12], "disable_crop_orient": [], "disable_page_orient": [], "disclaim": 16, "discuss": 2, "disparag": 1, "displai": [6, 9], "display_artefact": 9, "distribut": 8, "div": 16, "divers": 1, "divid": 6, "do": [2, 3, 7], "doc": [2, 6, 15, 16], "docartefact": [5, 14], "docstr": 2, "doctr": [3, 11, 12, 13, 14, 16], "doctr_cache_dir": 12, "doctr_multiprocessing_dis": 12, "document": [5, 7, 9, 10, 14, 16], "documentbuild": [], "documentfil": [6, 13], "doesn": [], "don": [11, 16], "done": 8, "download": [5, 14], "download_from_url": [], "downsiz": 7, "draw": [8, 9], "draw_proba": 9, "drop": 5, "drop_last": 5, "dtype": [6, 7, 8, 9, 15], "dual": [], "dummi": 13, "dummy_img": 16, "dummy_input": 15, "dure": 1, "dutch": [], "dynam": 5, "dynamic_seq_length": 5, "e": [1, 2, 3, 6, 7], "each": [4, 5, 6, 7, 8, 9, 14, 16], "eas": 2, "easi": [4, 9, 13], "easili": [6, 9, 11, 13, 14, 16], "econom": 1, "edit": 1, "educ": 1, "effect": [], "effici": [2, 4, 5, 7], "either": [9, 16], "element": [5, 6, 7, 9, 16], "els": 2, "email": 1, "empathi": 1, "en": 16, "enabl": [5, 6], "enclos": 6, "encod": [4, 5, 6, 7, 16], "encode_sequ": 5, "encode_str": [], "encount": 2, "encrypt": 6, "end": [4, 5, 7, 9], "english": [5, 14], "enough": [2, 16], "ensur": 2, "entri": 5, "environ": [1, 12], "eo": 5, "equiv": 16, "estim": 7, "etc": 6, "ethnic": 1, "evalu": [14, 16], "event": 1, "everyon": 1, "everyth": [2, 16], "exact": [9, 16], "exampl": [1, 2, 4, 5, 7, 13], "exchang": 15, "execut": [], "exist": 13, "expand": 8, "expect": [6, 8, 9], "experi": 1, "explan": [1, 16], "explicit": 1, "exploit": [4, 7], "export": [6, 7, 9, 10, 16], "export_as_straight_box": [7, 16], "export_as_xml": 16, "export_model_to_onnx": 15, "express": [1, 8], "extens": 6, "extern": [1, 14], "extra": 3, "extract": [4, 5], "extractor": 7, "f_": 9, "f_a": 9, "factor": 8, "fair": 1, "fairli": 1, "fals": [5, 6, 7, 8, 9, 11, 16], "famili": 9, "faq": 1, "fascan": [], "fast": [4, 5, 7], "fast_bas": [], "fast_smal": [], "fast_tini": [], "faster": 15, "fasterrcnn_mobilenet_v3_large_fpn": 7, "favorit": 16, "featur": [3, 7, 9, 10], "feedback": 1, "feel": [2, 13], "felix92": 13, "few": [3, 15], "figsiz": 9, "figur": 9, "file": [2, 5], "final": 7, "find": [2, 3, 14], "fine": [], "finnish": [], "first": 2, "firsthand": 5, "fit": [7, 16], "flag": 16, "flip": 8, "float": [6, 8, 9, 15], "float32": [6, 7, 8, 15], "fn": 8, "focu": 13, "focus": [1, 5], "folder": 5, "follow": [1, 2, 3, 5, 8, 9, 11, 12, 13, 16], "font": [5, 9], "font_famili": [5, 9], "font_siz": 9, "foral": 9, "forc": 2, "forg": [], "form": [4, 5, 16], "format": [6, 9, 11, 14, 15, 16], "forpost": [4, 5], "forum": 2, "found": [], "fp16": 15, "frac": 9, "framework": [3, 13, 14, 16], "free": [1, 2, 13], "french": [5, 11, 13, 16], "friendli": 4, "from": [1, 4, 5, 6, 7, 8, 9, 10, 11, 14, 15, 16], "from_hub": [7, 13], "from_imag": [6, 13], "from_pdf": 6, "from_url": 6, "full": [5, 9, 16], "function": [5, 8, 9], "funsd": [4, 5, 14, 16], "further": 14, "futur": 5, "g": [6, 7], "g_": 9, "g_x": 9, "gallagh": [], "gamma": 8, "gaussian": 8, "gaussianblur": 8, "gaussiannois": 8, "gdk": 3, "gen": 16, "gender": 1, "gener": [2, 4, 7], "generic_cyrillic_lett": [], "geom": [], "geometri": [4, 6, 16], "geq": 9, "german": [5, 11], "get": 16, "git": 13, "github": [2, 3, 13], "give": 1, "given": [5, 6, 8, 9, 16], "global": 7, "go": 16, "good": 15, "googl": 2, "googlevis": 4, "gpu": [4, 15], "gracefulli": 1, "graph": 6, "grayscal": 8, "ground": 9, "groung": 9, "group": 4, "gt": 9, "gt_box": 9, "gt_label": 9, "gtk": 3, "guid": 2, "guidanc": 14, "gvision": 16, "h": [6, 7, 8], "h_": 9, "ha": [2, 5, 9, 14], "handl": 14, "handwrit": 5, "handwritten": 14, "harass": 1, "hardwar": [], "harm": 1, "hat": 9, "have": [1, 2, 9, 11, 13, 14, 16], "head": [7, 16], "healthi": 1, "hebrew": [], "height": 6, "hello": [9, 16], "help": 15, "here": [3, 8, 10, 14, 16], "hf": 7, "hf_hub_download": 7, "high": 6, "higher": [3, 5], "hindi": [], "hindi_digit": 5, "hocr": 16, "homebrew": 3, "hook": [], "horizont": [6, 8], "hous": 5, "how": [2, 11, 13, 14], "howev": 14, "hsv": 8, "html": [1, 2, 16], "http": [1, 3, 6, 7, 13, 16], "hub": 7, "hue": 8, "huggingfac": 7, "hw": 5, "i": [1, 2, 5, 6, 7, 8, 9, 12, 13, 14, 15], "i7": 16, "ibrahimov": [], "ic03": [4, 5, 14], "ic13": [4, 5, 14], "icdar": [4, 5], "icdar2019": 5, "id": 16, "ident": 1, "identifi": 4, "iiit": [4, 5], "iiit5k": [5, 14], "iiithw": [4, 5, 14], "imag": [4, 5, 6, 7, 8, 9, 13, 14, 16], "imagenet": 7, "imageri": 1, "images_90k_norm": 5, "imagetensor": [], "imagetransform": [], "img": [5, 8, 14], "img_cont": 6, "img_fold": [5, 14], "img_path": 6, "img_transform": 5, "imgur5k": [4, 5, 14], "imgur5k_annot": 5, "imlist": 5, "impact": 1, "implement": [5, 6, 8, 9, 16], "import": [5, 6, 7, 8, 9, 11, 13, 14, 15, 16], "improv": [], "inappropri": 1, "incid": 1, "includ": [1, 3, 5, 14, 15], "inclus": 1, "increas": 8, "independ": [], "index": [2, 6], "indic": 9, "individu": 1, "infer": [4, 7, 8], "inform": [1, 2, 4, 5, 14], "initi": [], "input": [2, 6, 7, 8, 15, 16], "input_crop": 7, "input_pag": [7, 9, 16], "input_seq": [], "input_shap": 15, "input_str": [], "input_tensor": 7, "inspir": [1, 8], "instal": 13, "instanc": [1, 16], "instanti": [7, 16], "instead": [5, 6, 7], "insult": 1, "int": [5, 6, 8, 9], "int64": [8, 9], "integ": 9, "integr": [4, 13, 14], "intel": 16, "interact": [1, 6, 9], "interfac": 13, "interoper": 15, "interpol": 8, "interpret": [5, 6], "intersect": 9, "invert": 8, "investig": 1, "invis": 1, "involv": [1, 16], "io": 13, "iou": 9, "iou_thresh": 9, "iou_threshold": [], "irregular": [4, 7, 14], "isn": 5, "issu": [1, 2, 13], "italian": [], "iter": [5, 8, 14, 16], "its": [6, 7, 8, 9, 14, 16], "itself": [7, 13], "j": 9, "jame": [], "job": 2, "join": 2, "jpeg": 8, "jpegqual": 8, "jpg": [5, 6, 13], "json": [5, 14, 16], "json_output": 16, "jump": 2, "just": 1, "kei": [], "kera": [7, 15], "kernel": 8, "kernel_shap": 8, "keywoard": [], "keyword": [5, 7], "kie": [7, 11], "kie_predictor": [7, 11], "kiepredictor": 7, "kind": [1, 16], "know": 2, "kwarg": [5, 6, 7, 9], "l": 9, "l_j": 9, "label": [5, 8, 9, 14], "label_fil": [5, 14], "label_fold": 5, "label_path": [5, 14], "labels_path": [5, 14], "ladder": 1, "lambda": 8, "lambdatransform": 8, "lang": 16, "languag": [1, 4, 5, 6, 7, 13, 16], "larg": [7, 13], "largest": 9, "last": [3, 5], "latenc": 7, "later": 2, "latest": [3, 16], "latin": 5, "layer": 15, "layout": 16, "lead": 1, "leader": 1, "learn": [1, 4, 7, 15, 16], "least": 3, "left": [9, 16], "legacy_french": 5, "length": 5, "less": 15, "level": [1, 5, 9, 16], "leverag": 10, "lf": 13, "libffi": 3, "librari": [2, 3, 10, 11], "light": 4, "lightweight": [], "like": 1, "limits_": 9, "line": [4, 9, 16], "line_1_1": 16, "link": 11, "linknet": [4, 7], "linknet_resnet18": [7, 11, 16], "linknet_resnet18_rot": [7, 16], "linknet_resnet34": [7, 15, 16], "linknet_resnet50": [7, 16], "linux": 3, "list": [5, 6, 8, 9, 13], "ll": 9, "load": [4, 5, 7], "load_state_dict": 11, "load_weight": 11, "loc_pr": [], "local": [2, 4, 5, 7, 9, 14, 16], "localis": 5, "localizationconfus": 9, "locat": [2, 6], "login": 7, "login_to_hub": [7, 13], "logo": [6, 14], "love": 13, "lower": [8, 9], "m": [2, 9, 16], "m1": 3, "macbook": 3, "machin": 15, "maco": 3, "made": 4, "magc_resnet31": 7, "mai": [1, 2], "mail": 1, "main": 10, "maintain": 4, "mainten": 2, "make": [1, 2, 9, 12, 13, 15, 16], "mani": [14, 16], "manipul": [], "map": 5, "map_loc": 11, "mask": [], "mask_label": [], "mask_shap": 9, "master": [4, 7, 16], "match": [9, 16], "mathcal": 9, "matplotlib": 9, "max": [5, 8, 9], "max_angl": 8, "max_area": 8, "max_char": [5, 14], "max_delta": 8, "max_font_s": [], "max_gain": 8, "max_gamma": 8, "max_qual": 8, "max_ratio": 8, "maximum": [5, 8], "maxval": [7, 8], "mbox": 9, "mean": [8, 9, 11], "meaniou": 9, "meant": [6, 15], "measur": 16, "media": 1, "median": [], "meet": 11, "member": 1, "memori": [9, 12, 15], "mention": 16, "merg": 5, "messag": 2, "meta": 16, "metadata": 15, "metal": 3, "method": [8, 16], "metric": [9, 16], "middl": [], "might": [15, 16], "min": 8, "min_area": 8, "min_char": [5, 14], "min_font_s": [], "min_gain": 8, "min_gamma": 8, "min_qual": 8, "min_ratio": 8, "min_val": 8, "minde": [1, 3, 4, 7], "minim": [2, 4], "minimalist": [], "minimum": [3, 5, 8, 9], "minval": 8, "miss": 3, "mistak": 1, "mixed_float16": 15, "mixed_precis": 15, "mjsynth": [4, 5, 14], "mnt": 5, "mobilenet": [7, 13], "mobilenet_v3_larg": 7, "mobilenet_v3_large_r": 7, "mobilenet_v3_smal": 7, "mobilenet_v3_small_crop_orient": [], "mobilenet_v3_small_orient": 7, "mobilenet_v3_small_page_orient": [], "mobilenet_v3_small_r": 7, "mobilenetv3": 7, "modal": [], "mode": 3, "model": [5, 9, 12, 14], "model_nam": [7, 13, 15], "model_path": 15, "moder": 1, "modif": 2, "modifi": [7, 12], "modul": [6, 8, 9, 16], "moment": 16, "more": [2, 9, 14, 16], "moscardi": [], "most": 16, "mozilla": 1, "multi": [4, 7], "multiclass": [], "multilingu": [], "multipl": [5, 6, 8], "multipli": 8, "multiprocess": 12, "my": 7, "my_awesome_model": 13, "my_hook": [], "n": [5, 9], "name": [5, 7, 15, 16], "nation": 1, "natur": [1, 4, 5], "nb": 16, "ndarrai": [5, 6, 8, 9], "necessari": [3, 11, 12], "need": [2, 3, 5, 9, 11, 12, 13], "neg": 8, "nest": 16, "netraj": [], "network": [4, 5, 7, 15], "neural": [4, 5, 7, 15], "new": [2, 9], "next": [5, 14], "nois": 8, "noisi": [4, 5], "non": [4, 5, 6, 7, 8, 9], "none": [5, 6, 7, 8, 9, 16], "normal": [7, 8], "norwegian": [], "note": [0, 2, 5, 7, 13, 15], "now": 2, "np": [7, 8, 9, 16], "num_output_channel": 8, "num_sampl": [5, 14], "num_work": 5, "number": [5, 8, 9, 16], "numpi": [6, 7, 9, 16], "o": 3, "obb": [], "obj_detect": 13, "object": [5, 9, 10, 16], "objectness_scor": [], "oblig": 1, "obtain": 16, "occupi": 15, "ocr": [4, 5, 7, 9, 13, 14], "ocr_carea": 16, "ocr_db_crnn": 9, "ocr_lin": 16, "ocr_pag": 16, "ocr_par": 16, "ocr_predictor": [7, 11, 13, 15, 16], "ocrdataset": [5, 14], "ocrmetr": 9, "ocrpredictor": [7, 11], "ocrx_word": 16, "offens": 1, "offici": 1, "offlin": 1, "offset": 8, "onc": 16, "one": [2, 5, 7, 8, 11, 13, 16], "oneof": 8, "ones": [5, 8, 9], "onli": [2, 7, 8, 9, 13, 14, 15, 16], "onlin": 1, "onnx": [], "onnxruntim": [], "onnxtr": [], "opac": 8, "opacity_rang": 8, "open": [1, 2, 13, 15], "opinion": 1, "optic": [4, 16], "optim": 4, "option": [5, 11], "order": [2, 5, 6, 8], "org": [1, 7, 16], "organ": 6, "orient": [1, 6, 7, 16], "orientationpredictor": [], "other": [1, 2], "otherwis": [1, 6, 9], "our": [2, 7, 16], "out": [2, 7, 8, 9, 16], "out_box": [], "outpout": 16, "output": [6, 8, 15], "output_s": [6, 8], "outsid": 12, "over": [3, 5, 9, 16], "overal": [1, 7], "overlai": 6, "overview": [], "overwrit": [], "overwritten": 13, "own": 4, "p": [8, 9, 16], "packag": [2, 4, 9, 12, 14], "pad": [5, 7, 8, 16], "page": [3, 5, 7, 9, 16], "page1": 6, "page2": 6, "page_1": 16, "page_idx": [6, 16], "page_orientation_predictor": [], "page_param": [], "pair": 9, "pango": 3, "paper": 7, "par_1_1": 16, "paragraph": [], "paragraph_break": [], "parallel": [], "param": [8, 16], "paramet": [4, 5, 6, 7, 8, 9, 15], "pars": [4, 5], "parseq": [4, 7, 16], "part": [5, 8, 16], "parti": 3, "partial": 16, "particip": 1, "pass": [5, 6, 7, 16], "password": 6, "patch": 7, "path": [5, 6, 14], "path_to_checkpoint": 11, "path_to_custom_model": [], "path_to_pt": 11, "patil": [], "pattern": 1, "pdf": [6, 7, 10], "pdfpage": 6, "peopl": 1, "per": [8, 16], "perform": [4, 6, 8, 9, 12, 15, 16], "period": 1, "permiss": 1, "permut": [4, 7], "persian_lett": 5, "person": [1, 14], "phase": 16, "photo": 14, "physic": [1, 6], "pick": 8, "pictur": 6, "pip": [2, 3], "pipelin": [], "pixbuf": 3, "pixel": [6, 8, 16], "pleas": 2, "plot": 9, "plt": 9, "plug": 13, "plugin": 3, "png": 6, "point": 15, "polici": 12, "polish": [], "polit": 1, "polygon": [5, 16], "pool": 7, "portugues": 5, "posit": [1, 9], "possibl": [2, 9, 13], "post": [1, 16], "postprocessor": [], "potenti": 7, "power": 4, "ppageno": 16, "pre": [2, 7], "pre_transform_multiclass": [], "precis": [9, 16], "pred": 9, "pred_box": 9, "pred_label": 9, "predefin": 14, "predict": [6, 7, 9], "predictor": [4, 6, 7, 11, 13, 15], "prefer": 14, "preinstal": [], "preprocessor": [11, 16], "prerequisit": 13, "present": 10, "preserv": [7, 8, 16], "preserve_aspect_ratio": [6, 7, 8, 11, 16], "pretrain": [4, 7, 9, 11, 15, 16], "pretrained_backbon": [7, 11], "print": 16, "prior": 5, "privaci": 1, "privat": 1, "probabl": 8, "problem": 2, "procedur": 8, "process": [2, 4, 6, 11, 16], "processor": 16, "produc": [10, 16], "product": 15, "profession": 1, "project": [2, 14], "promptli": 1, "proper": 2, "properli": 5, "provid": [1, 2, 4, 13, 14, 16], "public": [1, 4], "publicli": 16, "publish": 1, "pull": 13, "punctuat": 5, "pure": 5, "purpos": 2, "push_to_hf_hub": [7, 13], "py": 13, "pypdfium2": 6, "pyplot": 9, "python": 2, "python3": 13, "pytorch": [3, 4, 7, 8, 11, 13, 15, 16], "q": 2, "qr": 6, "qr_code": 14, "qualiti": 8, "question": 1, "quickli": 4, "quicktour": 10, "r": 16, "race": 1, "ramdisk": 5, "rand": [7, 8, 9, 15, 16], "random": [7, 8, 9, 16], "randomappli": 8, "randombright": 8, "randomcontrast": 8, "randomcrop": 8, "randomgamma": 8, "randomhorizontalflip": 8, "randomhu": 8, "randomjpegqu": 8, "randomli": 8, "randomres": [], "randomrot": 8, "randomsatur": 8, "randomshadow": 8, "rang": 8, "rassi": [], "ratio": [7, 8, 16], "raw": [6, 9], "re": 15, "read": [4, 5, 7], "read_html": 6, "read_img": 6, "read_img_as_numpi": 6, "read_img_as_tensor": 6, "read_pdf": 6, "readi": 15, "real": [4, 7, 8], "realli": [], "reason": 1, "rebuild": 2, "rebuilt": 2, "recal": [9, 16], "receipt": [4, 5, 16], "reco_arch": [7, 11, 13, 15], "reco_b": [], "reco_model": [11, 13], "reco_param": 11, "reco_predictor": 11, "recogn": 16, "recognit": [5, 9, 11], "recognition_predictor": [7, 16], "recognition_task": [5, 14], "recognitiondataset": [5, 14], "recognitionpredictor": [7, 11], "rectangular": 7, "red": 9, "reduc": [3, 8], "refer": [2, 3, 11, 13, 14, 16], "regardless": 1, "region": [], "regroup": 9, "regular": 14, "reject": 1, "rel": [6, 8, 9], "relat": 6, "releas": [0, 3], "relev": [], "religion": 1, "remov": 1, "render": 6, "repo": 7, "repo_id": [7, 13], "report": 1, "repositori": [5, 7, 13], "repres": [1, 9, 15, 16], "represent": [4, 7], "request": [1, 13], "requir": [3, 8], "research": 4, "residu": 7, "resiz": [8, 16], "resnet": 7, "resnet18": [7, 13], "resnet31": 7, "resnet34": 7, "resnet50": [7, 13], "resolv": 6, "resolve_block": [], "resolve_lin": [], "resourc": 14, "respect": 1, "respons": 9, "rest": [2, 8, 9], "restrict": 12, "result": [2, 5, 6, 10, 13, 16], "return": [5, 6, 7, 9, 16], "reusabl": 16, "review": 1, "rgb": [6, 8], "rgb_mode": 6, "rgb_output": 6, "right": [1, 7, 9], "roboflow": [], "robust": [4, 5], "root": 5, "rotat": [5, 6, 7, 8, 9, 14, 16], "run": [2, 3, 7], "same": [2, 6, 9, 14, 16], "sampl": [5, 14, 16], "sample_transform": 5, "samplecompos": [], "sanjin": [], "sar": [4, 7], "sar_resnet31": [7, 16], "satur": 8, "save": [7, 14], "scale": [6, 7, 8, 9], "scale_rang": [], "scan": [4, 5], "scene": [4, 5, 7], "score": 9, "script": [2, 14], "seamless": 4, "seamlessli": [4, 16], "search": 7, "searchabl": 10, "sec": 16, "second": 16, "section": [11, 13, 15, 16], "secur": [1, 12], "see": [1, 2], "seen": 16, "segment": [4, 7, 16], "self": [], "semant": [4, 7], "send": 16, "sens": 9, "sensit": 14, "separ": 16, "sequenc": [4, 5, 6, 7, 9, 16], "sequenti": 8, "seri": 1, "seriou": 1, "set": [1, 5, 7, 9, 12, 16], "set_global_polici": 15, "sever": [6, 8, 16], "sex": 1, "sexual": 1, "shade": 8, "shape": [6, 7, 8, 9, 16], "share": [12, 14], "shift": 8, "shm": 12, "should": [2, 5, 6, 8, 9], "show": [4, 6, 7, 9, 11, 13], "showcas": 2, "shuffl": [5, 8], "side": 9, "signatur": 6, "signific": 14, "simpl": [4, 7], "simpler": 7, "sinc": [5, 14], "singl": [1, 2, 4, 5], "single_img_doc": [], "size": [1, 5, 6, 8, 9, 16], "skew": 16, "slack": 2, "slightli": 7, "small": [2, 7], "smallest": 6, "smooth": [], "smoothing_factor": [], "snapshot_download": 7, "snippet": 16, "so": [2, 3, 5, 7, 13, 14], "social": 1, "socio": 1, "some": [3, 10, 13, 14], "someth": 2, "somewher": 2, "soon": 15, "sort": 1, "sourc": [5, 6, 7, 8, 9, 13], "space": 1, "span": 16, "spanish": 5, "spatial": [6, 9], "specif": [2, 3, 9, 11, 14, 16], "specifi": [1, 5, 6], "speed": [4, 7], "sphinx": 2, "sroie": [4, 5, 14], "stabl": 3, "stackoverflow": 2, "stage": 4, "standalon": [], "standard": 8, "start": 5, "state": [4, 9], "static": 9, "statist": [], "statu": 1, "std": [8, 11], "step": 12, "still": 16, "str": [5, 6, 7, 8, 9], "straight": [5, 7, 14, 16], "straighten": [], "straighten_pag": [], "straigten_pag": [], "stream": 6, "street": [4, 5], "strict": [], "strictli": 9, "string": [5, 6, 9, 16], "strive": 3, "strong": [4, 7], "structur": [15, 16], "subset": [5, 16], "suggest": [2, 13], "sum": 9, "summari": 9, "support": [15, 16], "sustain": 1, "svhn": [4, 5, 14], "svt": [5, 14], "swedish": [], "symmetr": [7, 8, 16], "symmetric_pad": [7, 8, 16], "synthes": 9, "synthesize_pag": 9, "synthet": 4, "synthtext": [4, 5, 14], "system": 16, "t": [2, 5, 11, 16], "tabl": 13, "take": [1, 5, 16], "target": [5, 6, 8, 9, 14], "target_s": 5, "task": [4, 5, 7, 13, 14, 16], "task2": 5, "team": [], "techminde": [], "templat": [2, 4], "tensor": [5, 6, 8, 16], "tensorflow": [3, 4, 6, 7, 8, 11, 13, 15, 16], "tensorspec": 15, "term": 1, "test": 14, "test_set": 5, "text": [5, 6, 7, 9, 14], "text_output": [], "textmatch": 9, "textnet": [], "textnet_bas": [], "textnet_smal": [], "textnet_tini": [], "textract": [4, 16], "textstylebrush": [4, 5], "textual": [4, 5, 6, 7, 16], "tf": [3, 6, 7, 8, 13, 15], "than": [2, 3, 9, 13], "thank": 2, "thei": [1, 9], "them": [3, 5, 16], "thi": [1, 2, 3, 5, 9, 11, 12, 13, 14, 15, 16], "thing": [15, 16], "third": 3, "those": [1, 3, 6, 16], "threaten": 1, "threshold": [], "through": [1, 8, 14], "tilman": [], "time": [1, 4, 7, 9, 14], "tini": [], "titl": [6, 16], "tm": 16, "tmp": 12, "togeth": [2, 6], "tograi": 8, "tool": 14, "top": [9, 16], "topic": 2, "torch": [3, 8, 11, 13, 15], "torchvis": 8, "total": 11, "toward": [1, 3], "train": [2, 5, 7, 8, 13, 14, 15, 16], "train_it": [5, 14], "train_load": [5, 14], "train_pytorch": 13, "train_set": [5, 14], "train_tensorflow": 13, "trainabl": [4, 7], "tranform": 8, "transcrib": 16, "transfer": [4, 5], "transfo": 8, "transform": [4, 5, 7], "translat": 1, "troll": 1, "true": [5, 6, 7, 8, 9, 11, 12, 13, 14, 15, 16], "truth": 9, "tune": 15, "tupl": [5, 6, 8, 9], "turn": [], "two": [6, 12], "txt": 5, "type": [6, 13, 15, 16], "typic": 16, "u": [1, 2], "ucsd": 5, "udac": 2, "uint8": [6, 7, 9, 16], "ukrainian": [], "unaccept": 1, "underli": 14, "underneath": 6, "understand": [4, 5, 16], "unidecod": 9, "uniform": [7, 8], "uniformli": 8, "uninterrupt": [6, 16], "union": 9, "unit": [], "unittest": 2, "unknown": [], "unknown_char": [], "unlock": 6, "unoffici": 7, "unprofession": 1, "unsolicit": 1, "unsupervis": 4, "unwelcom": 1, "up": [7, 16], "updat": 9, "upgrad": 2, "upper": [5, 8], "uppercas": 14, "url": 6, "us": [1, 2, 3, 5, 7, 9, 11, 12, 13, 16], "usabl": 16, "usag": [12, 15], "use_broadcast": 9, "use_polygon": [5, 9, 14], "useabl": 16, "useless": [], "user": [3, 4, 6, 10], "utf": 16, "util": 15, "v1": 13, "v3": [7, 13, 16], "valid": 14, "valu": [2, 6, 8, 16], "valuabl": 4, "variabl": 12, "varieti": 5, "veri": 7, "verma": [], "version": [1, 2, 3, 15, 16], "vgg": 7, "vgg16": 13, "vgg16_bn_r": 7, "via": 1, "video": [], "vietnames": 5, "view": [4, 5], "viewpoint": 1, "violat": 1, "visibl": 1, "vision": [4, 5, 7], "visiondataset": 5, "visiontransform": 7, "visual": 4, "visualize_pag": 9, "vit_": 7, "vit_b": 7, "vitstr": [4, 7, 15], "vitstr_bas": [7, 16], "vitstr_smal": [7, 11, 15, 16], "viz": [], "vocab": [11, 13, 14, 16], "vocab_nam": [], "vocabulari": [5, 11, 13], "w": [6, 7, 8, 9], "w3": 16, "wa": 1, "wai": [1, 4, 14], "want": [2, 15, 16], "warmup": 16, "wasn": 2, "we": [1, 2, 3, 4, 6, 8, 13, 14, 15, 16], "weasyprint": [], "web": [2, 6], "websit": 5, "weight": 11, "welcom": 1, "well": [1, 15], "were": [1, 6, 16], "what": 1, "when": [1, 2, 7], "whenev": 2, "where": [2, 6, 8, 9], "whether": [2, 5, 6, 8, 9, 14], "which": [1, 7, 12, 14, 16], "whichev": 3, "while": [8, 16], "why": 1, "width": 6, "wiki": 1, "wildreceipt": [], "window": [3, 7, 9], "wish": 2, "within": 1, "without": [1, 5, 7], "wonder": 2, "word": [4, 5, 7, 9, 16], "word_1_1": 16, "word_1_2": 16, "word_1_3": 16, "wordgener": [5, 14], "words_onli": 9, "work": [12, 16], "worker": 5, "workflow": 2, "worklow": 2, "world": [9, 16], "worth": 7, "would": [], "wrap": 16, "wrapper": [5, 8], "write": 12, "written": [1, 6], "www": [1, 6, 16], "x": [6, 8, 9], "x_ascend": 16, "x_descend": 16, "x_i": 9, "x_size": 16, "x_wconf": 16, "xhtml": 16, "xmax": 6, "xmin": 6, "xml": 16, "xml_bytes_str": 16, "xml_element": 16, "xml_output": 16, "xmln": 16, "y": 9, "y_i": 9, "y_j": 9, "yet": [], "ymax": 6, "ymin": 6, "yolov8": [], "yolov8_artefact": [], "you": [2, 3, 5, 6, 7, 11, 12, 13, 14, 15, 16], "your": [2, 4, 6, 9, 16], "yoursit": 6, "yugesh": [], "zero": [8, 9], "zoo": [], "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 5, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 5, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": [], "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 5, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 5, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": [], "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 5, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 5, "\u00e4\u00f6\u00e4\u00f6": [], "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 5, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": [], "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": [], "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": [], "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 5, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": [], "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": [], "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": [], "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": [], "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 5, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 5, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 5, "\u067e\u0686\u06a2\u06a4\u06af": 5, "\u0905": [], "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": [], "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": [], "\u0950": [], "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": [], "\u09bd": [], "\u09ce": [], "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": []}, "titles": ["Changelog", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 2, "0": 0, "01": 0, "02": 0, "03": 0, "04": [], "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 1], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 1], "2021": 0, "2022": 0, "2023": [], "2024": [], "21": [], "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 1], "31": 0, "4": [0, 1], "5": 0, "6": 0, "7": [], "8": [], "9": [], "advanc": [], "approach": 16, "architectur": 16, "artefact": 6, "artefactdetect": [], "attribut": 1, "avail": [14, 16], "aw": 12, "ban": 1, "block": 6, "bug": 2, "changelog": 0, "choos": [14, 16], "classif": [7, 13], "code": [1, 2], "codebas": 2, "commit": 2, "commun": 13, "compos": 8, "conda": [], "conduct": 1, "connect": 2, "continu": 2, "contrib": [], "contribut": 2, "contributor": 1, "convent": 13, "correct": 1, "coven": 1, "custom": [5, 11], "data": 14, "dataload": 5, "dataset": [4, 5, 14], "detect": [4, 7, 13, 14, 16], "develop": 2, "do": 16, "doctr": [2, 4, 5, 6, 7, 8, 9, 10, 15], "document": [2, 4, 6], "end": 16, "enforc": 1, "evalu": 9, "export": 15, "factori": 7, "featur": [2, 4], "feedback": 2, "file": 6, "from": 13, "gener": [5, 14], "git": 3, "guidelin": 1, "half": 15, "hub": 13, "huggingfac": 13, "i": 16, "infer": 15, "instal": [2, 3], "integr": 2, "io": 6, "lambda": 12, "let": 2, "line": 6, "linux": [], "load": [11, 13, 14], "loader": 5, "main": 4, "mode": 2, "model": [4, 7, 11, 13, 15, 16], "modifi": 2, "modul": [], "name": 13, "notebook": 10, "object": 14, "ocr": 16, "onli": [], "onnx": 15, "optim": 15, "option": [], "orient": [], "our": 1, "output": 16, "own": [11, 14], "packag": 3, "page": 6, "perman": 1, "pipelin": [], "pledg": 1, "precis": 15, "predictor": 16, "prepar": 15, "prerequisit": 3, "pretrain": 13, "push": 13, "python": 3, "qualiti": 2, "question": 2, "read": 6, "readi": 14, "recognit": [4, 7, 13, 14, 16], "reconstitut": [], "report": 2, "request": 2, "resourc": [], "respons": 1, "right": 16, "scope": 1, "share": 13, "should": 16, "stage": 16, "standard": 1, "structur": [2, 6], "style": 2, "support": [4, 5, 8], "synthet": [5, 14], "task": 9, "temporari": 1, "test": 2, "text": [4, 16], "train": 11, "transform": 8, "two": 16, "unit": 2, "us": [14, 15], "util": 9, "v0": 0, "verif": 2, "via": 3, "visual": 9, "vocab": 5, "warn": 1, "what": 16, "word": 6, "your": [11, 13, 14, 15], "zoo": [4, 7]}})
\ No newline at end of file
diff --git a/v0.8.0/searchindex.js b/v0.8.0/searchindex.js
index 5e73be3ff1..44746de16c 100644
--- a/v0.8.0/searchindex.js
+++ b/v0.8.0/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"alltitles": {"1. Correction": [[1, "correction"]], "2. Warning": [[1, "warning"]], "3. Temporary Ban": [[1, "temporary-ban"]], "4. Permanent Ban": [[1, "permanent-ban"]], "AWS Lambda": [[12, null]], "Advanced options": [[16, "advanced-options"]], "Args:": [[5, "args"], [5, "id4"], [5, "id7"], [5, "id10"], [5, "id13"], [5, "id16"], [5, "id19"], [5, "id22"], [5, "id25"], [5, "id29"], [5, "id32"], [5, "id37"], [5, "id40"], [5, "id46"], [5, "id49"], [5, "id50"], [5, "id51"], [5, "id54"], [5, "id57"], [5, "id60"], [5, "id61"], [6, "args"], [6, "id2"], [6, "id3"], [6, "id4"], [6, "id5"], [6, "id6"], [6, "id7"], [6, "id10"], [6, "id12"], [6, "id14"], [6, "id16"], [6, "id20"], [6, "id24"], [6, "id28"], [7, "args"], [7, "id3"], [7, "id8"], [7, "id13"], [7, "id17"], [7, "id21"], [7, "id26"], [7, "id31"], [7, "id36"], [7, "id41"], [7, "id45"], [7, "id49"], [7, "id54"], [7, "id58"], [7, "id63"], [7, "id68"], [7, "id72"], [7, "id76"], [7, "id81"], [7, "id86"], [7, "id90"], [7, "id95"], [7, "id99"], [7, "id103"], [7, "id108"], [7, "id113"], [7, "id118"], [7, "id122"], [7, "id126"], [7, "id131"], [7, "id135"], [7, "id139"], [7, "id143"], [7, "id145"], [7, "id147"], [7, "id149"], [8, "args"], [8, "id1"], [8, "id2"], [8, "id3"], [8, "id4"], [8, "id5"], [8, "id6"], [8, "id7"], [8, "id8"], [8, "id9"], [8, "id10"], [8, "id11"], [8, "id12"], [8, "id13"], [8, "id14"], [8, "id15"], [8, "id16"], [8, "id17"], [8, "id18"], [9, "args"], [9, "id3"], [9, "id5"], [9, "id6"], [9, "id7"], [9, "id8"], [9, "id9"], [9, "id10"], [9, "id11"]], "Artefact": [[6, "artefact"]], "Attribution": [[1, "attribution"]], "Available Datasets": [[14, "available-datasets"]], "Available architectures": [[16, "available-architectures"], [16, "id1"], [16, "id2"]], "Block": [[6, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[14, null]], "Choosing the right model": [[16, null]], "Classification": [[13, "classification"]], "Code quality": [[2, "code-quality"]], "Code style verification": [[2, "code-style-verification"]], "Codebase structure": [[2, "codebase-structure"]], "Commits": [[2, "commits"]], "Composing transformations": [[8, "composing-transformations"]], "Continuous Integration": [[2, "continuous-integration"]], "Contributing to docTR": [[2, null]], "Contributor Covenant Code of Conduct": [[1, null]], "Custom dataset loader": [[5, "custom-dataset-loader"]], "Data Loading": [[14, "data-loading"]], "Dataloader": [[5, "dataloader"]], "Detection": [[13, "detection"], [14, "detection"]], "Detection predictors": [[16, "detection-predictors"]], "Developer mode installation": [[2, "developer-mode-installation"]], "Developing docTR": [[2, "developing-doctr"]], "Document": [[6, "document"]], "Document structure": [[6, "document-structure"]], "End-to-End OCR": [[16, "end-to-end-ocr"]], "Enforcement": [[1, "enforcement"]], "Enforcement Guidelines": [[1, "enforcement-guidelines"]], "Enforcement Responsibilities": [[1, "enforcement-responsibilities"]], "Export to ONNX": [[15, "export-to-onnx"]], "Feature requests & bug report": [[2, "feature-requests-bug-report"]], "Feedback": [[2, "feedback"]], "File reading": [[6, "file-reading"]], "Half-precision": [[15, "half-precision"]], "Installation": [[3, null]], "Let\u2019s connect": [[2, "let-s-connect"]], "Line": [[6, "line"]], "Loading from Huggingface Hub": [[13, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[11, "loading-your-custom-trained-model"]], "Main Features": [[4, "main-features"]], "Model optimization": [[15, "model-optimization"]], "Model zoo": [[4, "model-zoo"]], "Modifying the documentation": [[2, "modifying-the-documentation"]], "Naming conventions": [[13, "naming-conventions"]], "Object Detection": [[14, "object-detection"]], "Our Pledge": [[1, "our-pledge"]], "Our Standards": [[1, "our-standards"]], "Page": [[6, "page"]], "Preparing your model for inference": [[15, null]], "Prerequisites": [[3, "prerequisites"]], "Pretrained community models": [[13, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[13, "pushing-to-the-huggingface-hub"]], "Questions": [[2, "questions"]], "Recognition": [[13, "recognition"], [14, "recognition"]], "Recognition predictors": [[16, "recognition-predictors"]], "Returns:": [[5, "returns"], [6, "returns"], [6, "id11"], [6, "id13"], [6, "id15"], [6, "id19"], [6, "id23"], [6, "id27"], [6, "id31"], [7, "returns"], [7, "id6"], [7, "id11"], [7, "id16"], [7, "id20"], [7, "id24"], [7, "id29"], [7, "id34"], [7, "id39"], [7, "id44"], [7, "id48"], [7, "id52"], [7, "id57"], [7, "id61"], [7, "id66"], [7, "id71"], [7, "id75"], [7, "id79"], [7, "id84"], [7, "id89"], [7, "id93"], [7, "id98"], [7, "id102"], [7, "id106"], [7, "id111"], [7, "id116"], [7, "id121"], [7, "id125"], [7, "id129"], [7, "id134"], [7, "id138"], [7, "id142"], [7, "id144"], [7, "id146"], [7, "id148"], [9, "returns"], [9, "id4"]], "Scope": [[1, "scope"]], "Share your model with the community": [[13, null]], "Supported Vocabs": [[5, "supported-vocabs"]], "Supported datasets": [[4, "supported-datasets"]], "Supported transformations": [[8, "supported-transformations"]], "Synthetic dataset generator": [[5, "synthetic-dataset-generator"], [14, "synthetic-dataset-generator"]], "Task evaluation": [[9, "task-evaluation"]], "Text Detection": [[16, "text-detection"]], "Text Recognition": [[16, "text-recognition"]], "Text detection models": [[4, "text-detection-models"]], "Text recognition models": [[4, "text-recognition-models"]], "Train your own model": [[11, null]], "Two-stage approaches": [[16, "two-stage-approaches"]], "Unit tests": [[2, "unit-tests"]], "Use your own datasets": [[14, "use-your-own-datasets"]], "Using your ONNX exported model in docTR": [[15, "using-your-onnx-exported-model-in-doctr"]], "Via Git": [[3, "via-git"]], "Via Python Package": [[3, "via-python-package"]], "Visualization": [[9, "visualization"]], "What should I do with the output?": [[16, "what-should-i-do-with-the-output"]], "Word": [[6, "word"]], "docTR Notebooks": [[10, null]], "docTR Vocabs": [[5, "id62"]], "docTR: Document Text Recognition": [[4, null]], "doctr.datasets": [[5, null], [5, "datasets"]], "doctr.io": [[6, null]], "doctr.models": [[7, null]], "doctr.models.classification": [[7, "doctr-models-classification"]], "doctr.models.detection": [[7, "doctr-models-detection"]], "doctr.models.factory": [[7, "doctr-models-factory"]], "doctr.models.recognition": [[7, "doctr-models-recognition"]], "doctr.models.zoo": [[7, "doctr-models-zoo"]], "doctr.transforms": [[8, null]], "doctr.utils": [[9, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2024-09-09)": [[0, "v0-7-0-2024-09-09"]]}, "docnames": ["changelog", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[6, "doctr.io.Artefact", false]], "block (class in doctr.io)": [[6, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms)": [[8, "doctr.transforms.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[5, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms)": [[8, "doctr.transforms.ColorInversion", false]], "compose (class in doctr.transforms)": [[8, "doctr.transforms.Compose", false]], "cord (class in doctr.datasets)": [[5, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[7, "doctr.models.classification.crop_orientation_predictor", false]], "dataloader (class in doctr.datasets.loader)": [[5, "doctr.datasets.loader.DataLoader", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[7, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[7, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[6, "doctr.io.decode_img_as_tensor", false]], "detection_predictor() (in module doctr.models.detection)": [[7, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[5, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[5, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[6, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[6, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[5, "doctr.datasets.encode_sequences", false]], "from_hub() (in module doctr.models.factory)": [[7, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[6, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[6, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[6, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[5, "doctr.datasets.FUNSD", false]], "gaussianblur (class in doctr.transforms)": [[8, "doctr.transforms.GaussianBlur", false]], "gaussiannoise (class in doctr.transforms)": [[8, "doctr.transforms.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[5, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[5, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[5, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[5, "doctr.datasets.IIITHWS", false]], "imgur5k (class in doctr.datasets)": [[5, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[7, "doctr.models.kie_predictor", false]], "lambdatransformation (class in doctr.transforms)": [[8, "doctr.transforms.LambdaTransformation", false]], "line (class in doctr.io)": [[6, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[7, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[7, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[7, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[7, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[7, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[5, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_orientation() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_small_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_small_r", false]], "normalize (class in doctr.transforms)": [[8, "doctr.transforms.Normalize", false]], "ocr_predictor() (in module doctr.models)": [[7, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[5, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms)": [[8, "doctr.transforms.OneOf", false]], "page (class in doctr.io)": [[6, "doctr.io.Page", false]], "parseq() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.parseq", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[7, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms)": [[8, "doctr.transforms.RandomApply", false]], "randombrightness (class in doctr.transforms)": [[8, "doctr.transforms.RandomBrightness", false]], "randomcontrast (class in doctr.transforms)": [[8, "doctr.transforms.RandomContrast", false]], "randomcrop (class in doctr.transforms)": [[8, "doctr.transforms.RandomCrop", false]], "randomgamma (class in doctr.transforms)": [[8, "doctr.transforms.RandomGamma", false]], "randomhorizontalflip (class in doctr.transforms)": [[8, "doctr.transforms.RandomHorizontalFlip", false]], "randomhue (class in doctr.transforms)": [[8, "doctr.transforms.RandomHue", false]], "randomjpegquality (class in doctr.transforms)": [[8, "doctr.transforms.RandomJpegQuality", false]], "randomrotate (class in doctr.transforms)": [[8, "doctr.transforms.RandomRotate", false]], "randomsaturation (class in doctr.transforms)": [[8, "doctr.transforms.RandomSaturation", false]], "randomshadow (class in doctr.transforms)": [[8, "doctr.transforms.RandomShadow", false]], "read_html() (in module doctr.io)": [[6, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[6, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[6, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[6, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[5, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms)": [[8, "doctr.transforms.Resize", false]], "resnet18() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet50", false]], "sar_resnet31() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[6, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[6, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[5, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[9, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[9, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[9, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[9, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[5, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[5, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.visualization)": [[9, "doctr.utils.visualization.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[5, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[7, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[7, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[7, "doctr.models.classification.textnet_tiny", false]], "togray (class in doctr.transforms)": [[8, "doctr.transforms.ToGray", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[9, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[9, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[9, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[9, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[7, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[9, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[7, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[7, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[5, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[6, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[5, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.datasets": [[5, 0, 1, "", "CORD"], [5, 0, 1, "", "CharacterGenerator"], [5, 0, 1, "", "DetectionDataset"], [5, 0, 1, "", "DocArtefacts"], [5, 0, 1, "", "FUNSD"], [5, 0, 1, "", "IC03"], [5, 0, 1, "", "IC13"], [5, 0, 1, "", "IIIT5K"], [5, 0, 1, "", "IIITHWS"], [5, 0, 1, "", "IMGUR5K"], [5, 0, 1, "", "MJSynth"], [5, 0, 1, "", "OCRDataset"], [5, 0, 1, "", "RecognitionDataset"], [5, 0, 1, "", "SROIE"], [5, 0, 1, "", "SVHN"], [5, 0, 1, "", "SVT"], [5, 0, 1, "", "SynthText"], [5, 0, 1, "", "WILDRECEIPT"], [5, 0, 1, "", "WordGenerator"], [5, 1, 1, "", "encode_sequences"]], "doctr.datasets.loader": [[5, 0, 1, "", "DataLoader"]], "doctr.io": [[6, 0, 1, "", "Artefact"], [6, 0, 1, "", "Block"], [6, 0, 1, "", "Document"], [6, 0, 1, "", "DocumentFile"], [6, 0, 1, "", "Line"], [6, 0, 1, "", "Page"], [6, 0, 1, "", "Word"], [6, 1, 1, "", "decode_img_as_tensor"], [6, 1, 1, "", "read_html"], [6, 1, 1, "", "read_img_as_numpy"], [6, 1, 1, "", "read_img_as_tensor"], [6, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[6, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[6, 2, 1, "", "from_images"], [6, 2, 1, "", "from_pdf"], [6, 2, 1, "", "from_url"]], "doctr.io.Page": [[6, 2, 1, "", "show"]], "doctr.models": [[7, 1, 1, "", "kie_predictor"], [7, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[7, 1, 1, "", "crop_orientation_predictor"], [7, 1, 1, "", "magc_resnet31"], [7, 1, 1, "", "mobilenet_v3_large"], [7, 1, 1, "", "mobilenet_v3_large_r"], [7, 1, 1, "", "mobilenet_v3_small"], [7, 1, 1, "", "mobilenet_v3_small_orientation"], [7, 1, 1, "", "mobilenet_v3_small_r"], [7, 1, 1, "", "resnet18"], [7, 1, 1, "", "resnet31"], [7, 1, 1, "", "resnet34"], [7, 1, 1, "", "resnet50"], [7, 1, 1, "", "textnet_base"], [7, 1, 1, "", "textnet_small"], [7, 1, 1, "", "textnet_tiny"], [7, 1, 1, "", "vgg16_bn_r"], [7, 1, 1, "", "vit_b"], [7, 1, 1, "", "vit_s"]], "doctr.models.detection": [[7, 1, 1, "", "db_mobilenet_v3_large"], [7, 1, 1, "", "db_resnet50"], [7, 1, 1, "", "detection_predictor"], [7, 1, 1, "", "linknet_resnet18"], [7, 1, 1, "", "linknet_resnet34"], [7, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[7, 1, 1, "", "from_hub"], [7, 1, 1, "", "login_to_hub"], [7, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[7, 1, 1, "", "crnn_mobilenet_v3_large"], [7, 1, 1, "", "crnn_mobilenet_v3_small"], [7, 1, 1, "", "crnn_vgg16_bn"], [7, 1, 1, "", "master"], [7, 1, 1, "", "parseq"], [7, 1, 1, "", "recognition_predictor"], [7, 1, 1, "", "sar_resnet31"], [7, 1, 1, "", "vitstr_base"], [7, 1, 1, "", "vitstr_small"]], "doctr.transforms": [[8, 0, 1, "", "ChannelShuffle"], [8, 0, 1, "", "ColorInversion"], [8, 0, 1, "", "Compose"], [8, 0, 1, "", "GaussianBlur"], [8, 0, 1, "", "GaussianNoise"], [8, 0, 1, "", "LambdaTransformation"], [8, 0, 1, "", "Normalize"], [8, 0, 1, "", "OneOf"], [8, 0, 1, "", "RandomApply"], [8, 0, 1, "", "RandomBrightness"], [8, 0, 1, "", "RandomContrast"], [8, 0, 1, "", "RandomCrop"], [8, 0, 1, "", "RandomGamma"], [8, 0, 1, "", "RandomHorizontalFlip"], [8, 0, 1, "", "RandomHue"], [8, 0, 1, "", "RandomJpegQuality"], [8, 0, 1, "", "RandomRotate"], [8, 0, 1, "", "RandomSaturation"], [8, 0, 1, "", "RandomShadow"], [8, 0, 1, "", "Resize"], [8, 0, 1, "", "ToGray"]], "doctr.utils.metrics": [[9, 0, 1, "", "DetectionMetric"], [9, 0, 1, "", "LocalizationConfusion"], [9, 0, 1, "", "OCRMetric"], [9, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.visualization": [[9, 1, 1, "", "synthesize_page"], [9, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [1, 6, 7, 9, 13], "0": [1, 3, 5, 8, 9, 11, 14, 16], "00": 16, "01": 16, "0123456789": 5, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 5, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 5, "02": [], "02562": 7, "03": 16, "035": 16, "0361328125": 16, "04": [], "05": 16, "06": 16, "06640625": 16, "07": 16, "08": [8, 16], "09": 16, "0966796875": 16, "1": [3, 5, 6, 7, 8, 9, 11, 14, 16], "10": [5, 9, 16], "100": [5, 8, 9, 14, 16], "1000": 16, "101": 5, "1024": [7, 9, 11, 16], "104": 5, "106": 5, "108": 5, "1095": 14, "11": 16, "110": 9, "1107": 14, "114": 5, "115": [], "1156": 14, "116": 5, "118": 5, "11800h": 16, "11th": 16, "12": [3, 16], "120": 5, "123": 5, "126": 5, "1268": 14, "128": [7, 11, 15, 16], "13": [9, 16], "130": 5, "13068": 14, "131": 5, "1337891": 14, "1357421875": 16, "1396484375": 16, "14": 16, "1420": 16, "14470v1": 5, "149": 14, "15": 16, "150": [9, 16], "1552": 16, "16": [7, 15, 16], "1630859375": 16, "1684": 16, "16x16": 7, "17": 16, "1778": 16, "1782": 16, "18": 7, "185546875": 16, "1900": 16, "1910": 7, "19342": 14, "19370": 14, "195": 5, "19598": 14, "199": 16, "1999": 16, "2": [3, 4, 5, 6, 8, 16], "20": 16, "200": 9, "2000": 14, "2003": [4, 5], "2012": 5, "2013": [4, 5], "2015": 5, "2019": 4, "2023": [], "207901": 14, "21": 16, "2103": 5, "2186": 14, "21888": 14, "22": 16, "224": [7, 8], "225": 8, "22672": 14, "229": [8, 14], "23": 16, "233": 14, "234": 5, "236": [], "24": 16, "246": 14, "249": 14, "25": 16, "2504": 16, "255": [6, 7, 8, 9, 16], "256": 7, "257": 14, "26": 16, "26032": 14, "264": 11, "27": 16, "2700": 14, "2710": 16, "2749": 11, "28": 16, "287": 11, "29": 16, "296": 11, "299": 11, "2d": 16, "3": [3, 4, 6, 7, 8, 9, 15, 16], "30": 16, "300": 14, "3000": 14, "301": 11, "30595": 16, "30ghz": 16, "31": 7, "32": [5, 7, 8, 11, 14, 15, 16], "3232421875": 16, "33": [8, 16], "33402": 14, "33608": 14, "34": [7, 16], "340": 16, "3456": 16, "35": [], "3515625": 16, "36": [], "360": 14, "37": [5, 16], "38": 16, "39": 16, "4": [7, 8, 9, 16], "40": 16, "406": 8, "41": 16, "42": 16, "43": 16, "44": 16, "45": 16, "456": 8, "46": 16, "47": 16, "472": 14, "48": [5, 16], "485": 8, "49": 16, "49377": 14, "5": [5, 8, 9, 16], "50": [7, 14, 16], "51": 16, "51171875": 16, "512": 7, "52": [5, 16], "529": 16, "53": 16, "54": 16, "540": 16, "5478515625": 16, "55": 16, "56": 16, "57": 16, "58": 16, "580": 16, "5810546875": 16, "583": 16, "59": 16, "597": 16, "5k": [4, 5], "5m": [], "6": [8, 16], "60": 8, "600": [7, 9, 16], "61": 16, "62": 16, "626": 14, "63": 16, "64": [7, 8, 16], "641": 16, "647": 14, "65": 16, "66": 16, "67": 16, "68": 16, "69": 16, "693": 11, "694": 11, "695": 11, "6m": [], "7": 16, "70": [9, 16], "707470": 14, "71": 16, "7100000": 14, "7141797": 14, "7149": 14, "72": 16, "72dpi": 6, "73": 16, "73257": 14, "74": 16, "75": [8, 16], "7581382": 14, "76": 16, "77": 16, "772": 11, "772875": 14, "78": 16, "785": 11, "79": 16, "793533": 14, "796": 14, "798": 11, "7m": [], "8": [3, 7, 8, 16], "80": 16, "800": [7, 9, 14, 16], "81": 16, "82": 16, "83": 16, "84": 16, "849": 14, "85": 16, "8564453125": 16, "857": 16, "85875": 14, "86": 16, "8603515625": 16, "87": 16, "8707": 14, "88": 16, "89": 16, "9": 16, "90": 16, "90k": 5, "90kdict32px": 5, "91": 16, "914085328578949": 16, "92": 16, "93": 16, "94": [5, 16], "95": [9, 16], "9578408598899841": 16, "96": 16, "97": [], "98": 16, "99": 16, "9949972033500671": 16, "A": [1, 2, 4, 5, 6, 7, 10, 15], "As": 2, "Be": 16, "Being": 1, "By": 12, "For": [1, 2, 3, 11, 16], "If": [2, 3, 6, 7, 11, 16], "In": [2, 5, 14], "It": [8, 13, 15], "Its": [4, 7], "No": [1, 16], "Of": 5, "Or": [], "The": [1, 2, 5, 6, 9, 12, 16], "Then": 7, "To": [2, 3, 12, 13, 16], "_": [1, 5, 7], "__call__": 16, "_build": 2, "_i": 9, "ab": 5, "abc": [], "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 5, "abdef": [5, 14], "abl": [14, 16], "about": [1, 14, 16], "abov": 16, "abstract": [], "abstractdataset": 5, "abus": 1, "accept": 1, "access": [4, 6, 14, 16], "account": [1, 13], "accur": 16, "accuraci": 9, "achiev": 15, "act": 1, "action": 1, "activ": 4, "ad": [2, 7, 8], "adapt": 1, "add": [8, 9, 13, 16], "add_hook": 16, "add_label": 9, "addit": [2, 3, 6], "addition": [2, 16], "address": [1, 6], "adjust": 8, "advanc": 1, "advantag": 15, "advis": 2, "aesthet": [4, 5], "affect": 1, "after": [13, 16], "ag": 1, "again": 7, "aggreg": [9, 14], "aggress": 1, "align": [1, 6], "all": [1, 2, 5, 6, 8, 9, 14, 16], "allow": 1, "along": 16, "alreadi": 2, "also": [1, 7, 13, 14, 16], "alwai": 14, "an": [1, 2, 4, 5, 6, 7, 9, 15, 16], "analysi": 6, "ancient_greek": 5, "andrej": [], "angl": [6, 8], "ani": [1, 5, 6, 7, 8, 9, 16], "annot": 5, "anot": 14, "anoth": [3, 7, 11, 14], "answer": 1, "anyascii": [], "anyon": 4, "anyth": [], "api": [2, 4], "apolog": 1, "apologi": 1, "app": 2, "appear": 1, "appli": [1, 5, 8], "applic": [4, 7], "appoint": 1, "appreci": 13, "appropri": [1, 2, 16], "ar": [1, 2, 3, 5, 6, 8, 9, 10, 14, 16], "arab": 5, "arabic_diacrit": 5, "arabic_lett": 5, "arabic_punctu": 5, "arbitrarili": 7, "arch": [7, 13], "architectur": [4, 7, 13], "area": 16, "arg": [], "argument": [5, 6, 7, 9, 16], "around": 1, "arrai": [6, 8, 9], "art": 4, "artefact": [9, 10, 16], "artefact_typ": 6, "artefactdetector": [], "articl": [], "artifici": [4, 5], "arxiv": [5, 7], "asarrai": 9, "ascii_lett": 5, "aspect": [4, 7, 8, 16], "assess": 9, "assign": 9, "associ": 6, "assum": 7, "assume_straight_pag": [7, 16], "astyp": [7, 9, 16], "attack": 1, "attend": [4, 7], "attent": [1, 7], "autom": 4, "automat": 16, "autoregress": [4, 7], "avail": [1, 4, 8], "averag": [8, 16], "avoid": [1, 3], "aw": [4, 16], "awar": 16, "azur": 16, "b": [7, 9, 16], "b_j": 9, "back": 2, "backbon": 7, "backend": 16, "background": 14, "bangla": [], "bar": [], "bar_cod": 14, "baranovskij": [], "base": [4, 7], "baselin": [4, 7, 16], "batch": [5, 7, 8, 14, 16], "batch_siz": [5, 11, 14, 15], "bblanchon": [], "bbox": 16, "becaus": 12, "been": [2, 9, 14, 16], "befor": [5, 7, 8, 16], "begin": 9, "behavior": [1, 16], "being": [9, 16], "belong": 16, "benchmark": 16, "best": 1, "better": [10, 16], "between": [8, 9, 16], "bgr": 6, "bilinear": 8, "bin_thresh": 16, "binar": [4, 7, 16], "binari": [6, 15, 16], "bit": 15, "blank": 9, "block": [9, 16], "block_1_1": 16, "blue": 9, "blur": 8, "bmvc": 5, "bn": 13, "bodi": [1, 16], "bool": [5, 6, 7, 8, 9], "boolean": [7, 16], "both": [4, 5, 8, 14, 16], "bottom": [7, 16], "bound": [5, 6, 7, 8, 9, 16], "box": [5, 6, 7, 8, 9, 14, 16], "box_thresh": 16, "brew": 3, "bright": 8, "broadcast": 9, "browser": [2, 4], "build": [2, 3], "built": 2, "byte": [6, 16], "c": [6, 9], "c_j": 9, "cach": [2, 5, 12], "cache_sampl": 5, "cairo": 3, "call": [], "callabl": [5, 8], "can": [2, 3, 11, 12, 13, 14, 16], "capabl": [2, 10, 16], "case": [5, 9], "cf": 16, "cfg": 16, "challeng": 5, "challenge2_test_task12_imag": 5, "challenge2_test_task1_gt": 5, "challenge2_training_task12_imag": 5, "challenge2_training_task1_gt": 5, "chang": 12, "channel": [1, 2, 6, 8], "channel_prior": [], "channelshuffl": 8, "charact": [4, 5, 6, 9, 14, 16], "charactergener": [5, 14], "characterist": 1, "charg": 16, "charset": 16, "chart": 6, "check": [2, 13, 16], "checkpoint": 7, "chip": 3, "christian": [], "ci": 2, "clarifi": 1, "clariti": 1, "class": [1, 5, 6, 8, 9, 16], "class_nam": 11, "classif": 14, "classif_mobilenet_v3_smal": 7, "classmethod": 6, "clear": 2, "clone": 3, "close": 2, "co": 13, "code": [4, 6], "codecov": 2, "colab": 10, "collate_fn": 5, "collect": 6, "color": [8, 9], "colorinvers": 8, "column": 6, "com": [1, 3, 6, 7, 13], "combin": 16, "come": 15, "command": 2, "comment": 1, "commit": 1, "common": [1, 8, 9, 15], "commun": 1, "compar": 4, "comparison": [9, 16], "competit": 5, "compil": [10, 16], "complaint": 1, "complementari": 9, "complet": 2, "compon": 16, "compos": [5, 16], "comprehens": 16, "comput": [5, 9, 15, 16], "conf_threshold": [], "confid": [6, 9, 16], "config": 7, "configur": 7, "confus": 9, "consecut": [8, 16], "consequ": 1, "consid": [1, 2, 5, 6, 9, 16], "consist": 16, "consolid": [4, 5], "constant": 8, "construct": 1, "consum": 9, "contact": 1, "contain": [5, 14], "content": [5, 6, 9, 16], "context": 7, "contib": [], "continu": 1, "contrast": 8, "contrast_factor": 8, "contrib": [], "contribut": 1, "contributor": 2, "convers": 6, "convert": [6, 8], "convert_target_to_rel": [], "convolut": 7, "cool": [], "coordin": [6, 16], "cord": [4, 5, 14, 16], "core": [9, 16], "corner": 16, "correct": 8, "correspond": [3, 6, 16], "could": 1, "counterpart": 9, "cover": 2, "coverag": 2, "cpu": [4, 11], "creat": 13, "crnn": [4, 7, 13], "crnn_mobilenet_v3_larg": [7, 13, 16], "crnn_mobilenet_v3_smal": [7, 15, 16], "crnn_vgg16_bn": [7, 11, 13, 16], "crop": [7, 8, 14, 16], "crop_bboxes_from_imag": [], "crop_orient": [], "crop_orientation_predictor": 7, "crop_param": [], "croporientationpredictor": 7, "cuda": 15, "currenc": 5, "current": [2, 16], "custom": [13, 16], "custom_crop_orientation_model": [], "custom_page_orientation_model": [], "customhook": 16, "cvit": 4, "czczup": 7, "czech": 5, "d": [5, 14], "danish": 5, "data": [4, 5, 6, 8, 9, 11, 13], "dataload": 14, "dataset": [7, 11, 16], "dataset_info": 5, "date": [11, 16], "db": 13, "db_mobilenet_v3_larg": [7, 13, 16], "db_resnet34": 16, "db_resnet50": [7, 11, 13, 16], "db_resnet50_rot": [], "dbnet": [4, 7], "deal": [], "decis": 1, "decod": 6, "decode_img_as_tensor": 6, "decode_sequ": [], "dedic": [], "deem": 1, "deep": [7, 16], "def": 16, "default": [6, 9, 11, 12, 16], "defer": 14, "defin": [9, 15], "degre": 8, "degress": 6, "delet": 2, "delimit": 16, "delta": 8, "demo": [2, 4], "demonstr": 1, "depend": [2, 3, 4], "deploi": 2, "deploy": 4, "derogatori": 1, "describ": [7, 9], "descript": 10, "design": 8, "desir": 6, "det_arch": [7, 11, 13, 15], "det_b": [], "det_model": [11, 13], "det_param": 11, "det_predictor": [11, 16], "detail": [11, 16], "detect": [5, 9, 10, 11], "detect_languag": 7, "detect_orient": 7, "detection_predictor": [7, 16], "detection_task": [], "detectiondataset": [5, 14], "detectionmetr": 9, "detectionpredictor": [7, 11], "detector": 7, "deterior": 7, "determin": 1, "dev": [2, 12], "develop": 3, "deviat": 8, "devic": 15, "dict": [6, 9, 16], "dictionari": [6, 9], "differ": 1, "differenti": [4, 7], "digit": [4, 5, 14], "dimens": [6, 9, 16], "dimension": 8, "direct": 5, "directli": [13, 16], "directori": [2, 12], "disabl": [1, 12, 16], "disable_crop_orient": [], "disable_page_orient": [], "disclaim": 16, "discuss": 2, "disparag": 1, "displai": [6, 9], "display_artefact": 9, "distribut": 8, "div": 16, "divers": 1, "divid": 6, "do": [2, 3, 7], "doc": [2, 6, 15, 16], "docartefact": [5, 14], "docstr": 2, "doctr": [3, 11, 12, 13, 14, 16], "doctr_cache_dir": 12, "doctr_multiprocessing_dis": 12, "document": [5, 7, 9, 10, 14, 16], "documentbuild": 16, "documentfil": [6, 13], "doesn": [], "don": [11, 16], "done": 8, "download": [5, 14], "download_from_url": [], "downsiz": 7, "draw": [8, 9], "draw_proba": 9, "drop": 5, "drop_last": 5, "dtype": [6, 7, 8, 9, 15], "dual": [4, 5], "dummi": 13, "dummy_img": 16, "dummy_input": 15, "dure": 1, "dutch": 5, "dynam": 5, "dynamic_seq_length": 5, "e": [1, 2, 3, 6, 7], "each": [4, 5, 6, 7, 8, 9, 14, 16], "eas": 2, "easi": [4, 9, 13], "easili": [6, 9, 11, 13, 14, 16], "econom": 1, "edit": 1, "educ": 1, "effect": [], "effici": [2, 4, 5, 7], "either": [9, 16], "element": [5, 6, 7, 9, 16], "els": 2, "email": 1, "empathi": 1, "en": 16, "enabl": [5, 6], "enclos": 6, "encod": [4, 5, 6, 7, 16], "encode_sequ": 5, "encode_str": [], "encount": 2, "encrypt": 6, "end": [4, 5, 7, 9], "english": [5, 14], "enough": [2, 16], "ensur": 2, "entri": 5, "environ": [1, 12], "eo": 5, "equiv": 16, "estim": 7, "etc": 6, "ethnic": 1, "evalu": [14, 16], "event": 1, "everyon": 1, "everyth": [2, 16], "exact": [9, 16], "exampl": [1, 2, 4, 5, 7, 13, 16], "exchang": 15, "execut": 16, "exist": 13, "expand": 8, "expect": [6, 8, 9], "experi": 1, "explan": [1, 16], "explicit": 1, "exploit": [4, 7], "export": [6, 7, 9, 10, 16], "export_as_straight_box": [7, 16], "export_as_xml": 16, "export_model_to_onnx": 15, "express": [1, 8], "extens": 6, "extern": [1, 14], "extra": 3, "extract": [4, 5], "extractor": 7, "f_": 9, "f_a": 9, "factor": 8, "fair": 1, "fairli": 1, "fals": [5, 6, 7, 8, 9, 11, 16], "famili": 9, "faq": 1, "fascan": 13, "fast": [4, 5, 7], "fast_bas": [], "fast_smal": [], "fast_tini": [], "faster": [7, 15], "fasterrcnn_mobilenet_v3_large_fpn": 7, "favorit": 16, "featur": [3, 7, 9, 10], "feedback": 1, "feel": [2, 13], "felix92": 13, "few": [3, 15, 16], "figsiz": 9, "figur": 9, "file": [2, 5], "final": 7, "find": [2, 3, 14], "fine": [], "finnish": 5, "first": [2, 5], "firsthand": 5, "fit": [7, 16], "flag": 16, "flip": 8, "float": [6, 8, 9, 15], "float32": [6, 7, 8, 15], "fn": 8, "focu": 13, "focus": [1, 5], "folder": 5, "follow": [1, 2, 3, 5, 8, 9, 11, 12, 13, 16], "font": [5, 9], "font_famili": [5, 9], "font_siz": 9, "foral": 9, "forc": 2, "forg": [], "form": [4, 5, 16], "format": [6, 9, 11, 14, 15, 16], "forpost": [4, 5], "forum": 2, "found": [], "fp16": 15, "frac": 9, "framework": [3, 13, 14, 16], "free": [1, 2, 13], "french": [5, 11, 13, 16], "friendli": 4, "from": [1, 4, 5, 6, 7, 8, 9, 10, 11, 14, 15, 16], "from_hub": [7, 13], "from_imag": [6, 13], "from_pdf": 6, "from_url": 6, "full": [5, 9, 16], "function": [5, 8, 9], "funsd": [4, 5, 14, 16], "further": 14, "futur": 5, "g": [6, 7], "g_": 9, "g_x": 9, "gallagh": [], "gamma": 8, "gaussian": 8, "gaussianblur": 8, "gaussiannois": 8, "gdk": 3, "gen": 16, "gender": 1, "gener": [2, 4, 7], "generic_cyrillic_lett": [], "geom": [], "geometri": [4, 6, 16], "geq": 9, "german": [5, 11, 13], "get": 16, "git": 13, "github": [2, 3, 7, 13], "give": 1, "given": [5, 6, 8, 9, 16], "global": 7, "go": 16, "good": 15, "googl": 2, "googlevis": 4, "gpu": [4, 15], "gracefulli": 1, "graph": [4, 5, 6], "grayscal": 8, "ground": 9, "groung": 9, "group": [4, 16], "gt": 9, "gt_box": 9, "gt_label": 9, "gtk": 3, "guid": 2, "guidanc": 14, "gvision": 16, "h": [6, 7, 8], "h_": 9, "ha": [2, 5, 9, 14], "handl": [14, 16], "handwrit": 5, "handwritten": 14, "harass": 1, "hardwar": [], "harm": 1, "hat": 9, "have": [1, 2, 9, 11, 13, 14, 16], "head": [7, 16], "healthi": 1, "hebrew": 5, "height": 6, "hello": [9, 16], "help": 15, "here": [3, 8, 10, 14, 16], "hf": 7, "hf_hub_download": 7, "high": 6, "higher": [3, 5, 16], "hindi": [], "hindi_digit": 5, "hocr": 16, "homebrew": 3, "hook": 16, "horizont": [6, 8], "hous": 5, "how": [2, 11, 13, 14], "howev": 14, "hsv": 8, "html": [1, 2, 6, 16], "http": [1, 3, 5, 6, 7, 13, 16], "hub": 7, "hue": 8, "huggingfac": 7, "hw": 5, "i": [1, 2, 5, 6, 7, 8, 9, 12, 13, 14, 15], "i7": 16, "ibrahimov": [], "ic03": [4, 5, 14], "ic13": [4, 5, 14], "icdar": [4, 5], "icdar2019": 5, "id": 16, "ident": 1, "identifi": 4, "iiit": [4, 5], "iiit5k": [5, 14], "iiithw": [4, 5, 14], "imag": [4, 5, 6, 7, 8, 9, 13, 14, 16], "imagenet": 7, "imageri": 1, "images_90k_norm": 5, "imagetensor": [], "imagetransform": [], "img": [5, 8, 14], "img_cont": 6, "img_fold": [5, 14], "img_path": 6, "img_transform": 5, "imgur5k": [4, 5, 14], "imgur5k_annot": 5, "imlist": 5, "impact": 1, "implement": [5, 6, 7, 8, 9, 16], "import": [5, 6, 7, 8, 9, 11, 13, 14, 15, 16], "improv": 7, "inappropri": 1, "incid": 1, "includ": [1, 3, 5, 14, 15], "inclus": 1, "increas": 8, "independ": [], "index": [2, 6], "indic": 9, "individu": 1, "infer": [4, 7, 8], "inform": [1, 2, 4, 5, 14], "input": [2, 6, 7, 8, 15, 16], "input_crop": 7, "input_pag": [7, 9, 16], "input_seq": [], "input_shap": 15, "input_str": [], "input_tensor": 7, "inspir": [1, 8], "instal": 13, "instanc": [1, 16], "instanti": [7, 16], "instead": [5, 6, 7], "insult": 1, "int": [5, 6, 8, 9], "int64": [8, 9], "integ": 9, "integr": [4, 13, 14], "intel": 16, "interact": [1, 6, 9], "interfac": 13, "interoper": 15, "interpol": 8, "interpret": [5, 6], "intersect": 9, "invert": 8, "investig": 1, "invis": 1, "involv": [1, 16], "io": 13, "iou": 9, "iou_thresh": 9, "iou_threshold": [], "irregular": [4, 7, 14], "isn": 5, "issu": [1, 2, 13], "italian": 5, "iter": [5, 8, 14, 16], "its": [6, 7, 8, 9, 14, 16], "itself": [7, 13], "j": 9, "jame": [], "job": 2, "join": 2, "jpeg": 8, "jpegqual": 8, "jpg": [5, 6, 13], "json": [5, 14, 16], "json_output": 16, "jump": 2, "just": 1, "kei": [4, 5], "kera": [7, 15], "kernel": [7, 8], "kernel_shap": 8, "keywoard": 7, "keyword": [5, 6, 7, 9], "kie": [7, 11], "kie_predictor": [7, 11], "kiepredictor": 7, "kind": 1, "know": 2, "kwarg": [5, 6, 7, 9], "l": 9, "l_j": 9, "label": [5, 8, 9, 14], "label_fil": [5, 14], "label_fold": 5, "label_path": [5, 14], "labels_path": [5, 14], "ladder": 1, "lambda": 8, "lambdatransform": 8, "lang": 16, "languag": [1, 4, 5, 6, 7, 13, 16], "larg": [7, 13], "largest": 9, "last": [3, 5], "latenc": 7, "later": 2, "latest": [3, 16], "latin": 5, "layer": 15, "layout": 16, "lead": 1, "leader": 1, "learn": [1, 4, 7, 15, 16], "least": 3, "left": [9, 16], "legacy_french": 5, "length": [5, 16], "less": [15, 16], "level": [1, 5, 9, 16], "leverag": 10, "lf": 13, "libffi": 3, "librari": [2, 3, 10, 11], "light": 4, "lightweight": [], "like": 1, "limits_": 9, "line": [4, 7, 9, 16], "line_1_1": 16, "link": 11, "linknet": [4, 7], "linknet_resnet18": [7, 11, 16], "linknet_resnet18_rot": [], "linknet_resnet34": [7, 15, 16], "linknet_resnet50": [7, 16], "linux": 3, "list": [5, 6, 8, 9, 13], "ll": 9, "load": [4, 5, 7], "load_state_dict": 11, "load_weight": 11, "loc_pr": 16, "local": [2, 4, 5, 7, 9, 14, 16], "localis": 5, "localizationconfus": 9, "locat": [2, 6, 16], "login": 7, "login_to_hub": [7, 13], "logo": [6, 14], "love": 13, "lower": [8, 9, 16], "m": [2, 9, 16], "m1": 3, "macbook": 3, "machin": 15, "maco": 3, "made": 4, "magc_resnet31": 7, "mai": [1, 2], "mail": 1, "main": 10, "maintain": 4, "mainten": 2, "make": [1, 2, 9, 12, 13, 15, 16], "mani": [14, 16], "manipul": 16, "map": [5, 7], "map_loc": 11, "mask": [], "mask_label": [], "mask_shap": 9, "master": [4, 7, 16], "match": [9, 16], "mathcal": 9, "matplotlib": [6, 9], "max": [5, 8, 9], "max_angl": 8, "max_area": 8, "max_char": [5, 14], "max_delta": 8, "max_font_s": [], "max_gain": 8, "max_gamma": 8, "max_qual": 8, "max_ratio": 8, "maximum": [5, 8], "maxval": [7, 8], "mbox": 9, "mean": [8, 9, 11], "meaniou": 9, "meant": [6, 15], "measur": 16, "media": 1, "median": 7, "meet": 11, "member": 1, "memori": [9, 12, 15], "mention": 16, "merg": 5, "messag": 2, "meta": 16, "metadata": 15, "metal": 3, "method": [6, 8, 16], "metric": [9, 16], "middl": 16, "might": [15, 16], "min": 8, "min_area": 8, "min_char": [5, 14], "min_font_s": [], "min_gain": 8, "min_gamma": 8, "min_qual": 8, "min_ratio": 8, "min_val": 8, "minde": [1, 3, 4, 7], "minim": [2, 4], "minimalist": 7, "minimum": [3, 5, 8, 9, 16], "minval": 8, "miss": 3, "mistak": 1, "mixed_float16": 15, "mixed_precis": 15, "mjsynth": [4, 5, 14], "mnt": 5, "mobilenet": [7, 13], "mobilenet_v3_larg": 7, "mobilenet_v3_large_r": 7, "mobilenet_v3_smal": 7, "mobilenet_v3_small_crop_orient": [], "mobilenet_v3_small_orient": 7, "mobilenet_v3_small_page_orient": [], "mobilenet_v3_small_r": 7, "mobilenetv3": 7, "modal": [4, 5], "mode": 3, "model": [5, 9, 12, 14], "model_nam": [7, 13, 15], "model_path": 15, "moder": 1, "modif": 2, "modifi": [7, 12, 16], "modul": [6, 7, 8, 9, 16], "moment": [], "more": [2, 9, 14, 16], "moscardi": [], "most": 16, "mozilla": 1, "multi": [4, 7], "multiclass": [], "multilingu": [5, 13], "multipl": [5, 6, 8, 16], "multipli": 8, "multiprocess": 12, "my": 7, "my_awesome_model": 13, "my_hook": 16, "n": [5, 9], "name": [5, 7, 15, 16], "nation": 1, "natur": [1, 4, 5], "nb": [], "ndarrai": [5, 6, 8, 9], "necessari": [3, 11, 12], "need": [2, 3, 5, 9, 11, 12, 13, 16], "neg": 8, "nest": 16, "netraj": [], "network": [4, 5, 7, 15], "neural": [4, 5, 7, 15], "new": [2, 9], "next": [5, 14], "nois": 8, "noisi": [4, 5], "non": [4, 5, 6, 7, 8, 9], "none": [5, 6, 7, 8, 9, 16], "normal": [7, 8], "norwegian": 5, "note": [0, 2, 5, 7, 13, 15], "now": 2, "np": [7, 8, 9, 16], "num_output_channel": 8, "num_sampl": [5, 14], "num_work": 5, "number": [5, 8, 9, 16], "numpi": [6, 7, 9, 16], "o": 3, "obb": [], "obj_detect": 13, "object": [5, 9, 10, 16], "objectness_scor": [], "oblig": 1, "obtain": 16, "occupi": 15, "ocr": [4, 5, 7, 9, 13, 14], "ocr_carea": 16, "ocr_db_crnn": 9, "ocr_lin": 16, "ocr_pag": 16, "ocr_par": 16, "ocr_predictor": [7, 11, 13, 15, 16], "ocrdataset": [5, 14], "ocrmetr": 9, "ocrpredictor": [7, 11], "ocrx_word": 16, "offens": 1, "offici": [1, 7], "offlin": 1, "offset": 8, "onc": 16, "one": [2, 5, 7, 8, 11, 13, 16], "oneof": 8, "ones": [5, 8, 9], "onli": [2, 7, 8, 9, 13, 14, 15, 16], "onlin": 1, "onnx": [], "onnxruntim": [], "onnxtr": [], "opac": 8, "opacity_rang": 8, "open": [1, 2, 13, 15], "opinion": 1, "optic": [4, 16], "optim": 4, "option": [5, 7, 11], "order": [2, 5, 6, 8], "org": [1, 5, 7, 16], "organ": 6, "orient": [1, 6, 7, 16], "orientationpredictor": [], "other": [1, 2], "otherwis": [1, 6, 9], "our": [2, 7, 16], "out": [2, 7, 8, 9, 16], "out_box": [], "outpout": 16, "output": [6, 8, 15], "output_s": [6, 8], "outsid": 12, "over": [3, 5, 9, 16], "overal": [1, 7], "overlai": 6, "overview": [], "overwrit": [], "overwritten": 13, "own": 4, "p": [8, 9, 16], "packag": [2, 4, 9, 12, 14], "pad": [5, 7, 8, 16], "page": [3, 5, 7, 9, 16], "page1": 6, "page2": 6, "page_1": 16, "page_idx": [6, 16], "page_orientation_predictor": [], "page_param": [], "pair": 9, "pango": 3, "paper": 7, "par_1_1": 16, "paragraph": 16, "paragraph_break": 16, "parallel": [], "param": [8, 16], "paramet": [4, 6, 7, 15], "pars": [4, 5], "parseq": [4, 7, 13, 16], "part": [5, 8, 16], "parti": 3, "partial": 16, "particip": 1, "pass": [5, 6, 7, 16], "password": 6, "patch": [7, 9], "path": [5, 6, 14], "path_to_checkpoint": 11, "path_to_custom_model": [], "path_to_pt": 11, "patil": [], "pattern": 1, "pdf": [6, 7, 10], "pdfpage": 6, "peopl": 1, "per": [8, 16], "perform": [4, 6, 7, 8, 9, 12, 15, 16], "period": 1, "permiss": 1, "permut": [4, 7], "persian_lett": 5, "person": [1, 14], "phase": 16, "photo": 14, "physic": [1, 6], "pick": 8, "pictur": 6, "pip": [2, 3], "pipelin": 16, "pixbuf": 3, "pixel": [6, 8, 16], "pleas": 2, "plot": 9, "plt": 9, "plug": 13, "plugin": 3, "png": 6, "point": 15, "polici": 12, "polish": 5, "polit": 1, "polygon": [5, 9, 16], "pool": 7, "portugues": 5, "posit": [1, 9], "possibl": [2, 9, 13, 16], "post": [1, 16], "postprocessor": 16, "potenti": 7, "power": 4, "ppageno": 16, "pre": [2, 7], "pre_transform_multiclass": [], "precis": [9, 16], "pred": 9, "pred_box": 9, "pred_label": 9, "predefin": 14, "predict": [6, 7, 9, 16], "predictor": [4, 6, 7, 11, 13, 15], "prefer": 14, "preinstal": [], "preprocessor": [11, 16], "prerequisit": 13, "present": 10, "preserv": [7, 8, 16], "preserve_aspect_ratio": [6, 7, 8, 11, 16], "pretrain": [4, 7, 9, 11, 15, 16], "pretrained_backbon": [7, 11], "print": 16, "prior": 5, "privaci": 1, "privat": 1, "probabl": 8, "problem": 2, "procedur": 8, "process": [2, 4, 6, 11, 16], "processor": 16, "produc": [10, 16], "product": 15, "profession": 1, "project": [2, 14], "promptli": 1, "proper": 2, "properli": 5, "provid": [1, 2, 4, 13, 14, 16], "public": [1, 4], "publicli": 16, "publish": 1, "pull": 13, "punctuat": 5, "pure": 5, "purpos": 2, "push_to_hf_hub": [7, 13], "py": 13, "pypdfium2": 6, "pyplot": [6, 9], "python": 2, "python3": 13, "pytorch": [3, 4, 7, 8, 11, 13, 15, 16], "q": 2, "qr": 6, "qr_code": 14, "qualiti": 8, "question": 1, "quickli": 4, "quicktour": 10, "r": 16, "race": 1, "ramdisk": 5, "rand": [7, 8, 9, 15, 16], "random": [7, 8, 9, 16], "randomappli": 8, "randombright": 8, "randomcontrast": 8, "randomcrop": 8, "randomgamma": 8, "randomhorizontalflip": 8, "randomhu": 8, "randomjpegqu": 8, "randomli": 8, "randomres": [], "randomrot": 8, "randomsatur": 8, "randomshadow": 8, "rang": 8, "rassi": 13, "ratio": [7, 8, 16], "raw": [6, 9], "re": 15, "read": [4, 5, 7], "read_html": 6, "read_img": [], "read_img_as_numpi": 6, "read_img_as_tensor": 6, "read_pdf": 6, "readi": 15, "real": [4, 7, 8], "realli": [], "reason": [1, 4, 5], "rebuild": 2, "rebuilt": 2, "recal": [9, 16], "receipt": [4, 5, 16], "reco_arch": [7, 11, 13, 15], "reco_b": [], "reco_model": [11, 13], "reco_param": 11, "reco_predictor": 11, "recogn": 16, "recognit": [5, 9, 11], "recognition_predictor": [7, 16], "recognition_task": [5, 14], "recognitiondataset": [5, 14], "recognitionpredictor": [7, 11], "rectangular": 7, "red": 9, "reduc": [3, 8], "refer": [2, 3, 11, 13, 14, 16], "regardless": 1, "region": 16, "regroup": 9, "regular": 14, "reject": 1, "rel": [6, 8, 9, 16], "relat": 6, "releas": [0, 3], "relev": [], "religion": 1, "remov": 1, "render": [6, 16], "repo": 7, "repo_id": [7, 13], "report": 1, "repositori": [5, 7, 13], "repres": [1, 9, 15, 16], "represent": [4, 7], "request": [1, 13], "requir": [3, 8], "research": 4, "residu": 7, "resiz": [8, 16], "resnet": 7, "resnet18": [7, 13], "resnet31": 7, "resnet34": 7, "resnet50": [7, 13], "resolv": 6, "resolve_block": 16, "resolve_lin": 16, "resourc": 14, "respect": 1, "respons": 9, "rest": [2, 8, 9], "restrict": 12, "result": [2, 5, 6, 10, 13, 16], "return": 16, "reusabl": 16, "review": 1, "rgb": [6, 8], "rgb_mode": 6, "rgb_output": 6, "right": [1, 7, 9], "roboflow": [], "robust": [4, 5], "root": 5, "rotat": [5, 6, 7, 8, 9, 14, 16], "run": [2, 3, 7], "same": [2, 6, 9, 14, 16], "sampl": [5, 14, 16], "sample_transform": 5, "samplecompos": [], "sanjin": [], "sar": [4, 7], "sar_resnet31": [7, 16], "satur": 8, "save": [7, 14], "scale": [6, 7, 8, 9], "scale_rang": [], "scan": [4, 5], "scene": [4, 5, 7], "score": 9, "script": [2, 14], "seamless": 4, "seamlessli": [4, 16], "search": 7, "searchabl": 10, "sec": 16, "second": 16, "section": [11, 13, 15, 16], "secur": [1, 12], "see": [1, 2], "seen": 16, "segment": [4, 7, 16], "self": 16, "semant": [4, 7], "send": 16, "sens": 9, "sensit": 14, "separ": 16, "sequenc": [4, 5, 6, 7, 9, 16], "sequenti": [8, 16], "seri": 1, "seriou": 1, "set": [1, 5, 7, 9, 12, 16], "set_global_polici": 15, "sever": [6, 8, 16], "sex": 1, "sexual": 1, "shade": 8, "shape": [6, 7, 8, 9, 16], "share": [12, 14], "shift": 8, "shm": 12, "should": [2, 5, 6, 8, 9], "show": [4, 6, 7, 9, 11, 13], "showcas": 2, "shuffl": [5, 8], "side": 9, "signatur": 6, "signific": 14, "simpl": [4, 7], "simpler": 7, "sinc": [5, 14], "singl": [1, 2, 4, 5], "single_img_doc": [], "size": [1, 5, 6, 8, 9, 16], "skew": 16, "slack": 2, "slightli": 7, "small": [2, 7], "smallest": 6, "smooth": [], "smoothing_factor": [], "snapshot_download": 7, "snippet": 16, "so": [2, 3, 5, 7, 13, 14], "social": 1, "socio": 1, "some": [3, 10, 13, 14], "someth": 2, "somewher": 2, "soon": 15, "sort": 1, "sourc": [5, 6, 7, 8, 9, 13], "space": [1, 16], "span": 16, "spanish": 5, "spatial": [4, 5, 6, 9], "specif": [2, 3, 9, 11, 14, 16], "specifi": [1, 5, 6], "speed": [4, 7], "sphinx": 2, "sroie": [4, 5, 14], "stabl": 3, "stackoverflow": 2, "stage": 4, "standalon": [], "standard": 8, "start": 5, "state": [4, 9], "static": 9, "statist": [], "statu": 1, "std": [8, 11], "step": 12, "still": 16, "str": [5, 6, 7, 8, 9], "straight": [5, 7, 14, 16], "straighten": [], "straighten_pag": 7, "straigten_pag": [], "stream": 6, "street": [4, 5], "strict": [], "strictli": 9, "string": [5, 6, 9, 16], "strive": 3, "strong": [4, 7], "structur": [15, 16], "subset": [5, 16], "suggest": [2, 13], "sum": 9, "summari": 9, "support": [15, 16], "sustain": 1, "svhn": [4, 5, 14], "svt": [5, 14], "swedish": 5, "symmetr": [7, 8, 16], "symmetric_pad": [7, 8, 16], "synthes": 9, "synthesize_pag": 9, "synthet": 4, "synthtext": [4, 5, 14], "system": 16, "t": [2, 5, 11, 16], "tabl": 13, "take": [1, 5, 16], "target": [5, 6, 8, 9, 14], "target_s": 5, "task": [4, 5, 7, 13, 14, 16], "task2": 5, "team": [], "techminde": [], "templat": [2, 4], "tensor": [5, 6, 8, 16], "tensorflow": [3, 4, 6, 7, 8, 11, 13, 15, 16], "tensorspec": 15, "term": 1, "test": [5, 14], "test_set": 5, "text": [5, 6, 7, 9, 14], "text_output": 16, "textmatch": 9, "textnet": 7, "textnet_bas": 7, "textnet_smal": 7, "textnet_tini": 7, "textract": [4, 16], "textstylebrush": [4, 5], "textual": [4, 5, 6, 7, 16], "tf": [3, 6, 7, 8, 13, 15], "than": [2, 3, 9, 13], "thank": 2, "thei": [1, 9], "them": [3, 5, 16], "thi": [1, 2, 3, 5, 9, 11, 12, 13, 14, 15, 16], "thing": [15, 16], "third": 3, "those": [1, 3, 6, 16], "threaten": 1, "threshold": 16, "through": [1, 8, 14], "tilman": 13, "time": [1, 4, 7, 9, 14], "tini": 7, "titl": [6, 16], "tm": 16, "tmp": 12, "togeth": [2, 6], "tograi": 8, "tool": 14, "top": [9, 16], "topic": 2, "torch": [3, 8, 11, 13, 15], "torchvis": 8, "total": 11, "toward": [1, 3], "train": [2, 5, 7, 8, 13, 14, 15, 16], "train_it": [5, 14], "train_load": [5, 14], "train_pytorch": 13, "train_set": [5, 14], "train_tensorflow": 13, "trainabl": [4, 7], "tranform": 8, "transcrib": 16, "transfer": [4, 5], "transfo": 8, "transform": [4, 5, 7], "translat": 1, "troll": 1, "true": [5, 6, 7, 8, 9, 11, 12, 13, 14, 15, 16], "truth": 9, "tune": 15, "tupl": [5, 6, 8, 9], "turn": [], "two": [6, 12], "txt": 5, "type": [6, 9, 13, 15, 16], "typic": 16, "u": [1, 2], "ucsd": 5, "udac": 2, "uint8": [6, 7, 9, 16], "ukrainian": [], "unaccept": 1, "underli": [14, 16], "underneath": 6, "understand": [4, 5, 16], "unidecod": 9, "uniform": [7, 8], "uniformli": 8, "uninterrupt": [6, 16], "union": 9, "unit": [], "unittest": 2, "unknown": [], "unknown_char": [], "unlock": 6, "unoffici": 7, "unprofession": 1, "unsolicit": 1, "unsupervis": 4, "unwelcom": 1, "up": [7, 16], "updat": 9, "upgrad": 2, "upper": [5, 8], "uppercas": 14, "url": 6, "us": [1, 2, 3, 5, 7, 9, 11, 12, 13, 16], "usabl": 16, "usag": [12, 15], "use_broadcast": 9, "use_polygon": [5, 9, 14], "useabl": 16, "user": [3, 4, 6, 10], "utf": 16, "util": 15, "v1": 13, "v3": [7, 13, 16], "valid": 14, "valu": [2, 6, 8, 16], "valuabl": 4, "variabl": 12, "varieti": 5, "veri": 7, "verma": [], "version": [1, 2, 3, 15, 16], "vgg": 7, "vgg16": 13, "vgg16_bn_r": 7, "via": 1, "video": [], "vietnames": 5, "view": [4, 5], "viewpoint": 1, "violat": 1, "visibl": 1, "vision": [4, 5, 7], "visiondataset": 5, "visiontransform": 7, "visual": 4, "visualize_pag": 9, "vit_": 7, "vit_b": 7, "vitstr": [4, 7, 15], "vitstr_bas": [7, 16], "vitstr_smal": [7, 11, 15, 16], "viz": [], "vocab": [11, 13, 14, 16], "vocab_nam": [], "vocabulari": [5, 11, 13], "w": [6, 7, 8, 9], "w3": 16, "wa": 1, "wai": [1, 4, 14], "want": [2, 15, 16], "warmup": 16, "wasn": 2, "we": [1, 2, 3, 4, 6, 8, 13, 14, 15, 16], "weasyprint": 6, "web": [2, 6], "websit": 5, "weight": 11, "welcom": 1, "well": [1, 15], "were": [1, 6, 16], "what": 1, "when": [1, 2, 7], "whenev": 2, "where": [2, 6, 8, 9], "whether": [2, 5, 6, 8, 9, 14, 16], "which": [1, 7, 12, 14, 16], "whichev": 3, "while": [8, 16], "why": 1, "width": 6, "wiki": 1, "wildreceipt": [4, 5, 14], "window": [3, 7, 9], "wish": 2, "within": 1, "without": [1, 5, 7], "wonder": 2, "word": [4, 5, 7, 9, 16], "word_1_1": 16, "word_1_2": 16, "word_1_3": 16, "wordgener": [5, 14], "words_onli": 9, "work": [12, 16], "worker": 5, "workflow": 2, "worklow": 2, "world": [9, 16], "worth": 7, "wrap": 16, "wrapper": [5, 8], "write": 12, "written": [1, 6], "www": [1, 6, 16], "x": [6, 8, 9], "x_ascend": 16, "x_descend": 16, "x_i": 9, "x_size": 16, "x_wconf": 16, "xhtml": 16, "xmax": 6, "xmin": 6, "xml": 16, "xml_bytes_str": 16, "xml_element": 16, "xml_output": 16, "xmln": 16, "y": 9, "y_i": 9, "y_j": 9, "yet": [], "ymax": 6, "ymin": 6, "yolov8": [], "yolov8_artefact": [], "you": [2, 3, 5, 6, 7, 11, 12, 13, 14, 15, 16], "your": [2, 4, 6, 9, 16], "yoursit": 6, "yugesh": [], "zero": [8, 9], "zoo": [], "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 5, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 5, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 5, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 5, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 5, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": [], "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 5, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 5, "\u00e4\u00f6\u00e4\u00f6": 5, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 5, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 5, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 5, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 5, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 5, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": [], "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": [], "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": [], "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 5, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 5, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 5, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 5, "\u067e\u0686\u06a2\u06a4\u06af": 5, "\u0905": [], "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": [], "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": [], "\u0950": [], "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": [], "\u09bd": [], "\u09ce": [], "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": []}, "titles": ["Changelog", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 2, "0": 0, "01": 0, "02": 0, "03": 0, "04": [], "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 1], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 1], "2021": 0, "2022": 0, "2023": [], "2024": 0, "21": [], "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 1], "31": 0, "4": [0, 1], "5": 0, "6": 0, "7": 0, "8": [], "9": [], "advanc": 16, "approach": 16, "architectur": 16, "arg": [5, 6, 7, 8, 9], "artefact": 6, "artefactdetect": [], "attribut": 1, "avail": [14, 16], "aw": 12, "ban": 1, "block": 6, "bug": 2, "changelog": 0, "choos": [14, 16], "classif": [7, 13], "code": [1, 2], "codebas": 2, "commit": 2, "commun": 13, "compos": 8, "conda": [], "conduct": 1, "connect": 2, "continu": 2, "contrib": [], "contribut": 2, "contributor": 1, "convent": 13, "correct": 1, "coven": 1, "custom": [5, 11], "data": 14, "dataload": 5, "dataset": [4, 5, 14], "detect": [4, 7, 13, 14, 16], "develop": 2, "do": 16, "doctr": [2, 4, 5, 6, 7, 8, 9, 10, 15], "document": [2, 4, 6], "end": 16, "enforc": 1, "evalu": 9, "export": 15, "factori": 7, "featur": [2, 4], "feedback": 2, "file": 6, "from": 13, "gener": [5, 14], "git": 3, "guidelin": 1, "half": 15, "hub": 13, "huggingfac": 13, "i": 16, "infer": 15, "instal": [2, 3], "integr": 2, "io": 6, "lambda": 12, "let": 2, "line": 6, "linux": [], "load": [11, 13, 14], "loader": 5, "main": 4, "mode": 2, "model": [4, 7, 11, 13, 15, 16], "modifi": 2, "modul": [], "name": 13, "notebook": 10, "object": 14, "ocr": 16, "onli": [], "onnx": 15, "optim": 15, "option": 16, "orient": [], "our": 1, "output": 16, "own": [11, 14], "packag": 3, "page": 6, "perman": 1, "pipelin": [], "pledg": 1, "precis": 15, "predictor": 16, "prepar": 15, "prerequisit": 3, "pretrain": 13, "push": 13, "python": 3, "qualiti": 2, "question": 2, "read": 6, "readi": 14, "recognit": [4, 7, 13, 14, 16], "reconstitut": [], "report": 2, "request": 2, "resourc": [], "respons": 1, "return": [5, 6, 7, 9], "right": 16, "scope": 1, "share": 13, "should": 16, "stage": 16, "standard": 1, "structur": [2, 6], "style": 2, "support": [4, 5, 8], "synthet": [5, 14], "task": 9, "temporari": 1, "test": 2, "text": [4, 16], "train": 11, "transform": 8, "two": 16, "unit": 2, "us": [14, 15], "util": 9, "v0": 0, "verif": 2, "via": 3, "visual": 9, "vocab": 5, "warn": 1, "what": 16, "word": 6, "your": [11, 13, 14, 15], "zoo": [4, 7]}})
\ No newline at end of file
+Search.setIndex({"alltitles": {"1. Correction": [[1, "correction"]], "2. Warning": [[1, "warning"]], "3. Temporary Ban": [[1, "temporary-ban"]], "4. Permanent Ban": [[1, "permanent-ban"]], "AWS Lambda": [[12, null]], "Advanced options": [[16, "advanced-options"]], "Args:": [[5, "args"], [5, "id4"], [5, "id7"], [5, "id10"], [5, "id13"], [5, "id16"], [5, "id19"], [5, "id22"], [5, "id25"], [5, "id29"], [5, "id32"], [5, "id37"], [5, "id40"], [5, "id46"], [5, "id49"], [5, "id50"], [5, "id51"], [5, "id54"], [5, "id57"], [5, "id60"], [5, "id61"], [6, "args"], [6, "id2"], [6, "id3"], [6, "id4"], [6, "id5"], [6, "id6"], [6, "id7"], [6, "id10"], [6, "id12"], [6, "id14"], [6, "id16"], [6, "id20"], [6, "id24"], [6, "id28"], [7, "args"], [7, "id3"], [7, "id8"], [7, "id13"], [7, "id17"], [7, "id21"], [7, "id26"], [7, "id31"], [7, "id36"], [7, "id41"], [7, "id45"], [7, "id49"], [7, "id54"], [7, "id58"], [7, "id63"], [7, "id68"], [7, "id72"], [7, "id76"], [7, "id81"], [7, "id86"], [7, "id90"], [7, "id95"], [7, "id99"], [7, "id103"], [7, "id108"], [7, "id113"], [7, "id118"], [7, "id122"], [7, "id126"], [7, "id131"], [7, "id135"], [7, "id139"], [7, "id143"], [7, "id145"], [7, "id147"], [7, "id149"], [8, "args"], [8, "id1"], [8, "id2"], [8, "id3"], [8, "id4"], [8, "id5"], [8, "id6"], [8, "id7"], [8, "id8"], [8, "id9"], [8, "id10"], [8, "id11"], [8, "id12"], [8, "id13"], [8, "id14"], [8, "id15"], [8, "id16"], [8, "id17"], [8, "id18"], [9, "args"], [9, "id3"], [9, "id5"], [9, "id6"], [9, "id7"], [9, "id8"], [9, "id9"], [9, "id10"], [9, "id11"]], "Artefact": [[6, "artefact"]], "Attribution": [[1, "attribution"]], "Available Datasets": [[14, "available-datasets"]], "Available architectures": [[16, "available-architectures"], [16, "id1"], [16, "id2"]], "Block": [[6, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[14, null]], "Choosing the right model": [[16, null]], "Classification": [[13, "classification"]], "Code quality": [[2, "code-quality"]], "Code style verification": [[2, "code-style-verification"]], "Codebase structure": [[2, "codebase-structure"]], "Commits": [[2, "commits"]], "Composing transformations": [[8, "composing-transformations"]], "Continuous Integration": [[2, "continuous-integration"]], "Contributing to docTR": [[2, null]], "Contributor Covenant Code of Conduct": [[1, null]], "Custom dataset loader": [[5, "custom-dataset-loader"]], "Data Loading": [[14, "data-loading"]], "Dataloader": [[5, "dataloader"]], "Detection": [[13, "detection"], [14, "detection"]], "Detection predictors": [[16, "detection-predictors"]], "Developer mode installation": [[2, "developer-mode-installation"]], "Developing docTR": [[2, "developing-doctr"]], "Document": [[6, "document"]], "Document structure": [[6, "document-structure"]], "End-to-End OCR": [[16, "end-to-end-ocr"]], "Enforcement": [[1, "enforcement"]], "Enforcement Guidelines": [[1, "enforcement-guidelines"]], "Enforcement Responsibilities": [[1, "enforcement-responsibilities"]], "Export to ONNX": [[15, "export-to-onnx"]], "Feature requests & bug report": [[2, "feature-requests-bug-report"]], "Feedback": [[2, "feedback"]], "File reading": [[6, "file-reading"]], "Half-precision": [[15, "half-precision"]], "Installation": [[3, null]], "Let\u2019s connect": [[2, "let-s-connect"]], "Line": [[6, "line"]], "Loading from Huggingface Hub": [[13, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[11, "loading-your-custom-trained-model"]], "Main Features": [[4, "main-features"]], "Model optimization": [[15, "model-optimization"]], "Model zoo": [[4, "model-zoo"]], "Modifying the documentation": [[2, "modifying-the-documentation"]], "Naming conventions": [[13, "naming-conventions"]], "Object Detection": [[14, "object-detection"]], "Our Pledge": [[1, "our-pledge"]], "Our Standards": [[1, "our-standards"]], "Page": [[6, "page"]], "Preparing your model for inference": [[15, null]], "Prerequisites": [[3, "prerequisites"]], "Pretrained community models": [[13, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[13, "pushing-to-the-huggingface-hub"]], "Questions": [[2, "questions"]], "Recognition": [[13, "recognition"], [14, "recognition"]], "Recognition predictors": [[16, "recognition-predictors"]], "Returns:": [[5, "returns"], [6, "returns"], [6, "id11"], [6, "id13"], [6, "id15"], [6, "id19"], [6, "id23"], [6, "id27"], [6, "id31"], [7, "returns"], [7, "id6"], [7, "id11"], [7, "id16"], [7, "id20"], [7, "id24"], [7, "id29"], [7, "id34"], [7, "id39"], [7, "id44"], [7, "id48"], [7, "id52"], [7, "id57"], [7, "id61"], [7, "id66"], [7, "id71"], [7, "id75"], [7, "id79"], [7, "id84"], [7, "id89"], [7, "id93"], [7, "id98"], [7, "id102"], [7, "id106"], [7, "id111"], [7, "id116"], [7, "id121"], [7, "id125"], [7, "id129"], [7, "id134"], [7, "id138"], [7, "id142"], [7, "id144"], [7, "id146"], [7, "id148"], [9, "returns"], [9, "id4"]], "Scope": [[1, "scope"]], "Share your model with the community": [[13, null]], "Supported Vocabs": [[5, "supported-vocabs"]], "Supported datasets": [[4, "supported-datasets"]], "Supported transformations": [[8, "supported-transformations"]], "Synthetic dataset generator": [[5, "synthetic-dataset-generator"], [14, "synthetic-dataset-generator"]], "Task evaluation": [[9, "task-evaluation"]], "Text Detection": [[16, "text-detection"]], "Text Recognition": [[16, "text-recognition"]], "Text detection models": [[4, "text-detection-models"]], "Text recognition models": [[4, "text-recognition-models"]], "Train your own model": [[11, null]], "Two-stage approaches": [[16, "two-stage-approaches"]], "Unit tests": [[2, "unit-tests"]], "Use your own datasets": [[14, "use-your-own-datasets"]], "Using your ONNX exported model in docTR": [[15, "using-your-onnx-exported-model-in-doctr"]], "Via Git": [[3, "via-git"]], "Via Python Package": [[3, "via-python-package"]], "Visualization": [[9, "visualization"]], "What should I do with the output?": [[16, "what-should-i-do-with-the-output"]], "Word": [[6, "word"]], "docTR Notebooks": [[10, null]], "docTR Vocabs": [[5, "id62"]], "docTR: Document Text Recognition": [[4, null]], "doctr.datasets": [[5, null], [5, "datasets"]], "doctr.io": [[6, null]], "doctr.models": [[7, null]], "doctr.models.classification": [[7, "doctr-models-classification"]], "doctr.models.detection": [[7, "doctr-models-detection"]], "doctr.models.factory": [[7, "doctr-models-factory"]], "doctr.models.recognition": [[7, "doctr-models-recognition"]], "doctr.models.zoo": [[7, "doctr-models-zoo"]], "doctr.transforms": [[8, null]], "doctr.utils": [[9, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2024-09-09)": [[0, "v0-7-0-2024-09-09"]]}, "docnames": ["changelog", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[6, "doctr.io.Artefact", false]], "block (class in doctr.io)": [[6, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms)": [[8, "doctr.transforms.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[5, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms)": [[8, "doctr.transforms.ColorInversion", false]], "compose (class in doctr.transforms)": [[8, "doctr.transforms.Compose", false]], "cord (class in doctr.datasets)": [[5, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[7, "doctr.models.classification.crop_orientation_predictor", false]], "dataloader (class in doctr.datasets.loader)": [[5, "doctr.datasets.loader.DataLoader", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[7, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[7, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[6, "doctr.io.decode_img_as_tensor", false]], "detection_predictor() (in module doctr.models.detection)": [[7, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[5, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[5, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[6, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[6, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[5, "doctr.datasets.encode_sequences", false]], "from_hub() (in module doctr.models.factory)": [[7, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[6, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[6, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[6, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[5, "doctr.datasets.FUNSD", false]], "gaussianblur (class in doctr.transforms)": [[8, "doctr.transforms.GaussianBlur", false]], "gaussiannoise (class in doctr.transforms)": [[8, "doctr.transforms.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[5, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[5, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[5, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[5, "doctr.datasets.IIITHWS", false]], "imgur5k (class in doctr.datasets)": [[5, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[7, "doctr.models.kie_predictor", false]], "lambdatransformation (class in doctr.transforms)": [[8, "doctr.transforms.LambdaTransformation", false]], "line (class in doctr.io)": [[6, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[7, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[7, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[7, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[7, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[7, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[5, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_orientation() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_small_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_small_r", false]], "normalize (class in doctr.transforms)": [[8, "doctr.transforms.Normalize", false]], "ocr_predictor() (in module doctr.models)": [[7, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[5, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms)": [[8, "doctr.transforms.OneOf", false]], "page (class in doctr.io)": [[6, "doctr.io.Page", false]], "parseq() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.parseq", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[7, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms)": [[8, "doctr.transforms.RandomApply", false]], "randombrightness (class in doctr.transforms)": [[8, "doctr.transforms.RandomBrightness", false]], "randomcontrast (class in doctr.transforms)": [[8, "doctr.transforms.RandomContrast", false]], "randomcrop (class in doctr.transforms)": [[8, "doctr.transforms.RandomCrop", false]], "randomgamma (class in doctr.transforms)": [[8, "doctr.transforms.RandomGamma", false]], "randomhorizontalflip (class in doctr.transforms)": [[8, "doctr.transforms.RandomHorizontalFlip", false]], "randomhue (class in doctr.transforms)": [[8, "doctr.transforms.RandomHue", false]], "randomjpegquality (class in doctr.transforms)": [[8, "doctr.transforms.RandomJpegQuality", false]], "randomrotate (class in doctr.transforms)": [[8, "doctr.transforms.RandomRotate", false]], "randomsaturation (class in doctr.transforms)": [[8, "doctr.transforms.RandomSaturation", false]], "randomshadow (class in doctr.transforms)": [[8, "doctr.transforms.RandomShadow", false]], "read_html() (in module doctr.io)": [[6, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[6, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[6, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[6, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[5, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms)": [[8, "doctr.transforms.Resize", false]], "resnet18() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet50", false]], "sar_resnet31() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[6, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[6, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[5, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[9, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[9, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[9, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[9, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[5, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[5, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.visualization)": [[9, "doctr.utils.visualization.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[5, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[7, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[7, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[7, "doctr.models.classification.textnet_tiny", false]], "togray (class in doctr.transforms)": [[8, "doctr.transforms.ToGray", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[9, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[9, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[9, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[9, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[7, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[9, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[7, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[7, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[5, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[6, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[5, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.datasets": [[5, 0, 1, "", "CORD"], [5, 0, 1, "", "CharacterGenerator"], [5, 0, 1, "", "DetectionDataset"], [5, 0, 1, "", "DocArtefacts"], [5, 0, 1, "", "FUNSD"], [5, 0, 1, "", "IC03"], [5, 0, 1, "", "IC13"], [5, 0, 1, "", "IIIT5K"], [5, 0, 1, "", "IIITHWS"], [5, 0, 1, "", "IMGUR5K"], [5, 0, 1, "", "MJSynth"], [5, 0, 1, "", "OCRDataset"], [5, 0, 1, "", "RecognitionDataset"], [5, 0, 1, "", "SROIE"], [5, 0, 1, "", "SVHN"], [5, 0, 1, "", "SVT"], [5, 0, 1, "", "SynthText"], [5, 0, 1, "", "WILDRECEIPT"], [5, 0, 1, "", "WordGenerator"], [5, 1, 1, "", "encode_sequences"]], "doctr.datasets.loader": [[5, 0, 1, "", "DataLoader"]], "doctr.io": [[6, 0, 1, "", "Artefact"], [6, 0, 1, "", "Block"], [6, 0, 1, "", "Document"], [6, 0, 1, "", "DocumentFile"], [6, 0, 1, "", "Line"], [6, 0, 1, "", "Page"], [6, 0, 1, "", "Word"], [6, 1, 1, "", "decode_img_as_tensor"], [6, 1, 1, "", "read_html"], [6, 1, 1, "", "read_img_as_numpy"], [6, 1, 1, "", "read_img_as_tensor"], [6, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[6, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[6, 2, 1, "", "from_images"], [6, 2, 1, "", "from_pdf"], [6, 2, 1, "", "from_url"]], "doctr.io.Page": [[6, 2, 1, "", "show"]], "doctr.models": [[7, 1, 1, "", "kie_predictor"], [7, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[7, 1, 1, "", "crop_orientation_predictor"], [7, 1, 1, "", "magc_resnet31"], [7, 1, 1, "", "mobilenet_v3_large"], [7, 1, 1, "", "mobilenet_v3_large_r"], [7, 1, 1, "", "mobilenet_v3_small"], [7, 1, 1, "", "mobilenet_v3_small_orientation"], [7, 1, 1, "", "mobilenet_v3_small_r"], [7, 1, 1, "", "resnet18"], [7, 1, 1, "", "resnet31"], [7, 1, 1, "", "resnet34"], [7, 1, 1, "", "resnet50"], [7, 1, 1, "", "textnet_base"], [7, 1, 1, "", "textnet_small"], [7, 1, 1, "", "textnet_tiny"], [7, 1, 1, "", "vgg16_bn_r"], [7, 1, 1, "", "vit_b"], [7, 1, 1, "", "vit_s"]], "doctr.models.detection": [[7, 1, 1, "", "db_mobilenet_v3_large"], [7, 1, 1, "", "db_resnet50"], [7, 1, 1, "", "detection_predictor"], [7, 1, 1, "", "linknet_resnet18"], [7, 1, 1, "", "linknet_resnet34"], [7, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[7, 1, 1, "", "from_hub"], [7, 1, 1, "", "login_to_hub"], [7, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[7, 1, 1, "", "crnn_mobilenet_v3_large"], [7, 1, 1, "", "crnn_mobilenet_v3_small"], [7, 1, 1, "", "crnn_vgg16_bn"], [7, 1, 1, "", "master"], [7, 1, 1, "", "parseq"], [7, 1, 1, "", "recognition_predictor"], [7, 1, 1, "", "sar_resnet31"], [7, 1, 1, "", "vitstr_base"], [7, 1, 1, "", "vitstr_small"]], "doctr.transforms": [[8, 0, 1, "", "ChannelShuffle"], [8, 0, 1, "", "ColorInversion"], [8, 0, 1, "", "Compose"], [8, 0, 1, "", "GaussianBlur"], [8, 0, 1, "", "GaussianNoise"], [8, 0, 1, "", "LambdaTransformation"], [8, 0, 1, "", "Normalize"], [8, 0, 1, "", "OneOf"], [8, 0, 1, "", "RandomApply"], [8, 0, 1, "", "RandomBrightness"], [8, 0, 1, "", "RandomContrast"], [8, 0, 1, "", "RandomCrop"], [8, 0, 1, "", "RandomGamma"], [8, 0, 1, "", "RandomHorizontalFlip"], [8, 0, 1, "", "RandomHue"], [8, 0, 1, "", "RandomJpegQuality"], [8, 0, 1, "", "RandomRotate"], [8, 0, 1, "", "RandomSaturation"], [8, 0, 1, "", "RandomShadow"], [8, 0, 1, "", "Resize"], [8, 0, 1, "", "ToGray"]], "doctr.utils.metrics": [[9, 0, 1, "", "DetectionMetric"], [9, 0, 1, "", "LocalizationConfusion"], [9, 0, 1, "", "OCRMetric"], [9, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.visualization": [[9, 1, 1, "", "synthesize_page"], [9, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [1, 6, 7, 9, 13], "0": [1, 3, 5, 8, 9, 11, 14, 16], "00": 16, "01": 16, "0123456789": 5, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 5, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 5, "02": [], "02562": 7, "03": 16, "035": 16, "0361328125": 16, "04": [], "05": 16, "06": 16, "06640625": 16, "07": 16, "08": [8, 16], "09": 16, "0966796875": 16, "1": [3, 5, 6, 7, 8, 9, 11, 14, 16], "10": [5, 9, 16], "100": [5, 8, 9, 14, 16], "1000": 16, "101": 5, "1024": [7, 9, 11, 16], "104": 5, "106": 5, "108": 5, "1095": 14, "11": 16, "110": 9, "1107": 14, "114": 5, "115": [], "1156": 14, "116": 5, "118": 5, "11800h": 16, "11th": 16, "12": [3, 16], "120": 5, "123": 5, "126": 5, "1268": 14, "128": [7, 11, 15, 16], "13": [9, 16], "130": 5, "13068": 14, "131": 5, "1337891": 14, "1357421875": 16, "1396484375": 16, "14": 16, "1420": 16, "14470v1": 5, "149": 14, "15": 16, "150": [9, 16], "1552": 16, "16": [7, 15, 16], "1630859375": 16, "1684": 16, "16x16": 7, "17": 16, "1778": 16, "1782": 16, "18": 7, "185546875": 16, "1900": 16, "1910": 7, "19342": 14, "19370": 14, "195": 5, "19598": 14, "199": 16, "1999": 16, "2": [3, 4, 5, 6, 8, 16], "20": 16, "200": 9, "2000": 14, "2003": [4, 5], "2012": 5, "2013": [4, 5], "2015": 5, "2019": 4, "2023": [], "207901": 14, "21": 16, "2103": 5, "2186": 14, "21888": 14, "22": 16, "224": [7, 8], "225": 8, "22672": 14, "229": [8, 14], "23": 16, "233": 14, "234": 5, "236": [], "24": 16, "246": 14, "249": 14, "25": 16, "2504": 16, "255": [6, 7, 8, 9, 16], "256": 7, "257": 14, "26": 16, "26032": 14, "264": 11, "27": 16, "2700": 14, "2710": 16, "2749": 11, "28": 16, "287": 11, "29": 16, "296": 11, "299": 11, "2d": 16, "3": [3, 4, 6, 7, 8, 9, 15, 16], "30": 16, "300": 14, "3000": 14, "301": 11, "30595": 16, "30ghz": 16, "31": 7, "32": [5, 7, 8, 11, 14, 15, 16], "3232421875": 16, "33": [8, 16], "33402": 14, "33608": 14, "34": [7, 16], "340": 16, "3456": 16, "35": [], "3515625": 16, "36": [], "360": 14, "37": [5, 16], "38": 16, "39": 16, "4": [7, 8, 9, 16], "40": 16, "406": 8, "41": 16, "42": 16, "43": 16, "44": 16, "45": 16, "456": 8, "46": 16, "47": 16, "472": 14, "48": [5, 16], "485": 8, "49": 16, "49377": 14, "5": [5, 8, 9, 16], "50": [7, 14, 16], "51": 16, "51171875": 16, "512": 7, "52": [5, 16], "529": 16, "53": 16, "54": 16, "540": 16, "5478515625": 16, "55": 16, "56": 16, "57": 16, "58": 16, "580": 16, "5810546875": 16, "583": 16, "59": 16, "597": 16, "5k": [4, 5], "5m": [], "6": [8, 16], "60": 8, "600": [7, 9, 16], "61": 16, "62": 16, "626": 14, "63": 16, "64": [7, 8, 16], "641": 16, "647": 14, "65": 16, "66": 16, "67": 16, "68": 16, "69": 16, "693": 11, "694": 11, "695": 11, "6m": [], "7": 16, "70": [9, 16], "707470": 14, "71": 16, "7100000": 14, "7141797": 14, "7149": 14, "72": 16, "72dpi": 6, "73": 16, "73257": 14, "74": 16, "75": [8, 16], "7581382": 14, "76": 16, "77": 16, "772": 11, "772875": 14, "78": 16, "785": 11, "79": 16, "793533": 14, "796": 14, "798": 11, "7m": [], "8": [3, 7, 8, 16], "80": 16, "800": [7, 9, 14, 16], "81": 16, "82": 16, "83": 16, "84": 16, "849": 14, "85": 16, "8564453125": 16, "857": 16, "85875": 14, "86": 16, "8603515625": 16, "87": 16, "8707": 14, "88": 16, "89": 16, "9": 16, "90": 16, "90k": 5, "90kdict32px": 5, "91": 16, "914085328578949": 16, "92": 16, "93": 16, "94": [5, 16], "95": [9, 16], "9578408598899841": 16, "96": 16, "97": [], "98": 16, "99": 16, "9949972033500671": 16, "A": [1, 2, 4, 5, 6, 7, 10, 15], "As": 2, "Be": 16, "Being": 1, "By": 12, "For": [1, 2, 3, 11, 16], "If": [2, 3, 6, 7, 11, 16], "In": [2, 5, 14], "It": [8, 13, 15], "Its": [4, 7], "No": [1, 16], "Of": 5, "Or": [], "The": [1, 2, 5, 6, 9, 12, 16], "Then": 7, "To": [2, 3, 12, 13, 16], "_": [1, 5, 7], "__call__": 16, "_build": 2, "_i": 9, "ab": 5, "abc": [], "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 5, "abdef": [5, 14], "abl": [14, 16], "about": [1, 14, 16], "abov": 16, "abstract": [], "abstractdataset": 5, "abus": 1, "accept": 1, "access": [4, 6, 14, 16], "account": [1, 13], "accur": 16, "accuraci": 9, "achiev": 15, "act": 1, "action": 1, "activ": 4, "ad": [2, 7, 8], "adapt": 1, "add": [8, 9, 13, 16], "add_hook": 16, "add_label": 9, "addit": [2, 3, 6], "addition": [2, 16], "address": [1, 6], "adjust": 8, "advanc": 1, "advantag": 15, "advis": 2, "aesthet": [4, 5], "affect": 1, "after": [13, 16], "ag": 1, "again": 7, "aggreg": [9, 14], "aggress": 1, "align": [1, 6], "all": [1, 2, 5, 6, 8, 9, 14, 16], "allow": 1, "along": 16, "alreadi": 2, "also": [1, 7, 13, 14, 16], "alwai": 14, "an": [1, 2, 4, 5, 6, 7, 9, 15, 16], "analysi": 6, "ancient_greek": 5, "andrej": [], "angl": [6, 8], "ani": [1, 5, 6, 7, 8, 9, 16], "annot": 5, "anot": 14, "anoth": [3, 7, 11, 14], "answer": 1, "anyascii": [], "anyon": 4, "anyth": [], "api": [2, 4], "apolog": 1, "apologi": 1, "app": 2, "appear": 1, "appli": [1, 5, 8], "applic": [4, 7], "appoint": 1, "appreci": 13, "appropri": [1, 2, 16], "ar": [1, 2, 3, 5, 6, 8, 9, 10, 14, 16], "arab": 5, "arabic_diacrit": 5, "arabic_lett": 5, "arabic_punctu": 5, "arbitrarili": 7, "arch": [7, 13], "architectur": [4, 7, 13], "area": 16, "arg": [], "argument": [5, 6, 7, 9, 16], "around": 1, "arrai": [6, 8, 9], "art": 4, "artefact": [9, 10, 16], "artefact_typ": 6, "artefactdetector": [], "articl": [], "artifici": [4, 5], "arxiv": [5, 7], "asarrai": 9, "ascii_lett": 5, "aspect": [4, 7, 8, 16], "assess": 9, "assign": 9, "associ": 6, "assum": 7, "assume_straight_pag": [7, 16], "astyp": [7, 9, 16], "attack": 1, "attend": [4, 7], "attent": [1, 7], "autom": 4, "automat": 16, "autoregress": [4, 7], "avail": [1, 4, 8], "averag": [8, 16], "avoid": [1, 3], "aw": [4, 16], "awar": 16, "azur": 16, "b": [7, 9, 16], "b_j": 9, "back": 2, "backbon": 7, "backend": 16, "background": 14, "bangla": [], "bar": [], "bar_cod": 14, "baranovskij": [], "base": [4, 7], "baselin": [4, 7, 16], "batch": [5, 7, 8, 14, 16], "batch_siz": [5, 11, 14, 15], "bblanchon": [], "bbox": 16, "becaus": 12, "been": [2, 9, 14, 16], "befor": [5, 7, 8, 16], "begin": 9, "behavior": [1, 16], "being": [9, 16], "belong": 16, "benchmark": 16, "best": 1, "better": [10, 16], "between": [8, 9, 16], "bgr": 6, "bilinear": 8, "bin_thresh": 16, "binar": [4, 7, 16], "binari": [6, 15, 16], "bit": 15, "blank": 9, "block": [9, 16], "block_1_1": 16, "blue": 9, "blur": 8, "bmvc": 5, "bn": 13, "bodi": [1, 16], "bool": [5, 6, 7, 8, 9], "boolean": [7, 16], "both": [4, 5, 8, 14, 16], "bottom": [7, 16], "bound": [5, 6, 7, 8, 9, 16], "box": [5, 6, 7, 8, 9, 14, 16], "box_thresh": 16, "brew": 3, "bright": 8, "broadcast": 9, "browser": [2, 4], "build": [2, 3], "built": 2, "byte": [6, 16], "c": [6, 9], "c_j": 9, "cach": [2, 5, 12], "cache_sampl": 5, "cairo": 3, "call": [], "callabl": [5, 8], "can": [2, 3, 11, 12, 13, 14, 16], "capabl": [2, 10, 16], "case": [5, 9], "cf": 16, "cfg": 16, "challeng": 5, "challenge2_test_task12_imag": 5, "challenge2_test_task1_gt": 5, "challenge2_training_task12_imag": 5, "challenge2_training_task1_gt": 5, "chang": 12, "channel": [1, 2, 6, 8], "channel_prior": [], "channelshuffl": 8, "charact": [4, 5, 6, 9, 14, 16], "charactergener": [5, 14], "characterist": 1, "charg": 16, "charset": 16, "chart": 6, "check": [2, 13, 16], "checkpoint": 7, "chip": 3, "christian": [], "ci": 2, "clarifi": 1, "clariti": 1, "class": [1, 5, 6, 8, 9, 16], "class_nam": 11, "classif": 14, "classif_mobilenet_v3_smal": 7, "classmethod": 6, "clear": 2, "clone": 3, "close": 2, "co": 13, "code": [4, 6], "codecov": 2, "colab": 10, "collate_fn": 5, "collect": 6, "color": [8, 9], "colorinvers": 8, "column": 6, "com": [1, 3, 6, 7, 13], "combin": 16, "come": 15, "command": 2, "comment": 1, "commit": 1, "common": [1, 8, 9, 15], "commun": 1, "compar": 4, "comparison": [9, 16], "competit": 5, "compil": [10, 16], "complaint": 1, "complementari": 9, "complet": 2, "compon": 16, "compos": [5, 16], "comprehens": 16, "comput": [5, 9, 15, 16], "conf_threshold": [], "confid": [6, 9, 16], "config": 7, "configur": 7, "confus": 9, "consecut": [8, 16], "consequ": 1, "consid": [1, 2, 5, 6, 9, 16], "consist": 16, "consolid": [4, 5], "constant": 8, "construct": 1, "consum": 9, "contact": 1, "contain": [5, 14], "content": [5, 6, 9, 16], "context": 7, "contib": [], "continu": 1, "contrast": 8, "contrast_factor": 8, "contrib": [], "contribut": 1, "contributor": 2, "convers": 6, "convert": [6, 8], "convert_target_to_rel": [], "convolut": 7, "cool": [], "coordin": [6, 16], "cord": [4, 5, 14, 16], "core": [9, 16], "corner": 16, "correct": 8, "correspond": [3, 6, 16], "could": 1, "counterpart": 9, "cover": 2, "coverag": 2, "cpu": [4, 11], "creat": 13, "crnn": [4, 7, 13], "crnn_mobilenet_v3_larg": [7, 13, 16], "crnn_mobilenet_v3_smal": [7, 15, 16], "crnn_vgg16_bn": [7, 11, 13, 16], "crop": [7, 8, 14, 16], "crop_bboxes_from_imag": [], "crop_orient": [], "crop_orientation_predictor": 7, "crop_param": [], "croporientationpredictor": 7, "cuda": 15, "currenc": 5, "current": [2, 16], "custom": [13, 16], "custom_crop_orientation_model": [], "custom_page_orientation_model": [], "customhook": 16, "cvit": 4, "czczup": 7, "czech": 5, "d": [5, 14], "danish": 5, "data": [4, 5, 6, 8, 9, 11, 13], "dataload": 14, "dataset": [7, 11, 16], "dataset_info": 5, "date": [11, 16], "db": 13, "db_mobilenet_v3_larg": [7, 13, 16], "db_resnet34": 16, "db_resnet50": [7, 11, 13, 16], "db_resnet50_rot": [], "dbnet": [4, 7], "deal": [], "decis": 1, "decod": 6, "decode_img_as_tensor": 6, "decode_sequ": [], "dedic": [], "deem": 1, "deep": [7, 16], "def": 16, "default": [6, 9, 11, 12, 16], "defer": 14, "defin": [9, 15], "degre": 8, "degress": 6, "delet": 2, "delimit": 16, "delta": 8, "demo": [2, 4], "demonstr": 1, "depend": [2, 3, 4], "deploi": 2, "deploy": 4, "derogatori": 1, "describ": [7, 9], "descript": 10, "design": 8, "desir": 6, "det_arch": [7, 11, 13, 15], "det_b": [], "det_model": [11, 13], "det_param": 11, "det_predictor": [11, 16], "detail": [11, 16], "detect": [5, 9, 10, 11], "detect_languag": 7, "detect_orient": 7, "detection_predictor": [7, 16], "detection_task": [], "detectiondataset": [5, 14], "detectionmetr": 9, "detectionpredictor": [7, 11], "detector": 7, "deterior": 7, "determin": 1, "dev": [2, 12], "develop": 3, "deviat": 8, "devic": 15, "dict": [6, 9, 16], "dictionari": [6, 9], "differ": 1, "differenti": [4, 7], "digit": [4, 5, 14], "dimens": [6, 9, 16], "dimension": 8, "direct": 5, "directli": [13, 16], "directori": [2, 12], "disabl": [1, 12, 16], "disable_crop_orient": [], "disable_page_orient": [], "disclaim": 16, "discuss": 2, "disparag": 1, "displai": [6, 9], "display_artefact": 9, "distribut": 8, "div": 16, "divers": 1, "divid": 6, "do": [2, 3, 7], "doc": [2, 6, 15, 16], "docartefact": [5, 14], "docstr": 2, "doctr": [3, 11, 12, 13, 14, 16], "doctr_cache_dir": 12, "doctr_multiprocessing_dis": 12, "document": [5, 7, 9, 10, 14, 16], "documentbuild": 16, "documentfil": [6, 13], "doesn": [], "don": [11, 16], "done": 8, "download": [5, 14], "download_from_url": [], "downsiz": 7, "draw": [8, 9], "draw_proba": 9, "drop": 5, "drop_last": 5, "dtype": [6, 7, 8, 9, 15], "dual": [4, 5], "dummi": 13, "dummy_img": 16, "dummy_input": 15, "dure": 1, "dutch": 5, "dynam": 5, "dynamic_seq_length": 5, "e": [1, 2, 3, 6, 7], "each": [4, 5, 6, 7, 8, 9, 14, 16], "eas": 2, "easi": [4, 9, 13], "easili": [6, 9, 11, 13, 14, 16], "econom": 1, "edit": 1, "educ": 1, "effect": [], "effici": [2, 4, 5, 7], "either": [9, 16], "element": [5, 6, 7, 9, 16], "els": 2, "email": 1, "empathi": 1, "en": 16, "enabl": [5, 6], "enclos": 6, "encod": [4, 5, 6, 7, 16], "encode_sequ": 5, "encode_str": [], "encount": 2, "encrypt": 6, "end": [4, 5, 7, 9], "english": [5, 14], "enough": [2, 16], "ensur": 2, "entri": 5, "environ": [1, 12], "eo": 5, "equiv": 16, "estim": 7, "etc": 6, "ethnic": 1, "evalu": [14, 16], "event": 1, "everyon": 1, "everyth": [2, 16], "exact": [9, 16], "exampl": [1, 2, 4, 5, 7, 13, 16], "exchang": 15, "execut": 16, "exist": 13, "expand": 8, "expect": [6, 8, 9], "experi": 1, "explan": [1, 16], "explicit": 1, "exploit": [4, 7], "export": [6, 7, 9, 10, 16], "export_as_straight_box": [7, 16], "export_as_xml": 16, "export_model_to_onnx": 15, "express": [1, 8], "extens": 6, "extern": [1, 14], "extra": 3, "extract": [4, 5], "extractor": 7, "f_": 9, "f_a": 9, "factor": 8, "fair": 1, "fairli": 1, "fals": [5, 6, 7, 8, 9, 11, 16], "famili": 9, "faq": 1, "fascan": 13, "fast": [4, 5, 7], "fast_bas": [], "fast_smal": [], "fast_tini": [], "faster": [7, 15], "fasterrcnn_mobilenet_v3_large_fpn": 7, "favorit": 16, "featur": [3, 7, 9, 10], "feedback": 1, "feel": [2, 13], "felix92": 13, "few": [3, 15, 16], "figsiz": 9, "figur": 9, "file": [2, 5], "final": 7, "find": [2, 3, 14], "fine": [], "finnish": 5, "first": [2, 5], "firsthand": 5, "fit": [7, 16], "flag": 16, "flip": 8, "float": [6, 8, 9, 15], "float32": [6, 7, 8, 15], "fn": 8, "focu": 13, "focus": [1, 5], "folder": 5, "follow": [1, 2, 3, 5, 8, 9, 11, 12, 13, 16], "font": [5, 9], "font_famili": [5, 9], "font_siz": 9, "foral": 9, "forc": 2, "forg": [], "form": [4, 5, 16], "format": [6, 9, 11, 14, 15, 16], "forpost": [4, 5], "forum": 2, "found": [], "fp16": 15, "frac": 9, "framework": [3, 13, 14, 16], "free": [1, 2, 13], "french": [5, 11, 13, 16], "friendli": 4, "from": [1, 4, 5, 6, 7, 8, 9, 10, 11, 14, 15, 16], "from_hub": [7, 13], "from_imag": [6, 13], "from_pdf": 6, "from_url": 6, "full": [5, 9, 16], "function": [5, 8, 9], "funsd": [4, 5, 14, 16], "further": 14, "futur": 5, "g": [6, 7], "g_": 9, "g_x": 9, "gallagh": [], "gamma": 8, "gaussian": 8, "gaussianblur": 8, "gaussiannois": 8, "gdk": 3, "gen": 16, "gender": 1, "gener": [2, 4, 7], "generic_cyrillic_lett": [], "geom": [], "geometri": [4, 6, 16], "geq": 9, "german": [5, 11, 13], "get": 16, "git": 13, "github": [2, 3, 7, 13], "give": 1, "given": [5, 6, 8, 9, 16], "global": 7, "go": 16, "good": 15, "googl": 2, "googlevis": 4, "gpu": [4, 15], "gracefulli": 1, "graph": [4, 5, 6], "grayscal": 8, "ground": 9, "groung": 9, "group": [4, 16], "gt": 9, "gt_box": 9, "gt_label": 9, "gtk": 3, "guid": 2, "guidanc": 14, "gvision": 16, "h": [6, 7, 8], "h_": 9, "ha": [2, 5, 9, 14], "handl": [14, 16], "handwrit": 5, "handwritten": 14, "harass": 1, "hardwar": [], "harm": 1, "hat": 9, "have": [1, 2, 9, 11, 13, 14, 16], "head": [7, 16], "healthi": 1, "hebrew": 5, "height": 6, "hello": [9, 16], "help": 15, "here": [3, 8, 10, 14, 16], "hf": 7, "hf_hub_download": 7, "high": 6, "higher": [3, 5, 16], "hindi": [], "hindi_digit": 5, "hocr": 16, "homebrew": 3, "hook": 16, "horizont": [6, 8], "hous": 5, "how": [2, 11, 13, 14], "howev": 14, "hsv": 8, "html": [1, 2, 6, 16], "http": [1, 3, 5, 6, 7, 13, 16], "hub": 7, "hue": 8, "huggingfac": 7, "hw": 5, "i": [1, 2, 5, 6, 7, 8, 9, 12, 13, 14, 15], "i7": 16, "ibrahimov": [], "ic03": [4, 5, 14], "ic13": [4, 5, 14], "icdar": [4, 5], "icdar2019": 5, "id": 16, "ident": 1, "identifi": 4, "iiit": [4, 5], "iiit5k": [5, 14], "iiithw": [4, 5, 14], "imag": [4, 5, 6, 7, 8, 9, 13, 14, 16], "imagenet": 7, "imageri": 1, "images_90k_norm": 5, "imagetensor": [], "imagetransform": [], "img": [5, 8, 14], "img_cont": 6, "img_fold": [5, 14], "img_path": 6, "img_transform": 5, "imgur5k": [4, 5, 14], "imgur5k_annot": 5, "imlist": 5, "impact": 1, "implement": [5, 6, 7, 8, 9, 16], "import": [5, 6, 7, 8, 9, 11, 13, 14, 15, 16], "improv": 7, "inappropri": 1, "incid": 1, "includ": [1, 3, 5, 14, 15], "inclus": 1, "increas": 8, "independ": [], "index": [2, 6], "indic": 9, "individu": 1, "infer": [4, 7, 8], "inform": [1, 2, 4, 5, 14], "initi": [], "input": [2, 6, 7, 8, 15, 16], "input_crop": 7, "input_pag": [7, 9, 16], "input_seq": [], "input_shap": 15, "input_str": [], "input_tensor": 7, "inspir": [1, 8], "instal": 13, "instanc": [1, 16], "instanti": [7, 16], "instead": [5, 6, 7], "insult": 1, "int": [5, 6, 8, 9], "int64": [8, 9], "integ": 9, "integr": [4, 13, 14], "intel": 16, "interact": [1, 6, 9], "interfac": 13, "interoper": 15, "interpol": 8, "interpret": [5, 6], "intersect": 9, "invert": 8, "investig": 1, "invis": 1, "involv": [1, 16], "io": 13, "iou": 9, "iou_thresh": 9, "iou_threshold": [], "irregular": [4, 7, 14], "isn": 5, "issu": [1, 2, 13], "italian": 5, "iter": [5, 8, 14, 16], "its": [6, 7, 8, 9, 14, 16], "itself": [7, 13], "j": 9, "jame": [], "job": 2, "join": 2, "jpeg": 8, "jpegqual": 8, "jpg": [5, 6, 13], "json": [5, 14, 16], "json_output": 16, "jump": 2, "just": 1, "kei": [4, 5], "kera": [7, 15], "kernel": [7, 8], "kernel_shap": 8, "keywoard": 7, "keyword": [5, 6, 7, 9], "kie": [7, 11], "kie_predictor": [7, 11], "kiepredictor": 7, "kind": 1, "know": 2, "kwarg": [5, 6, 7, 9], "l": 9, "l_j": 9, "label": [5, 8, 9, 14], "label_fil": [5, 14], "label_fold": 5, "label_path": [5, 14], "labels_path": [5, 14], "ladder": 1, "lambda": 8, "lambdatransform": 8, "lang": 16, "languag": [1, 4, 5, 6, 7, 13, 16], "larg": [7, 13], "largest": 9, "last": [3, 5], "latenc": 7, "later": 2, "latest": [3, 16], "latin": 5, "layer": 15, "layout": 16, "lead": 1, "leader": 1, "learn": [1, 4, 7, 15, 16], "least": 3, "left": [9, 16], "legacy_french": 5, "length": [5, 16], "less": [15, 16], "level": [1, 5, 9, 16], "leverag": 10, "lf": 13, "libffi": 3, "librari": [2, 3, 10, 11], "light": 4, "lightweight": [], "like": 1, "limits_": 9, "line": [4, 7, 9, 16], "line_1_1": 16, "link": 11, "linknet": [4, 7], "linknet_resnet18": [7, 11, 16], "linknet_resnet18_rot": [], "linknet_resnet34": [7, 15, 16], "linknet_resnet50": [7, 16], "linux": 3, "list": [5, 6, 8, 9, 13], "ll": 9, "load": [4, 5, 7], "load_state_dict": 11, "load_weight": 11, "loc_pr": 16, "local": [2, 4, 5, 7, 9, 14, 16], "localis": 5, "localizationconfus": 9, "locat": [2, 6, 16], "login": 7, "login_to_hub": [7, 13], "logo": [6, 14], "love": 13, "lower": [8, 9, 16], "m": [2, 9, 16], "m1": 3, "macbook": 3, "machin": 15, "maco": 3, "made": 4, "magc_resnet31": 7, "mai": [1, 2], "mail": 1, "main": 10, "maintain": 4, "mainten": 2, "make": [1, 2, 9, 12, 13, 15, 16], "mani": [14, 16], "manipul": 16, "map": [5, 7], "map_loc": 11, "mask": [], "mask_label": [], "mask_shap": 9, "master": [4, 7, 16], "match": [9, 16], "mathcal": 9, "matplotlib": [6, 9], "max": [5, 8, 9], "max_angl": 8, "max_area": 8, "max_char": [5, 14], "max_delta": 8, "max_font_s": [], "max_gain": 8, "max_gamma": 8, "max_qual": 8, "max_ratio": 8, "maximum": [5, 8], "maxval": [7, 8], "mbox": 9, "mean": [8, 9, 11], "meaniou": 9, "meant": [6, 15], "measur": 16, "media": 1, "median": 7, "meet": 11, "member": 1, "memori": [9, 12, 15], "mention": 16, "merg": 5, "messag": 2, "meta": 16, "metadata": 15, "metal": 3, "method": [6, 8, 16], "metric": [9, 16], "middl": 16, "might": [15, 16], "min": 8, "min_area": 8, "min_char": [5, 14], "min_font_s": [], "min_gain": 8, "min_gamma": 8, "min_qual": 8, "min_ratio": 8, "min_val": 8, "minde": [1, 3, 4, 7], "minim": [2, 4], "minimalist": 7, "minimum": [3, 5, 8, 9, 16], "minval": 8, "miss": 3, "mistak": 1, "mixed_float16": 15, "mixed_precis": 15, "mjsynth": [4, 5, 14], "mnt": 5, "mobilenet": [7, 13], "mobilenet_v3_larg": 7, "mobilenet_v3_large_r": 7, "mobilenet_v3_smal": 7, "mobilenet_v3_small_crop_orient": [], "mobilenet_v3_small_orient": 7, "mobilenet_v3_small_page_orient": [], "mobilenet_v3_small_r": 7, "mobilenetv3": 7, "modal": [4, 5], "mode": 3, "model": [5, 9, 12, 14], "model_nam": [7, 13, 15], "model_path": 15, "moder": 1, "modif": 2, "modifi": [7, 12, 16], "modul": [6, 7, 8, 9, 16], "moment": [], "more": [2, 9, 14, 16], "moscardi": [], "most": 16, "mozilla": 1, "multi": [4, 7], "multiclass": [], "multilingu": [5, 13], "multipl": [5, 6, 8, 16], "multipli": 8, "multiprocess": 12, "my": 7, "my_awesome_model": 13, "my_hook": 16, "n": [5, 9], "name": [5, 7, 15, 16], "nation": 1, "natur": [1, 4, 5], "nb": [], "ndarrai": [5, 6, 8, 9], "necessari": [3, 11, 12], "need": [2, 3, 5, 9, 11, 12, 13, 16], "neg": 8, "nest": 16, "netraj": [], "network": [4, 5, 7, 15], "neural": [4, 5, 7, 15], "new": [2, 9], "next": [5, 14], "nois": 8, "noisi": [4, 5], "non": [4, 5, 6, 7, 8, 9], "none": [5, 6, 7, 8, 9, 16], "normal": [7, 8], "norwegian": 5, "note": [0, 2, 5, 7, 13, 15], "now": 2, "np": [7, 8, 9, 16], "num_output_channel": 8, "num_sampl": [5, 14], "num_work": 5, "number": [5, 8, 9, 16], "numpi": [6, 7, 9, 16], "o": 3, "obb": [], "obj_detect": 13, "object": [5, 9, 10, 16], "objectness_scor": [], "oblig": 1, "obtain": 16, "occupi": 15, "ocr": [4, 5, 7, 9, 13, 14], "ocr_carea": 16, "ocr_db_crnn": 9, "ocr_lin": 16, "ocr_pag": 16, "ocr_par": 16, "ocr_predictor": [7, 11, 13, 15, 16], "ocrdataset": [5, 14], "ocrmetr": 9, "ocrpredictor": [7, 11], "ocrx_word": 16, "offens": 1, "offici": [1, 7], "offlin": 1, "offset": 8, "onc": 16, "one": [2, 5, 7, 8, 11, 13, 16], "oneof": 8, "ones": [5, 8, 9], "onli": [2, 7, 8, 9, 13, 14, 15, 16], "onlin": 1, "onnx": [], "onnxruntim": [], "onnxtr": [], "opac": 8, "opacity_rang": 8, "open": [1, 2, 13, 15], "opinion": 1, "optic": [4, 16], "optim": 4, "option": [5, 7, 11], "order": [2, 5, 6, 8], "org": [1, 5, 7, 16], "organ": 6, "orient": [1, 6, 7, 16], "orientationpredictor": [], "other": [1, 2], "otherwis": [1, 6, 9], "our": [2, 7, 16], "out": [2, 7, 8, 9, 16], "out_box": [], "outpout": 16, "output": [6, 8, 15], "output_s": [6, 8], "outsid": 12, "over": [3, 5, 9, 16], "overal": [1, 7], "overlai": 6, "overview": [], "overwrit": [], "overwritten": 13, "own": 4, "p": [8, 9, 16], "packag": [2, 4, 9, 12, 14], "pad": [5, 7, 8, 16], "page": [3, 5, 7, 9, 16], "page1": 6, "page2": 6, "page_1": 16, "page_idx": [6, 16], "page_orientation_predictor": [], "page_param": [], "pair": 9, "pango": 3, "paper": 7, "par_1_1": 16, "paragraph": 16, "paragraph_break": 16, "parallel": [], "param": [8, 16], "paramet": [4, 6, 7, 15], "pars": [4, 5], "parseq": [4, 7, 13, 16], "part": [5, 8, 16], "parti": 3, "partial": 16, "particip": 1, "pass": [5, 6, 7, 16], "password": 6, "patch": [7, 9], "path": [5, 6, 14], "path_to_checkpoint": 11, "path_to_custom_model": [], "path_to_pt": 11, "patil": [], "pattern": 1, "pdf": [6, 7, 10], "pdfpage": 6, "peopl": 1, "per": [8, 16], "perform": [4, 6, 7, 8, 9, 12, 15, 16], "period": 1, "permiss": 1, "permut": [4, 7], "persian_lett": 5, "person": [1, 14], "phase": 16, "photo": 14, "physic": [1, 6], "pick": 8, "pictur": 6, "pip": [2, 3], "pipelin": 16, "pixbuf": 3, "pixel": [6, 8, 16], "pleas": 2, "plot": 9, "plt": 9, "plug": 13, "plugin": 3, "png": 6, "point": 15, "polici": 12, "polish": 5, "polit": 1, "polygon": [5, 9, 16], "pool": 7, "portugues": 5, "posit": [1, 9], "possibl": [2, 9, 13, 16], "post": [1, 16], "postprocessor": 16, "potenti": 7, "power": 4, "ppageno": 16, "pre": [2, 7], "pre_transform_multiclass": [], "precis": [9, 16], "pred": 9, "pred_box": 9, "pred_label": 9, "predefin": 14, "predict": [6, 7, 9, 16], "predictor": [4, 6, 7, 11, 13, 15], "prefer": 14, "preinstal": [], "preprocessor": [11, 16], "prerequisit": 13, "present": 10, "preserv": [7, 8, 16], "preserve_aspect_ratio": [6, 7, 8, 11, 16], "pretrain": [4, 7, 9, 11, 15, 16], "pretrained_backbon": [7, 11], "print": 16, "prior": 5, "privaci": 1, "privat": 1, "probabl": 8, "problem": 2, "procedur": 8, "process": [2, 4, 6, 11, 16], "processor": 16, "produc": [10, 16], "product": 15, "profession": 1, "project": [2, 14], "promptli": 1, "proper": 2, "properli": 5, "provid": [1, 2, 4, 13, 14, 16], "public": [1, 4], "publicli": 16, "publish": 1, "pull": 13, "punctuat": 5, "pure": 5, "purpos": 2, "push_to_hf_hub": [7, 13], "py": 13, "pypdfium2": 6, "pyplot": [6, 9], "python": 2, "python3": 13, "pytorch": [3, 4, 7, 8, 11, 13, 15, 16], "q": 2, "qr": 6, "qr_code": 14, "qualiti": 8, "question": 1, "quickli": 4, "quicktour": 10, "r": 16, "race": 1, "ramdisk": 5, "rand": [7, 8, 9, 15, 16], "random": [7, 8, 9, 16], "randomappli": 8, "randombright": 8, "randomcontrast": 8, "randomcrop": 8, "randomgamma": 8, "randomhorizontalflip": 8, "randomhu": 8, "randomjpegqu": 8, "randomli": 8, "randomres": [], "randomrot": 8, "randomsatur": 8, "randomshadow": 8, "rang": 8, "rassi": 13, "ratio": [7, 8, 16], "raw": [6, 9], "re": 15, "read": [4, 5, 7], "read_html": 6, "read_img": [], "read_img_as_numpi": 6, "read_img_as_tensor": 6, "read_pdf": 6, "readi": 15, "real": [4, 7, 8], "realli": [], "reason": [1, 4, 5], "rebuild": 2, "rebuilt": 2, "recal": [9, 16], "receipt": [4, 5, 16], "reco_arch": [7, 11, 13, 15], "reco_b": [], "reco_model": [11, 13], "reco_param": 11, "reco_predictor": 11, "recogn": 16, "recognit": [5, 9, 11], "recognition_predictor": [7, 16], "recognition_task": [5, 14], "recognitiondataset": [5, 14], "recognitionpredictor": [7, 11], "rectangular": 7, "red": 9, "reduc": [3, 8], "refer": [2, 3, 11, 13, 14, 16], "regardless": 1, "region": 16, "regroup": 9, "regular": 14, "reject": 1, "rel": [6, 8, 9, 16], "relat": 6, "releas": [0, 3], "relev": [], "religion": 1, "remov": 1, "render": [6, 16], "repo": 7, "repo_id": [7, 13], "report": 1, "repositori": [5, 7, 13], "repres": [1, 9, 15, 16], "represent": [4, 7], "request": [1, 13], "requir": [3, 8], "research": 4, "residu": 7, "resiz": [8, 16], "resnet": 7, "resnet18": [7, 13], "resnet31": 7, "resnet34": 7, "resnet50": [7, 13], "resolv": 6, "resolve_block": 16, "resolve_lin": 16, "resourc": 14, "respect": 1, "respons": 9, "rest": [2, 8, 9], "restrict": 12, "result": [2, 5, 6, 10, 13, 16], "return": 16, "reusabl": 16, "review": 1, "rgb": [6, 8], "rgb_mode": 6, "rgb_output": 6, "right": [1, 7, 9], "roboflow": [], "robust": [4, 5], "root": 5, "rotat": [5, 6, 7, 8, 9, 14, 16], "run": [2, 3, 7], "same": [2, 6, 9, 14, 16], "sampl": [5, 14, 16], "sample_transform": 5, "samplecompos": [], "sanjin": [], "sar": [4, 7], "sar_resnet31": [7, 16], "satur": 8, "save": [7, 14], "scale": [6, 7, 8, 9], "scale_rang": [], "scan": [4, 5], "scene": [4, 5, 7], "score": 9, "script": [2, 14], "seamless": 4, "seamlessli": [4, 16], "search": 7, "searchabl": 10, "sec": 16, "second": 16, "section": [11, 13, 15, 16], "secur": [1, 12], "see": [1, 2], "seen": 16, "segment": [4, 7, 16], "self": 16, "semant": [4, 7], "send": 16, "sens": 9, "sensit": 14, "separ": 16, "sequenc": [4, 5, 6, 7, 9, 16], "sequenti": [8, 16], "seri": 1, "seriou": 1, "set": [1, 5, 7, 9, 12, 16], "set_global_polici": 15, "sever": [6, 8, 16], "sex": 1, "sexual": 1, "shade": 8, "shape": [6, 7, 8, 9, 16], "share": [12, 14], "shift": 8, "shm": 12, "should": [2, 5, 6, 8, 9], "show": [4, 6, 7, 9, 11, 13], "showcas": 2, "shuffl": [5, 8], "side": 9, "signatur": 6, "signific": 14, "simpl": [4, 7], "simpler": 7, "sinc": [5, 14], "singl": [1, 2, 4, 5], "single_img_doc": [], "size": [1, 5, 6, 8, 9, 16], "skew": 16, "slack": 2, "slightli": 7, "small": [2, 7], "smallest": 6, "smooth": [], "smoothing_factor": [], "snapshot_download": 7, "snippet": 16, "so": [2, 3, 5, 7, 13, 14], "social": 1, "socio": 1, "some": [3, 10, 13, 14], "someth": 2, "somewher": 2, "soon": 15, "sort": 1, "sourc": [5, 6, 7, 8, 9, 13], "space": [1, 16], "span": 16, "spanish": 5, "spatial": [4, 5, 6, 9], "specif": [2, 3, 9, 11, 14, 16], "specifi": [1, 5, 6], "speed": [4, 7], "sphinx": 2, "sroie": [4, 5, 14], "stabl": 3, "stackoverflow": 2, "stage": 4, "standalon": [], "standard": 8, "start": 5, "state": [4, 9], "static": 9, "statist": [], "statu": 1, "std": [8, 11], "step": 12, "still": 16, "str": [5, 6, 7, 8, 9], "straight": [5, 7, 14, 16], "straighten": [], "straighten_pag": 7, "straigten_pag": [], "stream": 6, "street": [4, 5], "strict": [], "strictli": 9, "string": [5, 6, 9, 16], "strive": 3, "strong": [4, 7], "structur": [15, 16], "subset": [5, 16], "suggest": [2, 13], "sum": 9, "summari": 9, "support": [15, 16], "sustain": 1, "svhn": [4, 5, 14], "svt": [5, 14], "swedish": 5, "symmetr": [7, 8, 16], "symmetric_pad": [7, 8, 16], "synthes": 9, "synthesize_pag": 9, "synthet": 4, "synthtext": [4, 5, 14], "system": 16, "t": [2, 5, 11, 16], "tabl": 13, "take": [1, 5, 16], "target": [5, 6, 8, 9, 14], "target_s": 5, "task": [4, 5, 7, 13, 14, 16], "task2": 5, "team": [], "techminde": [], "templat": [2, 4], "tensor": [5, 6, 8, 16], "tensorflow": [3, 4, 6, 7, 8, 11, 13, 15, 16], "tensorspec": 15, "term": 1, "test": [5, 14], "test_set": 5, "text": [5, 6, 7, 9, 14], "text_output": 16, "textmatch": 9, "textnet": 7, "textnet_bas": 7, "textnet_smal": 7, "textnet_tini": 7, "textract": [4, 16], "textstylebrush": [4, 5], "textual": [4, 5, 6, 7, 16], "tf": [3, 6, 7, 8, 13, 15], "than": [2, 3, 9, 13], "thank": 2, "thei": [1, 9], "them": [3, 5, 16], "thi": [1, 2, 3, 5, 9, 11, 12, 13, 14, 15, 16], "thing": [15, 16], "third": 3, "those": [1, 3, 6, 16], "threaten": 1, "threshold": 16, "through": [1, 8, 14], "tilman": 13, "time": [1, 4, 7, 9, 14], "tini": 7, "titl": [6, 16], "tm": 16, "tmp": 12, "togeth": [2, 6], "tograi": 8, "tool": 14, "top": [9, 16], "topic": 2, "torch": [3, 8, 11, 13, 15], "torchvis": 8, "total": 11, "toward": [1, 3], "train": [2, 5, 7, 8, 13, 14, 15, 16], "train_it": [5, 14], "train_load": [5, 14], "train_pytorch": 13, "train_set": [5, 14], "train_tensorflow": 13, "trainabl": [4, 7], "tranform": 8, "transcrib": 16, "transfer": [4, 5], "transfo": 8, "transform": [4, 5, 7], "translat": 1, "troll": 1, "true": [5, 6, 7, 8, 9, 11, 12, 13, 14, 15, 16], "truth": 9, "tune": 15, "tupl": [5, 6, 8, 9], "turn": [], "two": [6, 12], "txt": 5, "type": [6, 9, 13, 15, 16], "typic": 16, "u": [1, 2], "ucsd": 5, "udac": 2, "uint8": [6, 7, 9, 16], "ukrainian": [], "unaccept": 1, "underli": [14, 16], "underneath": 6, "understand": [4, 5, 16], "unidecod": 9, "uniform": [7, 8], "uniformli": 8, "uninterrupt": [6, 16], "union": 9, "unit": [], "unittest": 2, "unknown": [], "unknown_char": [], "unlock": 6, "unoffici": 7, "unprofession": 1, "unsolicit": 1, "unsupervis": 4, "unwelcom": 1, "up": [7, 16], "updat": 9, "upgrad": 2, "upper": [5, 8], "uppercas": 14, "url": 6, "us": [1, 2, 3, 5, 7, 9, 11, 12, 13, 16], "usabl": 16, "usag": [12, 15], "use_broadcast": 9, "use_polygon": [5, 9, 14], "useabl": 16, "useless": [], "user": [3, 4, 6, 10], "utf": 16, "util": 15, "v1": 13, "v3": [7, 13, 16], "valid": 14, "valu": [2, 6, 8, 16], "valuabl": 4, "variabl": 12, "varieti": 5, "veri": 7, "verma": [], "version": [1, 2, 3, 15, 16], "vgg": 7, "vgg16": 13, "vgg16_bn_r": 7, "via": 1, "video": [], "vietnames": 5, "view": [4, 5], "viewpoint": 1, "violat": 1, "visibl": 1, "vision": [4, 5, 7], "visiondataset": 5, "visiontransform": 7, "visual": 4, "visualize_pag": 9, "vit_": 7, "vit_b": 7, "vitstr": [4, 7, 15], "vitstr_bas": [7, 16], "vitstr_smal": [7, 11, 15, 16], "viz": [], "vocab": [11, 13, 14, 16], "vocab_nam": [], "vocabulari": [5, 11, 13], "w": [6, 7, 8, 9], "w3": 16, "wa": 1, "wai": [1, 4, 14], "want": [2, 15, 16], "warmup": 16, "wasn": 2, "we": [1, 2, 3, 4, 6, 8, 13, 14, 15, 16], "weasyprint": 6, "web": [2, 6], "websit": 5, "weight": 11, "welcom": 1, "well": [1, 15], "were": [1, 6, 16], "what": 1, "when": [1, 2, 7], "whenev": 2, "where": [2, 6, 8, 9], "whether": [2, 5, 6, 8, 9, 14, 16], "which": [1, 7, 12, 14, 16], "whichev": 3, "while": [8, 16], "why": 1, "width": 6, "wiki": 1, "wildreceipt": [4, 5, 14], "window": [3, 7, 9], "wish": 2, "within": 1, "without": [1, 5, 7], "wonder": 2, "word": [4, 5, 7, 9, 16], "word_1_1": 16, "word_1_2": 16, "word_1_3": 16, "wordgener": [5, 14], "words_onli": 9, "work": [12, 16], "worker": 5, "workflow": 2, "worklow": 2, "world": [9, 16], "worth": 7, "would": [], "wrap": 16, "wrapper": [5, 8], "write": 12, "written": [1, 6], "www": [1, 6, 16], "x": [6, 8, 9], "x_ascend": 16, "x_descend": 16, "x_i": 9, "x_size": 16, "x_wconf": 16, "xhtml": 16, "xmax": 6, "xmin": 6, "xml": 16, "xml_bytes_str": 16, "xml_element": 16, "xml_output": 16, "xmln": 16, "y": 9, "y_i": 9, "y_j": 9, "yet": [], "ymax": 6, "ymin": 6, "yolov8": [], "yolov8_artefact": [], "you": [2, 3, 5, 6, 7, 11, 12, 13, 14, 15, 16], "your": [2, 4, 6, 9, 16], "yoursit": 6, "yugesh": [], "zero": [8, 9], "zoo": [], "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 5, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 5, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 5, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 5, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 5, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": [], "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 5, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 5, "\u00e4\u00f6\u00e4\u00f6": 5, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 5, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 5, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 5, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 5, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 5, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": [], "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": [], "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": [], "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 5, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 5, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 5, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 5, "\u067e\u0686\u06a2\u06a4\u06af": 5, "\u0905": [], "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": [], "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": [], "\u0950": [], "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": [], "\u09bd": [], "\u09ce": [], "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": []}, "titles": ["Changelog", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 2, "0": 0, "01": 0, "02": 0, "03": 0, "04": [], "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 1], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 1], "2021": 0, "2022": 0, "2023": [], "2024": 0, "21": [], "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 1], "31": 0, "4": [0, 1], "5": 0, "6": 0, "7": 0, "8": [], "9": [], "advanc": 16, "approach": 16, "architectur": 16, "arg": [5, 6, 7, 8, 9], "artefact": 6, "artefactdetect": [], "attribut": 1, "avail": [14, 16], "aw": 12, "ban": 1, "block": 6, "bug": 2, "changelog": 0, "choos": [14, 16], "classif": [7, 13], "code": [1, 2], "codebas": 2, "commit": 2, "commun": 13, "compos": 8, "conda": [], "conduct": 1, "connect": 2, "continu": 2, "contrib": [], "contribut": 2, "contributor": 1, "convent": 13, "correct": 1, "coven": 1, "custom": [5, 11], "data": 14, "dataload": 5, "dataset": [4, 5, 14], "detect": [4, 7, 13, 14, 16], "develop": 2, "do": 16, "doctr": [2, 4, 5, 6, 7, 8, 9, 10, 15], "document": [2, 4, 6], "end": 16, "enforc": 1, "evalu": 9, "export": 15, "factori": 7, "featur": [2, 4], "feedback": 2, "file": 6, "from": 13, "gener": [5, 14], "git": 3, "guidelin": 1, "half": 15, "hub": 13, "huggingfac": 13, "i": 16, "infer": 15, "instal": [2, 3], "integr": 2, "io": 6, "lambda": 12, "let": 2, "line": 6, "linux": [], "load": [11, 13, 14], "loader": 5, "main": 4, "mode": 2, "model": [4, 7, 11, 13, 15, 16], "modifi": 2, "modul": [], "name": 13, "notebook": 10, "object": 14, "ocr": 16, "onli": [], "onnx": 15, "optim": 15, "option": 16, "orient": [], "our": 1, "output": 16, "own": [11, 14], "packag": 3, "page": 6, "perman": 1, "pipelin": [], "pledg": 1, "precis": 15, "predictor": 16, "prepar": 15, "prerequisit": 3, "pretrain": 13, "push": 13, "python": 3, "qualiti": 2, "question": 2, "read": 6, "readi": 14, "recognit": [4, 7, 13, 14, 16], "reconstitut": [], "report": 2, "request": 2, "resourc": [], "respons": 1, "return": [5, 6, 7, 9], "right": 16, "scope": 1, "share": 13, "should": 16, "stage": 16, "standard": 1, "structur": [2, 6], "style": 2, "support": [4, 5, 8], "synthet": [5, 14], "task": 9, "temporari": 1, "test": 2, "text": [4, 16], "train": 11, "transform": 8, "two": 16, "unit": 2, "us": [14, 15], "util": 9, "v0": 0, "verif": 2, "via": 3, "visual": 9, "vocab": 5, "warn": 1, "what": 16, "word": 6, "your": [11, 13, 14, 15], "zoo": [4, 7]}})
\ No newline at end of file
diff --git a/v0.8.1/searchindex.js b/v0.8.1/searchindex.js
index 668c9861cd..84be214dc3 100644
--- a/v0.8.1/searchindex.js
+++ b/v0.8.1/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"alltitles": {"1. Correction": [[1, "correction"]], "2. Warning": [[1, "warning"]], "3. Temporary Ban": [[1, "temporary-ban"]], "4. Permanent Ban": [[1, "permanent-ban"]], "AWS Lambda": [[12, null]], "Advanced options": [[16, "advanced-options"]], "Args:": [[5, "args"], [5, "id4"], [5, "id7"], [5, "id10"], [5, "id13"], [5, "id16"], [5, "id19"], [5, "id22"], [5, "id25"], [5, "id29"], [5, "id32"], [5, "id37"], [5, "id40"], [5, "id46"], [5, "id49"], [5, "id50"], [5, "id51"], [5, "id54"], [5, "id57"], [5, "id60"], [5, "id61"], [6, "args"], [6, "id2"], [6, "id3"], [6, "id4"], [6, "id5"], [6, "id6"], [6, "id7"], [6, "id10"], [6, "id12"], [6, "id14"], [6, "id16"], [6, "id20"], [6, "id24"], [6, "id28"], [7, "args"], [7, "id3"], [7, "id8"], [7, "id13"], [7, "id17"], [7, "id21"], [7, "id26"], [7, "id31"], [7, "id36"], [7, "id41"], [7, "id45"], [7, "id49"], [7, "id54"], [7, "id58"], [7, "id63"], [7, "id68"], [7, "id72"], [7, "id76"], [7, "id81"], [7, "id86"], [7, "id90"], [7, "id95"], [7, "id100"], [7, "id105"], [7, "id110"], [7, "id114"], [7, "id118"], [7, "id123"], [7, "id128"], [7, "id133"], [7, "id137"], [7, "id141"], [7, "id146"], [7, "id150"], [7, "id154"], [7, "id158"], [7, "id160"], [7, "id162"], [7, "id164"], [8, "args"], [8, "id1"], [8, "id2"], [8, "id3"], [8, "id4"], [8, "id5"], [8, "id6"], [8, "id7"], [8, "id8"], [8, "id9"], [8, "id10"], [8, "id11"], [8, "id12"], [8, "id13"], [8, "id14"], [8, "id15"], [8, "id16"], [8, "id17"], [8, "id18"], [9, "args"], [9, "id3"], [9, "id5"], [9, "id6"], [9, "id7"], [9, "id8"], [9, "id9"], [9, "id10"], [9, "id11"]], "Artefact": [[6, "artefact"]], "Attribution": [[1, "attribution"]], "Available Datasets": [[14, "available-datasets"]], "Available architectures": [[16, "available-architectures"], [16, "id1"], [16, "id2"]], "Block": [[6, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[14, null]], "Choosing the right model": [[16, null]], "Classification": [[13, "classification"]], "Code quality": [[2, "code-quality"]], "Code style verification": [[2, "code-style-verification"]], "Codebase structure": [[2, "codebase-structure"]], "Commits": [[2, "commits"]], "Composing transformations": [[8, "composing-transformations"]], "Continuous Integration": [[2, "continuous-integration"]], "Contributing to docTR": [[2, null]], "Contributor Covenant Code of Conduct": [[1, null]], "Custom dataset loader": [[5, "custom-dataset-loader"]], "Data Loading": [[14, "data-loading"]], "Dataloader": [[5, "dataloader"]], "Detection": [[13, "detection"], [14, "detection"]], "Detection predictors": [[16, "detection-predictors"]], "Developer mode installation": [[2, "developer-mode-installation"]], "Developing docTR": [[2, "developing-doctr"]], "Document": [[6, "document"]], "Document structure": [[6, "document-structure"]], "End-to-End OCR": [[16, "end-to-end-ocr"]], "Enforcement": [[1, "enforcement"]], "Enforcement Guidelines": [[1, "enforcement-guidelines"]], "Enforcement Responsibilities": [[1, "enforcement-responsibilities"]], "Export to ONNX": [[15, "export-to-onnx"]], "Feature requests & bug report": [[2, "feature-requests-bug-report"]], "Feedback": [[2, "feedback"]], "File reading": [[6, "file-reading"]], "Half-precision": [[15, "half-precision"]], "Installation": [[3, null]], "Let\u2019s connect": [[2, "let-s-connect"]], "Line": [[6, "line"]], "Loading from Huggingface Hub": [[13, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[11, "loading-your-custom-trained-model"]], "Main Features": [[4, "main-features"]], "Model optimization": [[15, "model-optimization"]], "Model zoo": [[4, "model-zoo"]], "Modifying the documentation": [[2, "modifying-the-documentation"]], "Naming conventions": [[13, "naming-conventions"]], "Object Detection": [[14, "object-detection"]], "Our Pledge": [[1, "our-pledge"]], "Our Standards": [[1, "our-standards"]], "Page": [[6, "page"]], "Preparing your model for inference": [[15, null]], "Prerequisites": [[3, "prerequisites"]], "Pretrained community models": [[13, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[13, "pushing-to-the-huggingface-hub"]], "Questions": [[2, "questions"]], "Recognition": [[13, "recognition"], [14, "recognition"]], "Recognition predictors": [[16, "recognition-predictors"]], "Returns:": [[5, "returns"], [6, "returns"], [6, "id11"], [6, "id13"], [6, "id15"], [6, "id19"], [6, "id23"], [6, "id27"], [6, "id31"], [7, "returns"], [7, "id6"], [7, "id11"], [7, "id16"], [7, "id20"], [7, "id24"], [7, "id29"], [7, "id34"], [7, "id39"], [7, "id44"], [7, "id48"], [7, "id52"], [7, "id57"], [7, "id61"], [7, "id66"], [7, "id71"], [7, "id75"], [7, "id79"], [7, "id84"], [7, "id89"], [7, "id93"], [7, "id98"], [7, "id103"], [7, "id108"], [7, "id113"], [7, "id117"], [7, "id121"], [7, "id126"], [7, "id131"], [7, "id136"], [7, "id140"], [7, "id144"], [7, "id149"], [7, "id153"], [7, "id157"], [7, "id159"], [7, "id161"], [7, "id163"], [9, "returns"], [9, "id4"]], "Scope": [[1, "scope"]], "Share your model with the community": [[13, null]], "Supported Vocabs": [[5, "supported-vocabs"]], "Supported datasets": [[4, "supported-datasets"]], "Supported transformations": [[8, "supported-transformations"]], "Synthetic dataset generator": [[5, "synthetic-dataset-generator"], [14, "synthetic-dataset-generator"]], "Task evaluation": [[9, "task-evaluation"]], "Text Detection": [[16, "text-detection"]], "Text Recognition": [[16, "text-recognition"]], "Text detection models": [[4, "text-detection-models"]], "Text recognition models": [[4, "text-recognition-models"]], "Train your own model": [[11, null]], "Two-stage approaches": [[16, "two-stage-approaches"]], "Unit tests": [[2, "unit-tests"]], "Use your own datasets": [[14, "use-your-own-datasets"]], "Using your ONNX exported model in docTR": [[15, "using-your-onnx-exported-model-in-doctr"]], "Via Conda (Only for Linux)": [[3, "via-conda-only-for-linux"]], "Via Git": [[3, "via-git"]], "Via Python Package": [[3, "via-python-package"]], "Visualization": [[9, "visualization"]], "What should I do with the output?": [[16, "what-should-i-do-with-the-output"]], "Word": [[6, "word"]], "docTR Notebooks": [[10, null]], "docTR Vocabs": [[5, "id62"]], "docTR: Document Text Recognition": [[4, null]], "doctr.datasets": [[5, null], [5, "datasets"]], "doctr.io": [[6, null]], "doctr.models": [[7, null]], "doctr.models.classification": [[7, "doctr-models-classification"]], "doctr.models.detection": [[7, "doctr-models-detection"]], "doctr.models.factory": [[7, "doctr-models-factory"]], "doctr.models.recognition": [[7, "doctr-models-recognition"]], "doctr.models.zoo": [[7, "doctr-models-zoo"]], "doctr.transforms": [[8, null]], "doctr.utils": [[9, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]]}, "docnames": ["changelog", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[6, "doctr.io.Artefact", false]], "block (class in doctr.io)": [[6, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms)": [[8, "doctr.transforms.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[5, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms)": [[8, "doctr.transforms.ColorInversion", false]], "compose (class in doctr.transforms)": [[8, "doctr.transforms.Compose", false]], "cord (class in doctr.datasets)": [[5, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[7, "doctr.models.classification.crop_orientation_predictor", false]], "dataloader (class in doctr.datasets.loader)": [[5, "doctr.datasets.loader.DataLoader", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[7, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[7, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[6, "doctr.io.decode_img_as_tensor", false]], "detection_predictor() (in module doctr.models.detection)": [[7, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[5, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[5, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[6, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[6, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[5, "doctr.datasets.encode_sequences", false]], "fast_base() (in module doctr.models.detection)": [[7, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[7, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[7, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[7, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[6, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[6, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[6, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[5, "doctr.datasets.FUNSD", false]], "gaussianblur (class in doctr.transforms)": [[8, "doctr.transforms.GaussianBlur", false]], "gaussiannoise (class in doctr.transforms)": [[8, "doctr.transforms.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[5, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[5, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[5, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[5, "doctr.datasets.IIITHWS", false]], "imgur5k (class in doctr.datasets)": [[5, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[7, "doctr.models.kie_predictor", false]], "lambdatransformation (class in doctr.transforms)": [[8, "doctr.transforms.LambdaTransformation", false]], "line (class in doctr.io)": [[6, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[7, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[7, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[7, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[7, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[7, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[5, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_orientation() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_small_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_small_r", false]], "normalize (class in doctr.transforms)": [[8, "doctr.transforms.Normalize", false]], "ocr_predictor() (in module doctr.models)": [[7, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[5, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms)": [[8, "doctr.transforms.OneOf", false]], "page (class in doctr.io)": [[6, "doctr.io.Page", false]], "parseq() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.parseq", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[7, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms)": [[8, "doctr.transforms.RandomApply", false]], "randombrightness (class in doctr.transforms)": [[8, "doctr.transforms.RandomBrightness", false]], "randomcontrast (class in doctr.transforms)": [[8, "doctr.transforms.RandomContrast", false]], "randomcrop (class in doctr.transforms)": [[8, "doctr.transforms.RandomCrop", false]], "randomgamma (class in doctr.transforms)": [[8, "doctr.transforms.RandomGamma", false]], "randomhorizontalflip (class in doctr.transforms)": [[8, "doctr.transforms.RandomHorizontalFlip", false]], "randomhue (class in doctr.transforms)": [[8, "doctr.transforms.RandomHue", false]], "randomjpegquality (class in doctr.transforms)": [[8, "doctr.transforms.RandomJpegQuality", false]], "randomrotate (class in doctr.transforms)": [[8, "doctr.transforms.RandomRotate", false]], "randomsaturation (class in doctr.transforms)": [[8, "doctr.transforms.RandomSaturation", false]], "randomshadow (class in doctr.transforms)": [[8, "doctr.transforms.RandomShadow", false]], "read_html() (in module doctr.io)": [[6, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[6, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[6, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[6, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[5, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms)": [[8, "doctr.transforms.Resize", false]], "resnet18() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet50", false]], "sar_resnet31() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[6, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[6, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[5, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[9, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[9, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[9, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[9, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[5, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[5, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.visualization)": [[9, "doctr.utils.visualization.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[5, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[7, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[7, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[7, "doctr.models.classification.textnet_tiny", false]], "togray (class in doctr.transforms)": [[8, "doctr.transforms.ToGray", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[9, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[9, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[9, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[9, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[7, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[9, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[7, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[7, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[5, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[6, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[5, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.datasets": [[5, 0, 1, "", "CORD"], [5, 0, 1, "", "CharacterGenerator"], [5, 0, 1, "", "DetectionDataset"], [5, 0, 1, "", "DocArtefacts"], [5, 0, 1, "", "FUNSD"], [5, 0, 1, "", "IC03"], [5, 0, 1, "", "IC13"], [5, 0, 1, "", "IIIT5K"], [5, 0, 1, "", "IIITHWS"], [5, 0, 1, "", "IMGUR5K"], [5, 0, 1, "", "MJSynth"], [5, 0, 1, "", "OCRDataset"], [5, 0, 1, "", "RecognitionDataset"], [5, 0, 1, "", "SROIE"], [5, 0, 1, "", "SVHN"], [5, 0, 1, "", "SVT"], [5, 0, 1, "", "SynthText"], [5, 0, 1, "", "WILDRECEIPT"], [5, 0, 1, "", "WordGenerator"], [5, 1, 1, "", "encode_sequences"]], "doctr.datasets.loader": [[5, 0, 1, "", "DataLoader"]], "doctr.io": [[6, 0, 1, "", "Artefact"], [6, 0, 1, "", "Block"], [6, 0, 1, "", "Document"], [6, 0, 1, "", "DocumentFile"], [6, 0, 1, "", "Line"], [6, 0, 1, "", "Page"], [6, 0, 1, "", "Word"], [6, 1, 1, "", "decode_img_as_tensor"], [6, 1, 1, "", "read_html"], [6, 1, 1, "", "read_img_as_numpy"], [6, 1, 1, "", "read_img_as_tensor"], [6, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[6, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[6, 2, 1, "", "from_images"], [6, 2, 1, "", "from_pdf"], [6, 2, 1, "", "from_url"]], "doctr.io.Page": [[6, 2, 1, "", "show"]], "doctr.models": [[7, 1, 1, "", "kie_predictor"], [7, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[7, 1, 1, "", "crop_orientation_predictor"], [7, 1, 1, "", "magc_resnet31"], [7, 1, 1, "", "mobilenet_v3_large"], [7, 1, 1, "", "mobilenet_v3_large_r"], [7, 1, 1, "", "mobilenet_v3_small"], [7, 1, 1, "", "mobilenet_v3_small_orientation"], [7, 1, 1, "", "mobilenet_v3_small_r"], [7, 1, 1, "", "resnet18"], [7, 1, 1, "", "resnet31"], [7, 1, 1, "", "resnet34"], [7, 1, 1, "", "resnet50"], [7, 1, 1, "", "textnet_base"], [7, 1, 1, "", "textnet_small"], [7, 1, 1, "", "textnet_tiny"], [7, 1, 1, "", "vgg16_bn_r"], [7, 1, 1, "", "vit_b"], [7, 1, 1, "", "vit_s"]], "doctr.models.detection": [[7, 1, 1, "", "db_mobilenet_v3_large"], [7, 1, 1, "", "db_resnet50"], [7, 1, 1, "", "detection_predictor"], [7, 1, 1, "", "fast_base"], [7, 1, 1, "", "fast_small"], [7, 1, 1, "", "fast_tiny"], [7, 1, 1, "", "linknet_resnet18"], [7, 1, 1, "", "linknet_resnet34"], [7, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[7, 1, 1, "", "from_hub"], [7, 1, 1, "", "login_to_hub"], [7, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[7, 1, 1, "", "crnn_mobilenet_v3_large"], [7, 1, 1, "", "crnn_mobilenet_v3_small"], [7, 1, 1, "", "crnn_vgg16_bn"], [7, 1, 1, "", "master"], [7, 1, 1, "", "parseq"], [7, 1, 1, "", "recognition_predictor"], [7, 1, 1, "", "sar_resnet31"], [7, 1, 1, "", "vitstr_base"], [7, 1, 1, "", "vitstr_small"]], "doctr.transforms": [[8, 0, 1, "", "ChannelShuffle"], [8, 0, 1, "", "ColorInversion"], [8, 0, 1, "", "Compose"], [8, 0, 1, "", "GaussianBlur"], [8, 0, 1, "", "GaussianNoise"], [8, 0, 1, "", "LambdaTransformation"], [8, 0, 1, "", "Normalize"], [8, 0, 1, "", "OneOf"], [8, 0, 1, "", "RandomApply"], [8, 0, 1, "", "RandomBrightness"], [8, 0, 1, "", "RandomContrast"], [8, 0, 1, "", "RandomCrop"], [8, 0, 1, "", "RandomGamma"], [8, 0, 1, "", "RandomHorizontalFlip"], [8, 0, 1, "", "RandomHue"], [8, 0, 1, "", "RandomJpegQuality"], [8, 0, 1, "", "RandomRotate"], [8, 0, 1, "", "RandomSaturation"], [8, 0, 1, "", "RandomShadow"], [8, 0, 1, "", "Resize"], [8, 0, 1, "", "ToGray"]], "doctr.utils.metrics": [[9, 0, 1, "", "DetectionMetric"], [9, 0, 1, "", "LocalizationConfusion"], [9, 0, 1, "", "OCRMetric"], [9, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.visualization": [[9, 1, 1, "", "synthesize_page"], [9, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [1, 6, 7, 9, 13], "0": [1, 3, 5, 8, 9, 11, 14, 16], "00": 16, "01": 16, "0123456789": 5, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 5, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 5, "02": [], "02562": 7, "03": 16, "035": 16, "0361328125": 16, "04": [], "05": 16, "06": 16, "06640625": 16, "07": 16, "08": [8, 16], "09": 16, "0966796875": 16, "1": [3, 5, 6, 7, 8, 9, 11, 14, 16], "10": [5, 9, 16], "100": [5, 8, 9, 14, 16], "1000": 16, "101": 5, "1024": [7, 9, 11, 16], "104": 5, "106": 5, "108": 5, "1095": 14, "11": 16, "110": 9, "1107": 14, "114": 5, "115": [], "1156": 14, "116": 5, "118": 5, "11800h": 16, "11th": 16, "12": [3, 16], "120": 5, "123": 5, "126": 5, "1268": 14, "128": [7, 11, 15, 16], "13": [9, 16], "130": 5, "13068": 14, "131": 5, "1337891": 14, "1357421875": 16, "1396484375": 16, "14": 16, "1420": 16, "14470v1": 5, "149": 14, "15": 16, "150": [9, 16], "1552": 16, "16": [7, 15, 16], "1630859375": 16, "1684": 16, "16x16": 7, "17": 16, "1778": 16, "1782": 16, "18": 7, "185546875": 16, "1900": 16, "1910": 7, "19342": 14, "19370": 14, "195": 5, "19598": 14, "199": 16, "1999": 16, "2": [3, 4, 5, 6, 8, 16], "20": 16, "200": 9, "2000": 14, "2003": [4, 5], "2012": 5, "2013": [4, 5], "2015": 5, "2019": 4, "2023": [], "207901": 14, "21": 16, "2103": 5, "2186": 14, "21888": 14, "22": 16, "224": [7, 8], "225": 8, "22672": 14, "229": [8, 14], "23": 16, "233": 14, "234": 5, "236": [], "24": 16, "246": 14, "249": 14, "25": 16, "2504": 16, "255": [6, 7, 8, 9, 16], "256": 7, "257": 14, "26": 16, "26032": 14, "264": 11, "27": 16, "2700": 14, "2710": 16, "2749": 11, "28": 16, "287": 11, "29": 16, "296": 11, "299": 11, "2d": 16, "3": [3, 4, 6, 7, 8, 9, 15, 16], "30": 16, "300": 14, "3000": 14, "301": 11, "30595": 16, "30ghz": 16, "31": 7, "32": [5, 7, 8, 11, 14, 15, 16], "3232421875": 16, "33": [8, 16], "33402": 14, "33608": 14, "34": [7, 16], "340": 16, "3456": 16, "35": [], "3515625": 16, "36": [], "360": 14, "37": [5, 16], "38": 16, "39": 16, "4": [7, 8, 9, 16], "40": 16, "406": 8, "41": 16, "42": 16, "43": 16, "44": 16, "45": 16, "456": 8, "46": 16, "47": 16, "472": 14, "48": [5, 16], "485": 8, "49": 16, "49377": 14, "5": [5, 8, 9, 16], "50": [7, 14, 16], "51": 16, "51171875": 16, "512": 7, "52": [5, 16], "529": 16, "53": 16, "54": 16, "540": 16, "5478515625": 16, "55": 16, "56": 16, "57": 16, "58": 16, "580": 16, "5810546875": 16, "583": 16, "59": 16, "597": 16, "5k": [4, 5], "5m": 16, "6": [8, 16], "60": 8, "600": [7, 9, 16], "61": 16, "62": 16, "626": 14, "63": 16, "64": [7, 8, 16], "641": 16, "647": 14, "65": 16, "66": 16, "67": 16, "68": 16, "69": 16, "693": 11, "694": 11, "695": 11, "6m": 16, "7": 16, "70": [9, 16], "707470": 14, "71": 16, "7100000": 14, "7141797": 14, "7149": 14, "72": 16, "72dpi": 6, "73": 16, "73257": 14, "74": 16, "75": [8, 16], "7581382": 14, "76": 16, "77": 16, "772": 11, "772875": 14, "78": 16, "785": 11, "79": 16, "793533": 14, "796": 14, "798": 11, "7m": 16, "8": [3, 7, 8, 16], "80": 16, "800": [7, 9, 14, 16], "81": 16, "82": 16, "83": 16, "84": 16, "849": 14, "85": 16, "8564453125": 16, "857": 16, "85875": 14, "86": 16, "8603515625": 16, "87": 16, "8707": 14, "88": 16, "89": 16, "9": 16, "90": 16, "90k": 5, "90kdict32px": 5, "91": 16, "914085328578949": 16, "92": 16, "93": 16, "94": [5, 16], "95": [9, 16], "9578408598899841": 16, "96": 16, "97": [], "98": 16, "99": 16, "9949972033500671": 16, "A": [1, 2, 4, 5, 6, 7, 10, 15], "As": 2, "Be": 16, "Being": 1, "By": 12, "For": [1, 2, 3, 11, 16], "If": [2, 3, 6, 7, 11, 16], "In": [2, 5, 14], "It": [8, 13, 15], "Its": [4, 7], "No": [1, 16], "Of": 5, "Or": [], "The": [1, 2, 5, 6, 9, 12, 16], "Then": 7, "To": [2, 3, 12, 13, 16], "_": [1, 5, 7], "__call__": 16, "_build": 2, "_i": 9, "ab": 5, "abc": [], "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 5, "abdef": [5, 14], "abl": [14, 16], "about": [1, 14, 16], "abov": 16, "abstract": [], "abstractdataset": 5, "abus": 1, "accept": 1, "access": [4, 6, 14, 16], "account": [1, 13], "accur": 16, "accuraci": 9, "achiev": 15, "act": 1, "action": 1, "activ": 4, "ad": [2, 7, 8], "adapt": 1, "add": [8, 9, 13, 16], "add_hook": 16, "add_label": 9, "addit": [2, 3, 6], "addition": [2, 16], "address": [1, 6], "adjust": 8, "advanc": 1, "advantag": 15, "advis": 2, "aesthet": [4, 5], "affect": 1, "after": [13, 16], "ag": 1, "again": 7, "aggreg": [9, 14], "aggress": 1, "align": [1, 6], "all": [1, 2, 5, 6, 8, 9, 14, 16], "allow": 1, "along": 16, "alreadi": 2, "also": [1, 7, 13, 14, 16], "alwai": 14, "an": [1, 2, 4, 5, 6, 7, 9, 15, 16], "analysi": 6, "ancient_greek": 5, "andrej": [], "angl": [6, 8], "ani": [1, 5, 6, 7, 8, 9, 16], "annot": 5, "anot": 14, "anoth": [3, 7, 11, 14], "answer": 1, "anyascii": [], "anyon": 4, "anyth": [], "api": [2, 4], "apolog": 1, "apologi": 1, "app": 2, "appear": 1, "appli": [1, 5, 8], "applic": [4, 7], "appoint": 1, "appreci": 13, "appropri": [1, 2, 16], "ar": [1, 2, 3, 5, 6, 8, 9, 10, 14, 16], "arab": 5, "arabic_diacrit": 5, "arabic_lett": 5, "arabic_punctu": 5, "arbitrarili": [4, 7], "arch": [7, 13], "architectur": [4, 7, 13], "area": 16, "arg": [], "argument": [5, 6, 7, 9, 16], "around": 1, "arrai": [6, 8, 9], "art": 4, "artefact": [9, 10, 16], "artefact_typ": 6, "artefactdetector": [], "articl": [], "artifici": [4, 5], "arxiv": [5, 7], "asarrai": 9, "ascii_lett": 5, "aspect": [4, 7, 8, 16], "assess": 9, "assign": 9, "associ": 6, "assum": 7, "assume_straight_pag": [7, 16], "astyp": [7, 9, 16], "attack": 1, "attend": [4, 7], "attent": [1, 7], "autom": 4, "automat": 16, "autoregress": [4, 7], "avail": [1, 4, 8], "averag": [8, 16], "avoid": [1, 3], "aw": [4, 16], "awar": 16, "azur": 16, "b": [7, 9, 16], "b_j": 9, "back": 2, "backbon": 7, "backend": 16, "background": 14, "bangla": [], "bar": [], "bar_cod": 14, "baranovskij": [], "base": [4, 7], "baselin": [4, 7, 16], "batch": [5, 7, 8, 14, 16], "batch_siz": [5, 11, 14, 15], "bblanchon": 3, "bbox": 16, "becaus": 12, "been": [2, 9, 14, 16], "befor": [5, 7, 8, 16], "begin": 9, "behavior": [1, 16], "being": [9, 16], "belong": 16, "benchmark": 16, "best": 1, "better": [10, 16], "between": [8, 9, 16], "bgr": 6, "bilinear": 8, "bin_thresh": 16, "binar": [4, 7, 16], "binari": [6, 15, 16], "bit": 15, "blank": 9, "block": [9, 16], "block_1_1": 16, "blue": 9, "blur": 8, "bmvc": 5, "bn": 13, "bodi": [1, 16], "bool": [5, 6, 7, 8, 9], "boolean": [7, 16], "both": [4, 5, 8, 14, 16], "bottom": [7, 16], "bound": [5, 6, 7, 8, 9, 16], "box": [5, 6, 7, 8, 9, 14, 16], "box_thresh": 16, "brew": 3, "bright": 8, "broadcast": 9, "browser": [2, 4], "build": [2, 3], "built": 2, "byte": [6, 16], "c": [3, 6, 9], "c_j": 9, "cach": [2, 5, 12], "cache_sampl": 5, "cairo": 3, "call": [], "callabl": [5, 8], "can": [2, 3, 11, 12, 13, 14, 16], "capabl": [2, 10, 16], "case": [5, 9], "cf": 16, "cfg": 16, "challeng": 5, "challenge2_test_task12_imag": 5, "challenge2_test_task1_gt": 5, "challenge2_training_task12_imag": 5, "challenge2_training_task1_gt": 5, "chang": 12, "channel": [1, 2, 6, 8], "channel_prior": 3, "channelshuffl": 8, "charact": [4, 5, 6, 9, 14, 16], "charactergener": [5, 14], "characterist": 1, "charg": 16, "charset": 16, "chart": 6, "check": [2, 13, 16], "checkpoint": 7, "chip": 3, "christian": [], "ci": 2, "clarifi": 1, "clariti": 1, "class": [1, 5, 6, 8, 9, 16], "class_nam": 11, "classif": 14, "classif_mobilenet_v3_smal": 7, "classmethod": 6, "clear": 2, "clone": 3, "close": 2, "co": 13, "code": [4, 6], "codecov": 2, "colab": 10, "collate_fn": 5, "collect": 6, "color": [8, 9], "colorinvers": 8, "column": 6, "com": [1, 3, 6, 7, 13], "combin": 16, "come": 15, "command": 2, "comment": 1, "commit": 1, "common": [1, 8, 9, 15], "commun": 1, "compar": 4, "comparison": [9, 16], "competit": 5, "compil": [10, 16], "complaint": 1, "complementari": 9, "complet": 2, "compon": 16, "compos": [5, 16], "comprehens": 16, "comput": [5, 9, 15, 16], "conf_threshold": [], "confid": [6, 9, 16], "config": [3, 7], "configur": 7, "confus": 9, "consecut": [8, 16], "consequ": 1, "consid": [1, 2, 5, 6, 9, 16], "consist": 16, "consolid": [4, 5], "constant": 8, "construct": 1, "consum": 9, "contact": 1, "contain": [5, 14], "content": [5, 6, 9, 16], "context": 7, "contib": [], "continu": 1, "contrast": 8, "contrast_factor": 8, "contrib": [], "contribut": 1, "contributor": 2, "convers": 6, "convert": [6, 8], "convert_target_to_rel": [], "convolut": 7, "cool": [], "coordin": [6, 16], "cord": [4, 5, 14, 16], "core": [9, 16], "corner": 16, "correct": 8, "correspond": [3, 6, 16], "could": 1, "counterpart": 9, "cover": 2, "coverag": 2, "cpu": [4, 11], "creat": 13, "crnn": [4, 7, 13], "crnn_mobilenet_v3_larg": [7, 13, 16], "crnn_mobilenet_v3_smal": [7, 15, 16], "crnn_vgg16_bn": [7, 11, 13, 16], "crop": [7, 8, 14, 16], "crop_bboxes_from_imag": [], "crop_orient": [], "crop_orientation_predictor": 7, "crop_param": [], "croporientationpredictor": 7, "cuda": 15, "currenc": 5, "current": [2, 16], "custom": [13, 16], "custom_crop_orientation_model": [], "custom_page_orientation_model": [], "customhook": 16, "cvit": 4, "czczup": 7, "czech": 5, "d": [5, 14], "danish": 5, "data": [4, 5, 6, 8, 9, 11, 13], "dataload": 14, "dataset": [7, 11, 16], "dataset_info": 5, "date": [11, 16], "db": 13, "db_mobilenet_v3_larg": [7, 13, 16], "db_resnet34": 16, "db_resnet50": [7, 11, 13, 16], "db_resnet50_rot": [], "dbnet": [4, 7], "deal": [], "decis": 1, "decod": 6, "decode_img_as_tensor": 6, "decode_sequ": [], "dedic": [], "deem": 1, "deep": [7, 16], "def": 16, "default": [3, 6, 9, 11, 12, 16], "defer": 14, "defin": [9, 15], "degre": 8, "degress": 6, "delet": 2, "delimit": 16, "delta": 8, "demo": [2, 4], "demonstr": 1, "depend": [2, 3, 4], "deploi": 2, "deploy": 4, "derogatori": 1, "describ": [7, 9], "descript": 10, "design": 8, "desir": 6, "det_arch": [7, 11, 13, 15], "det_b": [], "det_model": [11, 13], "det_param": 11, "det_predictor": [11, 16], "detail": [11, 16], "detect": [5, 9, 10, 11], "detect_languag": 7, "detect_orient": 7, "detection_predictor": [7, 16], "detection_task": [], "detectiondataset": [5, 14], "detectionmetr": 9, "detectionpredictor": [7, 11], "detector": [4, 7], "deterior": 7, "determin": 1, "dev": [2, 12], "develop": 3, "deviat": 8, "devic": 15, "dict": [6, 9, 16], "dictionari": [6, 9], "differ": 1, "differenti": [4, 7], "digit": [4, 5, 14], "dimens": [6, 9, 16], "dimension": 8, "direct": 5, "directli": [13, 16], "directori": [2, 12], "disabl": [1, 12, 16], "disable_crop_orient": [], "disable_page_orient": [], "disclaim": 16, "discuss": 2, "disparag": 1, "displai": [6, 9], "display_artefact": 9, "distribut": 8, "div": 16, "divers": 1, "divid": 6, "do": [2, 3, 7], "doc": [2, 6, 15, 16], "docartefact": [5, 14], "docstr": 2, "doctr": [3, 11, 12, 13, 14, 16], "doctr_cache_dir": 12, "doctr_multiprocessing_dis": 12, "document": [5, 7, 9, 10, 14, 16], "documentbuild": 16, "documentfil": [6, 13], "doesn": [], "don": [11, 16], "done": 8, "download": [5, 14], "download_from_url": [], "downsiz": 7, "draw": [8, 9], "draw_proba": 9, "drop": 5, "drop_last": 5, "dtype": [6, 7, 8, 9, 15], "dual": [4, 5], "dummi": 13, "dummy_img": 16, "dummy_input": 15, "dure": 1, "dutch": 5, "dynam": 5, "dynamic_seq_length": 5, "e": [1, 2, 3, 6, 7], "each": [4, 5, 6, 7, 8, 9, 14, 16], "eas": 2, "easi": [4, 9, 13], "easili": [6, 9, 11, 13, 14, 16], "econom": 1, "edit": 1, "educ": 1, "effect": [], "effici": [2, 4, 5, 7], "either": [9, 16], "element": [5, 6, 7, 9, 16], "els": 2, "email": 1, "empathi": 1, "en": 16, "enabl": [5, 6], "enclos": 6, "encod": [4, 5, 6, 7, 16], "encode_sequ": 5, "encode_str": [], "encount": 2, "encrypt": 6, "end": [4, 5, 7, 9], "english": [5, 14], "enough": [2, 16], "ensur": 2, "entri": 5, "environ": [1, 12], "eo": 5, "equiv": 16, "estim": 7, "etc": 6, "ethnic": 1, "evalu": [14, 16], "event": 1, "everyon": 1, "everyth": [2, 16], "exact": [9, 16], "exampl": [1, 2, 4, 5, 7, 13, 16], "exchang": 15, "execut": 16, "exist": 13, "expand": 8, "expect": [6, 8, 9], "experi": 1, "explan": [1, 16], "explicit": 1, "exploit": [4, 7], "export": [6, 7, 9, 10, 16], "export_as_straight_box": [7, 16], "export_as_xml": 16, "export_model_to_onnx": 15, "express": [1, 8], "extens": 6, "extern": [1, 14], "extra": 3, "extract": [4, 5], "extractor": 7, "f_": 9, "f_a": 9, "factor": 8, "fair": 1, "fairli": 1, "fals": [5, 6, 7, 8, 9, 11, 16], "famili": 9, "faq": 1, "fascan": 13, "fast": [4, 5, 7], "fast_bas": [7, 16], "fast_smal": [7, 16], "fast_tini": [7, 16], "faster": [4, 7, 15], "fasterrcnn_mobilenet_v3_large_fpn": 7, "favorit": 16, "featur": [3, 7, 9, 10], "feedback": 1, "feel": [2, 13], "felix92": 13, "few": [3, 15, 16], "figsiz": 9, "figur": 9, "file": [2, 5], "final": 7, "find": [2, 3, 14], "fine": [], "finnish": 5, "first": [2, 5], "firsthand": 5, "fit": [7, 16], "flag": 16, "flip": 8, "float": [6, 8, 9, 15], "float32": [6, 7, 8, 15], "fn": 8, "focu": 13, "focus": [1, 5], "folder": 5, "follow": [1, 2, 3, 5, 8, 9, 11, 12, 13, 16], "font": [5, 9], "font_famili": [5, 9], "font_siz": 9, "foral": 9, "forc": 2, "forg": 3, "form": [4, 5, 16], "format": [6, 9, 11, 14, 15, 16], "forpost": [4, 5], "forum": 2, "found": [], "fp16": 15, "frac": 9, "framework": [3, 13, 14, 16], "free": [1, 2, 13], "french": [5, 11, 13, 16], "friendli": 4, "from": [1, 4, 5, 6, 7, 8, 9, 10, 11, 14, 15, 16], "from_hub": [7, 13], "from_imag": [6, 13], "from_pdf": 6, "from_url": 6, "full": [5, 9, 16], "function": [5, 8, 9], "funsd": [4, 5, 14, 16], "further": 14, "futur": 5, "g": [6, 7], "g_": 9, "g_x": 9, "gallagh": [], "gamma": 8, "gaussian": 8, "gaussianblur": 8, "gaussiannois": 8, "gdk": 3, "gen": 16, "gender": 1, "gener": [2, 4, 7], "generic_cyrillic_lett": [], "geom": [], "geometri": [4, 6, 16], "geq": 9, "german": [5, 11, 13], "get": 16, "git": 13, "github": [2, 3, 7, 13], "give": 1, "given": [5, 6, 8, 9, 16], "global": 7, "go": 16, "good": 15, "googl": 2, "googlevis": 4, "gpu": [4, 15], "gracefulli": 1, "graph": [4, 5, 6], "grayscal": 8, "ground": 9, "groung": 9, "group": [4, 16], "gt": 9, "gt_box": 9, "gt_label": 9, "gtk": 3, "guid": 2, "guidanc": 14, "gvision": 16, "h": [6, 7, 8], "h_": 9, "ha": [2, 5, 9, 14], "handl": [14, 16], "handwrit": 5, "handwritten": 14, "harass": 1, "hardwar": [], "harm": 1, "hat": 9, "have": [1, 2, 9, 11, 13, 14, 16], "head": [7, 16], "healthi": 1, "hebrew": 5, "height": 6, "hello": [9, 16], "help": 15, "here": [3, 8, 10, 14, 16], "hf": 7, "hf_hub_download": 7, "high": 6, "higher": [3, 5, 16], "hindi": [], "hindi_digit": 5, "hocr": 16, "homebrew": 3, "hook": 16, "horizont": [6, 8], "hous": 5, "how": [2, 11, 13, 14], "howev": 14, "hsv": 8, "html": [1, 2, 6, 16], "http": [1, 3, 5, 6, 7, 13, 16], "hub": 7, "hue": 8, "huggingfac": 7, "hw": 5, "i": [1, 2, 5, 6, 7, 8, 9, 12, 13, 14, 15], "i7": 16, "ibrahimov": [], "ic03": [4, 5, 14], "ic13": [4, 5, 14], "icdar": [4, 5], "icdar2019": 5, "id": 16, "ident": 1, "identifi": 4, "iiit": [4, 5], "iiit5k": [5, 14], "iiithw": [4, 5, 14], "imag": [4, 5, 6, 7, 8, 9, 13, 14, 16], "imagenet": 7, "imageri": 1, "images_90k_norm": 5, "imagetensor": [], "imagetransform": [], "img": [5, 8, 14], "img_cont": 6, "img_fold": [5, 14], "img_path": 6, "img_transform": 5, "imgur5k": [4, 5, 14], "imgur5k_annot": 5, "imlist": 5, "impact": 1, "implement": [5, 6, 7, 8, 9, 16], "import": [5, 6, 7, 8, 9, 11, 13, 14, 15, 16], "improv": 7, "inappropri": 1, "incid": 1, "includ": [1, 3, 5, 14, 15], "inclus": 1, "increas": 8, "independ": [], "index": [2, 6], "indic": 9, "individu": 1, "infer": [4, 7, 8], "inform": [1, 2, 4, 5, 14], "input": [2, 6, 7, 8, 15, 16], "input_crop": 7, "input_pag": [7, 9, 16], "input_seq": [], "input_shap": 15, "input_str": [], "input_tensor": 7, "inspir": [1, 8], "instal": 13, "instanc": [1, 16], "instanti": [7, 16], "instead": [5, 6, 7], "insult": 1, "int": [5, 6, 8, 9], "int64": [8, 9], "integ": 9, "integr": [4, 13, 14], "intel": 16, "interact": [1, 6, 9], "interfac": 13, "interoper": 15, "interpol": 8, "interpret": [5, 6], "intersect": 9, "invert": 8, "investig": 1, "invis": 1, "involv": [1, 16], "io": 13, "iou": 9, "iou_thresh": 9, "iou_threshold": [], "irregular": [4, 7, 14], "isn": 5, "issu": [1, 2, 13], "italian": 5, "iter": [5, 8, 14, 16], "its": [6, 7, 8, 9, 14, 16], "itself": [7, 13], "j": 9, "jame": [], "job": 2, "join": 2, "jpeg": 8, "jpegqual": 8, "jpg": [5, 6, 13], "json": [5, 14, 16], "json_output": 16, "jump": 2, "just": 1, "kei": [4, 5], "kera": [7, 15], "kernel": [4, 7, 8], "kernel_shap": 8, "keywoard": 7, "keyword": [5, 6, 7, 9], "kie": [7, 11], "kie_predictor": [7, 11], "kiepredictor": 7, "kind": 1, "know": 2, "kwarg": [5, 6, 7, 9], "l": 9, "l_j": 9, "label": [5, 8, 9, 14], "label_fil": [5, 14], "label_fold": 5, "label_path": [5, 14], "labels_path": [5, 14], "ladder": 1, "lambda": 8, "lambdatransform": 8, "lang": 16, "languag": [1, 4, 5, 6, 7, 13, 16], "larg": [7, 13], "largest": 9, "last": [3, 5], "latenc": 7, "later": 2, "latest": [3, 16], "latin": 5, "layer": 15, "layout": 16, "lead": 1, "leader": 1, "learn": [1, 4, 7, 15, 16], "least": 3, "left": [9, 16], "legacy_french": 5, "length": [5, 16], "less": [15, 16], "level": [1, 5, 9, 16], "leverag": 10, "lf": 13, "libffi": 3, "librari": [2, 3, 10, 11], "light": 4, "lightweight": [], "like": 1, "limits_": 9, "line": [4, 7, 9, 16], "line_1_1": 16, "link": 11, "linknet": [4, 7], "linknet_resnet18": [7, 11, 16], "linknet_resnet18_rot": [], "linknet_resnet34": [7, 15, 16], "linknet_resnet50": [7, 16], "linux": [], "list": [5, 6, 8, 9, 13], "ll": 9, "load": [4, 5, 7], "load_state_dict": 11, "load_weight": 11, "loc_pr": 16, "local": [2, 4, 5, 7, 9, 14, 16], "localis": 5, "localizationconfus": 9, "locat": [2, 6, 16], "login": 7, "login_to_hub": [7, 13], "logo": [6, 14], "love": 13, "lower": [8, 9, 16], "m": [2, 9, 16], "m1": 3, "macbook": 3, "machin": 15, "maco": 3, "made": 4, "magc_resnet31": 7, "mai": [1, 2], "mail": 1, "main": 10, "maintain": 4, "mainten": 2, "make": [1, 2, 9, 12, 13, 15, 16], "mani": [14, 16], "manipul": 16, "map": [5, 7], "map_loc": 11, "mask": [], "mask_label": [], "mask_shap": 9, "master": [4, 7, 16], "match": [9, 16], "mathcal": 9, "matplotlib": [6, 9], "max": [5, 8, 9], "max_angl": 8, "max_area": 8, "max_char": [5, 14], "max_delta": 8, "max_font_s": [], "max_gain": 8, "max_gamma": 8, "max_qual": 8, "max_ratio": 8, "maximum": [5, 8], "maxval": [7, 8], "mbox": 9, "mean": [8, 9, 11], "meaniou": 9, "meant": [6, 15], "measur": 16, "media": 1, "median": 7, "meet": 11, "member": 1, "memori": [9, 12, 15], "mention": 16, "merg": 5, "messag": 2, "meta": 16, "metadata": 15, "metal": 3, "method": [6, 8, 16], "metric": [9, 16], "middl": 16, "might": [15, 16], "min": 8, "min_area": 8, "min_char": [5, 14], "min_font_s": [], "min_gain": 8, "min_gamma": 8, "min_qual": 8, "min_ratio": 8, "min_val": 8, "minde": [1, 3, 4, 7], "minim": [2, 4], "minimalist": [4, 7], "minimum": [3, 5, 8, 9, 16], "minval": 8, "miss": 3, "mistak": 1, "mixed_float16": 15, "mixed_precis": 15, "mjsynth": [4, 5, 14], "mnt": 5, "mobilenet": [7, 13], "mobilenet_v3_larg": 7, "mobilenet_v3_large_r": 7, "mobilenet_v3_smal": 7, "mobilenet_v3_small_crop_orient": [], "mobilenet_v3_small_orient": 7, "mobilenet_v3_small_page_orient": [], "mobilenet_v3_small_r": 7, "mobilenetv3": 7, "modal": [4, 5], "mode": 3, "model": [5, 9, 12, 14], "model_nam": [7, 13, 15], "model_path": 15, "moder": 1, "modif": 2, "modifi": [7, 12, 16], "modul": [6, 7, 8, 9, 16], "moment": [], "more": [2, 9, 14, 16], "moscardi": [], "most": 16, "mozilla": 1, "multi": [4, 7], "multiclass": [], "multilingu": [5, 13], "multipl": [5, 6, 8, 16], "multipli": 8, "multiprocess": 12, "my": 7, "my_awesome_model": 13, "my_hook": 16, "n": [5, 9], "name": [5, 7, 15, 16], "nation": 1, "natur": [1, 4, 5], "nb": [], "ndarrai": [5, 6, 8, 9], "necessari": [3, 11, 12], "need": [2, 3, 5, 9, 11, 12, 13, 16], "neg": 8, "nest": 16, "netraj": [], "network": [4, 5, 7, 15], "neural": [4, 5, 7, 15], "new": [2, 9], "next": [5, 14], "nois": 8, "noisi": [4, 5], "non": [4, 5, 6, 7, 8, 9], "none": [5, 6, 7, 8, 9, 16], "normal": [7, 8], "norwegian": 5, "note": [0, 2, 5, 7, 13, 15], "now": 2, "np": [7, 8, 9, 16], "num_output_channel": 8, "num_sampl": [5, 14], "num_work": 5, "number": [5, 8, 9, 16], "numpi": [6, 7, 9, 16], "o": 3, "obb": [], "obj_detect": 13, "object": [5, 9, 10, 16], "objectness_scor": [], "oblig": 1, "obtain": 16, "occupi": 15, "ocr": [4, 5, 7, 9, 13, 14], "ocr_carea": 16, "ocr_db_crnn": 9, "ocr_lin": 16, "ocr_pag": 16, "ocr_par": 16, "ocr_predictor": [7, 11, 13, 15, 16], "ocrdataset": [5, 14], "ocrmetr": 9, "ocrpredictor": [7, 11], "ocrx_word": 16, "offens": 1, "offici": [1, 7], "offlin": 1, "offset": 8, "onc": 16, "one": [2, 5, 7, 8, 11, 13, 16], "oneof": 8, "ones": [5, 8, 9], "onli": [2, 7, 8, 9, 13, 14, 15, 16], "onlin": 1, "onnx": [], "onnxruntim": [], "onnxtr": [], "opac": 8, "opacity_rang": 8, "open": [1, 2, 13, 15], "opinion": 1, "optic": [4, 16], "optim": 4, "option": [5, 7, 11], "order": [2, 5, 6, 8], "org": [1, 5, 7, 16], "organ": 6, "orient": [1, 6, 7, 16], "orientationpredictor": [], "other": [1, 2], "otherwis": [1, 6, 9], "our": [2, 7, 16], "out": [2, 7, 8, 9, 16], "out_box": [], "outpout": 16, "output": [6, 8, 15], "output_s": [6, 8], "outsid": 12, "over": [3, 5, 9, 16], "overal": [1, 7], "overlai": 6, "overview": [], "overwrit": [], "overwritten": 13, "own": 4, "p": [8, 9, 16], "packag": [2, 4, 9, 12, 14], "pad": [5, 7, 8, 16], "page": [3, 5, 7, 9, 16], "page1": 6, "page2": 6, "page_1": 16, "page_idx": [6, 16], "page_orientation_predictor": [], "page_param": [], "pair": 9, "pango": 3, "paper": 7, "par_1_1": 16, "paragraph": 16, "paragraph_break": 16, "parallel": [], "param": [8, 16], "paramet": [4, 6, 7, 15], "pars": [4, 5], "parseq": [4, 7, 13, 16], "part": [5, 8, 16], "parti": 3, "partial": 16, "particip": 1, "pass": [5, 6, 7, 16], "password": 6, "patch": [7, 9], "path": [5, 6, 14], "path_to_checkpoint": 11, "path_to_custom_model": [], "path_to_pt": 11, "patil": [], "pattern": 1, "pdf": [6, 7, 10], "pdfpage": 6, "peopl": 1, "per": [8, 16], "perform": [4, 6, 7, 8, 9, 12, 15, 16], "period": 1, "permiss": 1, "permut": [4, 7], "persian_lett": 5, "person": [1, 14], "phase": 16, "photo": 14, "physic": [1, 6], "pick": 8, "pictur": 6, "pip": [2, 3], "pipelin": 16, "pixbuf": 3, "pixel": [6, 8, 16], "pleas": 2, "plot": 9, "plt": 9, "plug": 13, "plugin": 3, "png": 6, "point": 15, "polici": 12, "polish": 5, "polit": 1, "polygon": [5, 9, 16], "pool": 7, "portugues": 5, "posit": [1, 9], "possibl": [2, 9, 13, 16], "post": [1, 16], "postprocessor": 16, "potenti": 7, "power": 4, "ppageno": 16, "pre": [2, 7], "pre_transform_multiclass": [], "precis": [9, 16], "pred": 9, "pred_box": 9, "pred_label": 9, "predefin": 14, "predict": [6, 7, 9, 16], "predictor": [4, 6, 7, 11, 13, 15], "prefer": 14, "preinstal": [], "preprocessor": [11, 16], "prerequisit": 13, "present": 10, "preserv": [7, 8, 16], "preserve_aspect_ratio": [6, 7, 8, 11, 16], "pretrain": [4, 7, 9, 11, 15, 16], "pretrained_backbon": [7, 11], "print": 16, "prior": 5, "privaci": 1, "privat": 1, "probabl": 8, "problem": 2, "procedur": 8, "process": [2, 4, 6, 11, 16], "processor": 16, "produc": [10, 16], "product": 15, "profession": 1, "project": [2, 14], "promptli": 1, "proper": 2, "properli": 5, "provid": [1, 2, 4, 13, 14, 16], "public": [1, 4], "publicli": 16, "publish": 1, "pull": 13, "punctuat": 5, "pure": 5, "purpos": 2, "push_to_hf_hub": [7, 13], "py": 13, "pypdfium2": [3, 6], "pyplot": [6, 9], "python": 2, "python3": 13, "pytorch": [3, 4, 7, 8, 11, 13, 15, 16], "q": 2, "qr": 6, "qr_code": 14, "qualiti": 8, "question": 1, "quickli": 4, "quicktour": 10, "r": 16, "race": 1, "ramdisk": 5, "rand": [7, 8, 9, 15, 16], "random": [7, 8, 9, 16], "randomappli": 8, "randombright": 8, "randomcontrast": 8, "randomcrop": 8, "randomgamma": 8, "randomhorizontalflip": 8, "randomhu": 8, "randomjpegqu": 8, "randomli": 8, "randomres": [], "randomrot": 8, "randomsatur": 8, "randomshadow": 8, "rang": 8, "rassi": 13, "ratio": [7, 8, 16], "raw": [6, 9], "re": 15, "read": [4, 5, 7], "read_html": 6, "read_img": [], "read_img_as_numpi": 6, "read_img_as_tensor": 6, "read_pdf": 6, "readi": 15, "real": [4, 7, 8], "realli": [], "reason": [1, 4, 5], "rebuild": 2, "rebuilt": 2, "recal": [9, 16], "receipt": [4, 5, 16], "reco_arch": [7, 11, 13, 15], "reco_b": [], "reco_model": [11, 13], "reco_param": 11, "reco_predictor": 11, "recogn": 16, "recognit": [5, 9, 11], "recognition_predictor": [7, 16], "recognition_task": [5, 14], "recognitiondataset": [5, 14], "recognitionpredictor": [7, 11], "rectangular": 7, "red": 9, "reduc": [3, 8], "refer": [2, 3, 11, 13, 14, 16], "regardless": 1, "region": 16, "regroup": 9, "regular": 14, "reject": 1, "rel": [6, 8, 9, 16], "relat": 6, "releas": [0, 3], "relev": [], "religion": 1, "remov": 1, "render": [6, 16], "repo": 7, "repo_id": [7, 13], "report": 1, "repositori": [5, 7, 13], "repres": [1, 9, 15, 16], "represent": [4, 7], "request": [1, 13], "requir": [3, 8], "research": 4, "residu": 7, "resiz": [8, 16], "resnet": 7, "resnet18": [7, 13], "resnet31": 7, "resnet34": 7, "resnet50": [7, 13], "resolv": 6, "resolve_block": 16, "resolve_lin": 16, "resourc": 14, "respect": 1, "respons": 9, "rest": [2, 8, 9], "restrict": 12, "result": [2, 5, 6, 10, 13, 16], "return": 16, "reusabl": 16, "review": 1, "rgb": [6, 8], "rgb_mode": 6, "rgb_output": 6, "right": [1, 7, 9], "roboflow": [], "robust": [4, 5], "root": 5, "rotat": [5, 6, 7, 8, 9, 14, 16], "run": [2, 3, 7], "same": [2, 6, 9, 14, 16], "sampl": [5, 14, 16], "sample_transform": 5, "samplecompos": [], "sanjin": [], "sar": [4, 7], "sar_resnet31": [7, 16], "satur": 8, "save": [7, 14], "scale": [6, 7, 8, 9], "scale_rang": [], "scan": [4, 5], "scene": [4, 5, 7], "score": 9, "script": [2, 14], "seamless": 4, "seamlessli": [4, 16], "search": 7, "searchabl": 10, "sec": 16, "second": 16, "section": [11, 13, 15, 16], "secur": [1, 12], "see": [1, 2], "seen": 16, "segment": [4, 7, 16], "self": 16, "semant": [4, 7], "send": 16, "sens": 9, "sensit": 14, "separ": 16, "sequenc": [4, 5, 6, 7, 9, 16], "sequenti": [8, 16], "seri": 1, "seriou": 1, "set": [1, 3, 5, 7, 9, 12, 16], "set_global_polici": 15, "sever": [6, 8, 16], "sex": 1, "sexual": 1, "shade": 8, "shape": [4, 6, 7, 8, 9, 16], "share": [12, 14], "shift": 8, "shm": 12, "should": [2, 5, 6, 8, 9], "show": [4, 6, 7, 9, 11, 13], "showcas": 2, "shuffl": [5, 8], "side": 9, "signatur": 6, "signific": 14, "simpl": [4, 7], "simpler": 7, "sinc": [5, 14], "singl": [1, 2, 4, 5], "single_img_doc": [], "size": [1, 5, 6, 8, 9, 16], "skew": 16, "slack": 2, "slightli": 7, "small": [2, 7], "smallest": 6, "smooth": [], "smoothing_factor": [], "snapshot_download": 7, "snippet": 16, "so": [2, 3, 5, 7, 13, 14], "social": 1, "socio": 1, "some": [3, 10, 13, 14], "someth": 2, "somewher": 2, "soon": 15, "sort": 1, "sourc": [5, 6, 7, 8, 9, 13], "space": [1, 16], "span": 16, "spanish": 5, "spatial": [4, 5, 6, 9], "specif": [2, 3, 9, 11, 14, 16], "specifi": [1, 5, 6], "speed": [4, 7], "sphinx": 2, "sroie": [4, 5, 14], "stabl": 3, "stackoverflow": 2, "stage": 4, "standalon": [], "standard": 8, "start": 5, "state": [4, 9], "static": 9, "statist": [], "statu": 1, "std": [8, 11], "step": 12, "still": 16, "str": [5, 6, 7, 8, 9], "straight": [5, 7, 14, 16], "straighten": [], "straighten_pag": 7, "straigten_pag": [], "stream": 6, "street": [4, 5], "strict": 3, "strictli": 9, "string": [5, 6, 9, 16], "strive": 3, "strong": [4, 7], "structur": [15, 16], "subset": [5, 16], "suggest": [2, 13], "sum": 9, "summari": 9, "support": [15, 16], "sustain": 1, "svhn": [4, 5, 14], "svt": [5, 14], "swedish": 5, "symmetr": [7, 8, 16], "symmetric_pad": [7, 8, 16], "synthes": 9, "synthesize_pag": 9, "synthet": 4, "synthtext": [4, 5, 14], "system": 16, "t": [2, 5, 11, 16], "tabl": 13, "take": [1, 5, 16], "target": [5, 6, 8, 9, 14], "target_s": 5, "task": [4, 5, 7, 13, 14, 16], "task2": 5, "team": 3, "techminde": 3, "templat": [2, 4], "tensor": [5, 6, 8, 16], "tensorflow": [3, 4, 6, 7, 8, 11, 13, 15, 16], "tensorspec": 15, "term": 1, "test": [5, 14], "test_set": 5, "text": [5, 6, 7, 9, 14], "text_output": 16, "textmatch": 9, "textnet": 7, "textnet_bas": 7, "textnet_smal": 7, "textnet_tini": 7, "textract": [4, 16], "textstylebrush": [4, 5], "textual": [4, 5, 6, 7, 16], "tf": [3, 6, 7, 8, 13, 15], "than": [2, 3, 9, 13], "thank": 2, "thei": [1, 9], "them": [3, 5, 16], "thi": [1, 2, 3, 5, 9, 11, 12, 13, 14, 15, 16], "thing": [15, 16], "third": 3, "those": [1, 3, 6, 16], "threaten": 1, "threshold": 16, "through": [1, 8, 14], "tilman": 13, "time": [1, 4, 7, 9, 14], "tini": 7, "titl": [6, 16], "tm": 16, "tmp": 12, "togeth": [2, 6], "tograi": 8, "tool": 14, "top": [9, 16], "topic": 2, "torch": [3, 8, 11, 13, 15], "torchvis": 8, "total": 11, "toward": [1, 3], "train": [2, 5, 7, 8, 13, 14, 15, 16], "train_it": [5, 14], "train_load": [5, 14], "train_pytorch": 13, "train_set": [5, 14], "train_tensorflow": 13, "trainabl": [4, 7], "tranform": 8, "transcrib": 16, "transfer": [4, 5], "transfo": 8, "transform": [4, 5, 7], "translat": 1, "troll": 1, "true": [5, 6, 7, 8, 9, 11, 12, 13, 14, 15, 16], "truth": 9, "tune": 15, "tupl": [5, 6, 8, 9], "turn": [], "two": [6, 12], "txt": 5, "type": [6, 9, 13, 15, 16], "typic": 16, "u": [1, 2], "ucsd": 5, "udac": 2, "uint8": [6, 7, 9, 16], "ukrainian": [], "unaccept": 1, "underli": [14, 16], "underneath": 6, "understand": [4, 5, 16], "unidecod": 9, "uniform": [7, 8], "uniformli": 8, "uninterrupt": [6, 16], "union": 9, "unit": [], "unittest": 2, "unknown": [], "unknown_char": [], "unlock": 6, "unoffici": 7, "unprofession": 1, "unsolicit": 1, "unsupervis": 4, "unwelcom": 1, "up": [7, 16], "updat": 9, "upgrad": 2, "upper": [5, 8], "uppercas": 14, "url": 6, "us": [1, 2, 3, 5, 7, 9, 11, 12, 13, 16], "usabl": 16, "usag": [12, 15], "use_broadcast": 9, "use_polygon": [5, 9, 14], "useabl": 16, "user": [3, 4, 6, 10], "utf": 16, "util": 15, "v1": 13, "v3": [7, 13, 16], "valid": 14, "valu": [2, 6, 8, 16], "valuabl": 4, "variabl": 12, "varieti": 5, "veri": 7, "verma": [], "version": [1, 2, 3, 15, 16], "vgg": 7, "vgg16": 13, "vgg16_bn_r": 7, "via": 1, "video": [], "vietnames": 5, "view": [4, 5], "viewpoint": 1, "violat": 1, "visibl": 1, "vision": [4, 5, 7], "visiondataset": 5, "visiontransform": 7, "visual": 4, "visualize_pag": 9, "vit_": 7, "vit_b": 7, "vitstr": [4, 7, 15], "vitstr_bas": [7, 16], "vitstr_smal": [7, 11, 15, 16], "viz": [], "vocab": [11, 13, 14, 16], "vocab_nam": [], "vocabulari": [5, 11, 13], "w": [6, 7, 8, 9], "w3": 16, "wa": 1, "wai": [1, 4, 14], "want": [2, 15, 16], "warmup": 16, "wasn": 2, "we": [1, 2, 3, 4, 6, 8, 13, 14, 15, 16], "weasyprint": 6, "web": [2, 6], "websit": 5, "weight": 11, "welcom": 1, "well": [1, 15], "were": [1, 6, 16], "what": 1, "when": [1, 2, 7], "whenev": 2, "where": [2, 6, 8, 9], "whether": [2, 5, 6, 8, 9, 14, 16], "which": [1, 7, 12, 14, 16], "whichev": 3, "while": [8, 16], "why": 1, "width": 6, "wiki": 1, "wildreceipt": [4, 5, 14], "window": [3, 7, 9], "wish": 2, "within": 1, "without": [1, 5, 7], "wonder": 2, "word": [4, 5, 7, 9, 16], "word_1_1": 16, "word_1_2": 16, "word_1_3": 16, "wordgener": [5, 14], "words_onli": 9, "work": [12, 16], "worker": 5, "workflow": 2, "worklow": 2, "world": [9, 16], "worth": 7, "wrap": 16, "wrapper": [5, 8], "write": 12, "written": [1, 6], "www": [1, 6, 16], "x": [6, 8, 9], "x_ascend": 16, "x_descend": 16, "x_i": 9, "x_size": 16, "x_wconf": 16, "xhtml": 16, "xmax": 6, "xmin": 6, "xml": 16, "xml_bytes_str": 16, "xml_element": 16, "xml_output": 16, "xmln": 16, "y": 9, "y_i": 9, "y_j": 9, "yet": [], "ymax": 6, "ymin": 6, "yolov8": [], "yolov8_artefact": [], "you": [2, 3, 5, 6, 7, 11, 12, 13, 14, 15, 16], "your": [2, 4, 6, 9, 16], "yoursit": 6, "yugesh": [], "zero": [8, 9], "zoo": [], "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 5, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 5, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 5, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 5, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 5, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": [], "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 5, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 5, "\u00e4\u00f6\u00e4\u00f6": 5, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 5, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 5, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 5, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 5, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 5, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": [], "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": [], "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": [], "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 5, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 5, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 5, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 5, "\u067e\u0686\u06a2\u06a4\u06af": 5, "\u0905": [], "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": [], "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": [], "\u0950": [], "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": [], "\u09bd": [], "\u09ce": [], "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": []}, "titles": ["Changelog", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 2, "0": 0, "01": 0, "02": 0, "03": 0, "04": [], "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 1], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 1], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": [], "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 1], "31": 0, "4": [0, 1], "5": 0, "6": 0, "7": 0, "8": 0, "9": [], "advanc": 16, "approach": 16, "architectur": 16, "arg": [5, 6, 7, 8, 9], "artefact": 6, "artefactdetect": [], "attribut": 1, "avail": [14, 16], "aw": 12, "ban": 1, "block": 6, "bug": 2, "changelog": 0, "choos": [14, 16], "classif": [7, 13], "code": [1, 2], "codebas": 2, "commit": 2, "commun": 13, "compos": 8, "conda": 3, "conduct": 1, "connect": 2, "continu": 2, "contrib": [], "contribut": 2, "contributor": 1, "convent": 13, "correct": 1, "coven": 1, "custom": [5, 11], "data": 14, "dataload": 5, "dataset": [4, 5, 14], "detect": [4, 7, 13, 14, 16], "develop": 2, "do": 16, "doctr": [2, 4, 5, 6, 7, 8, 9, 10, 15], "document": [2, 4, 6], "end": 16, "enforc": 1, "evalu": 9, "export": 15, "factori": 7, "featur": [2, 4], "feedback": 2, "file": 6, "from": 13, "gener": [5, 14], "git": 3, "guidelin": 1, "half": 15, "hub": 13, "huggingfac": 13, "i": 16, "infer": 15, "instal": [2, 3], "integr": 2, "io": 6, "lambda": 12, "let": 2, "line": 6, "linux": 3, "load": [11, 13, 14], "loader": 5, "main": 4, "mode": 2, "model": [4, 7, 11, 13, 15, 16], "modifi": 2, "modul": [], "name": 13, "notebook": 10, "object": 14, "ocr": 16, "onli": 3, "onnx": 15, "optim": 15, "option": 16, "orient": [], "our": 1, "output": 16, "own": [11, 14], "packag": 3, "page": 6, "perman": 1, "pipelin": [], "pledg": 1, "precis": 15, "predictor": 16, "prepar": 15, "prerequisit": 3, "pretrain": 13, "push": 13, "python": 3, "qualiti": 2, "question": 2, "read": 6, "readi": 14, "recognit": [4, 7, 13, 14, 16], "reconstitut": [], "report": 2, "request": 2, "resourc": [], "respons": 1, "return": [5, 6, 7, 9], "right": 16, "scope": 1, "share": 13, "should": 16, "stage": 16, "standard": 1, "structur": [2, 6], "style": 2, "support": [4, 5, 8], "synthet": [5, 14], "task": 9, "temporari": 1, "test": 2, "text": [4, 16], "train": 11, "transform": 8, "two": 16, "unit": 2, "us": [14, 15], "util": 9, "v0": 0, "verif": 2, "via": 3, "visual": 9, "vocab": 5, "warn": 1, "what": 16, "word": 6, "your": [11, 13, 14, 15], "zoo": [4, 7]}})
\ No newline at end of file
+Search.setIndex({"alltitles": {"1. Correction": [[1, "correction"]], "2. Warning": [[1, "warning"]], "3. Temporary Ban": [[1, "temporary-ban"]], "4. Permanent Ban": [[1, "permanent-ban"]], "AWS Lambda": [[12, null]], "Advanced options": [[16, "advanced-options"]], "Args:": [[5, "args"], [5, "id4"], [5, "id7"], [5, "id10"], [5, "id13"], [5, "id16"], [5, "id19"], [5, "id22"], [5, "id25"], [5, "id29"], [5, "id32"], [5, "id37"], [5, "id40"], [5, "id46"], [5, "id49"], [5, "id50"], [5, "id51"], [5, "id54"], [5, "id57"], [5, "id60"], [5, "id61"], [6, "args"], [6, "id2"], [6, "id3"], [6, "id4"], [6, "id5"], [6, "id6"], [6, "id7"], [6, "id10"], [6, "id12"], [6, "id14"], [6, "id16"], [6, "id20"], [6, "id24"], [6, "id28"], [7, "args"], [7, "id3"], [7, "id8"], [7, "id13"], [7, "id17"], [7, "id21"], [7, "id26"], [7, "id31"], [7, "id36"], [7, "id41"], [7, "id45"], [7, "id49"], [7, "id54"], [7, "id58"], [7, "id63"], [7, "id68"], [7, "id72"], [7, "id76"], [7, "id81"], [7, "id86"], [7, "id90"], [7, "id95"], [7, "id100"], [7, "id105"], [7, "id110"], [7, "id114"], [7, "id118"], [7, "id123"], [7, "id128"], [7, "id133"], [7, "id137"], [7, "id141"], [7, "id146"], [7, "id150"], [7, "id154"], [7, "id158"], [7, "id160"], [7, "id162"], [7, "id164"], [8, "args"], [8, "id1"], [8, "id2"], [8, "id3"], [8, "id4"], [8, "id5"], [8, "id6"], [8, "id7"], [8, "id8"], [8, "id9"], [8, "id10"], [8, "id11"], [8, "id12"], [8, "id13"], [8, "id14"], [8, "id15"], [8, "id16"], [8, "id17"], [8, "id18"], [9, "args"], [9, "id3"], [9, "id5"], [9, "id6"], [9, "id7"], [9, "id8"], [9, "id9"], [9, "id10"], [9, "id11"]], "Artefact": [[6, "artefact"]], "Attribution": [[1, "attribution"]], "Available Datasets": [[14, "available-datasets"]], "Available architectures": [[16, "available-architectures"], [16, "id1"], [16, "id2"]], "Block": [[6, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[14, null]], "Choosing the right model": [[16, null]], "Classification": [[13, "classification"]], "Code quality": [[2, "code-quality"]], "Code style verification": [[2, "code-style-verification"]], "Codebase structure": [[2, "codebase-structure"]], "Commits": [[2, "commits"]], "Composing transformations": [[8, "composing-transformations"]], "Continuous Integration": [[2, "continuous-integration"]], "Contributing to docTR": [[2, null]], "Contributor Covenant Code of Conduct": [[1, null]], "Custom dataset loader": [[5, "custom-dataset-loader"]], "Data Loading": [[14, "data-loading"]], "Dataloader": [[5, "dataloader"]], "Detection": [[13, "detection"], [14, "detection"]], "Detection predictors": [[16, "detection-predictors"]], "Developer mode installation": [[2, "developer-mode-installation"]], "Developing docTR": [[2, "developing-doctr"]], "Document": [[6, "document"]], "Document structure": [[6, "document-structure"]], "End-to-End OCR": [[16, "end-to-end-ocr"]], "Enforcement": [[1, "enforcement"]], "Enforcement Guidelines": [[1, "enforcement-guidelines"]], "Enforcement Responsibilities": [[1, "enforcement-responsibilities"]], "Export to ONNX": [[15, "export-to-onnx"]], "Feature requests & bug report": [[2, "feature-requests-bug-report"]], "Feedback": [[2, "feedback"]], "File reading": [[6, "file-reading"]], "Half-precision": [[15, "half-precision"]], "Installation": [[3, null]], "Let\u2019s connect": [[2, "let-s-connect"]], "Line": [[6, "line"]], "Loading from Huggingface Hub": [[13, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[11, "loading-your-custom-trained-model"]], "Main Features": [[4, "main-features"]], "Model optimization": [[15, "model-optimization"]], "Model zoo": [[4, "model-zoo"]], "Modifying the documentation": [[2, "modifying-the-documentation"]], "Naming conventions": [[13, "naming-conventions"]], "Object Detection": [[14, "object-detection"]], "Our Pledge": [[1, "our-pledge"]], "Our Standards": [[1, "our-standards"]], "Page": [[6, "page"]], "Preparing your model for inference": [[15, null]], "Prerequisites": [[3, "prerequisites"]], "Pretrained community models": [[13, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[13, "pushing-to-the-huggingface-hub"]], "Questions": [[2, "questions"]], "Recognition": [[13, "recognition"], [14, "recognition"]], "Recognition predictors": [[16, "recognition-predictors"]], "Returns:": [[5, "returns"], [6, "returns"], [6, "id11"], [6, "id13"], [6, "id15"], [6, "id19"], [6, "id23"], [6, "id27"], [6, "id31"], [7, "returns"], [7, "id6"], [7, "id11"], [7, "id16"], [7, "id20"], [7, "id24"], [7, "id29"], [7, "id34"], [7, "id39"], [7, "id44"], [7, "id48"], [7, "id52"], [7, "id57"], [7, "id61"], [7, "id66"], [7, "id71"], [7, "id75"], [7, "id79"], [7, "id84"], [7, "id89"], [7, "id93"], [7, "id98"], [7, "id103"], [7, "id108"], [7, "id113"], [7, "id117"], [7, "id121"], [7, "id126"], [7, "id131"], [7, "id136"], [7, "id140"], [7, "id144"], [7, "id149"], [7, "id153"], [7, "id157"], [7, "id159"], [7, "id161"], [7, "id163"], [9, "returns"], [9, "id4"]], "Scope": [[1, "scope"]], "Share your model with the community": [[13, null]], "Supported Vocabs": [[5, "supported-vocabs"]], "Supported datasets": [[4, "supported-datasets"]], "Supported transformations": [[8, "supported-transformations"]], "Synthetic dataset generator": [[5, "synthetic-dataset-generator"], [14, "synthetic-dataset-generator"]], "Task evaluation": [[9, "task-evaluation"]], "Text Detection": [[16, "text-detection"]], "Text Recognition": [[16, "text-recognition"]], "Text detection models": [[4, "text-detection-models"]], "Text recognition models": [[4, "text-recognition-models"]], "Train your own model": [[11, null]], "Two-stage approaches": [[16, "two-stage-approaches"]], "Unit tests": [[2, "unit-tests"]], "Use your own datasets": [[14, "use-your-own-datasets"]], "Using your ONNX exported model in docTR": [[15, "using-your-onnx-exported-model-in-doctr"]], "Via Conda (Only for Linux)": [[3, "via-conda-only-for-linux"]], "Via Git": [[3, "via-git"]], "Via Python Package": [[3, "via-python-package"]], "Visualization": [[9, "visualization"]], "What should I do with the output?": [[16, "what-should-i-do-with-the-output"]], "Word": [[6, "word"]], "docTR Notebooks": [[10, null]], "docTR Vocabs": [[5, "id62"]], "docTR: Document Text Recognition": [[4, null]], "doctr.datasets": [[5, null], [5, "datasets"]], "doctr.io": [[6, null]], "doctr.models": [[7, null]], "doctr.models.classification": [[7, "doctr-models-classification"]], "doctr.models.detection": [[7, "doctr-models-detection"]], "doctr.models.factory": [[7, "doctr-models-factory"]], "doctr.models.recognition": [[7, "doctr-models-recognition"]], "doctr.models.zoo": [[7, "doctr-models-zoo"]], "doctr.transforms": [[8, null]], "doctr.utils": [[9, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]]}, "docnames": ["changelog", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[6, "doctr.io.Artefact", false]], "block (class in doctr.io)": [[6, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms)": [[8, "doctr.transforms.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[5, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms)": [[8, "doctr.transforms.ColorInversion", false]], "compose (class in doctr.transforms)": [[8, "doctr.transforms.Compose", false]], "cord (class in doctr.datasets)": [[5, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[7, "doctr.models.classification.crop_orientation_predictor", false]], "dataloader (class in doctr.datasets.loader)": [[5, "doctr.datasets.loader.DataLoader", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[7, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[7, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[6, "doctr.io.decode_img_as_tensor", false]], "detection_predictor() (in module doctr.models.detection)": [[7, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[5, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[5, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[6, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[6, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[5, "doctr.datasets.encode_sequences", false]], "fast_base() (in module doctr.models.detection)": [[7, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[7, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[7, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[7, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[6, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[6, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[6, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[5, "doctr.datasets.FUNSD", false]], "gaussianblur (class in doctr.transforms)": [[8, "doctr.transforms.GaussianBlur", false]], "gaussiannoise (class in doctr.transforms)": [[8, "doctr.transforms.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[5, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[5, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[5, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[5, "doctr.datasets.IIITHWS", false]], "imgur5k (class in doctr.datasets)": [[5, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[7, "doctr.models.kie_predictor", false]], "lambdatransformation (class in doctr.transforms)": [[8, "doctr.transforms.LambdaTransformation", false]], "line (class in doctr.io)": [[6, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[7, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[7, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[7, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[7, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[7, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[5, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_orientation() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_small_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[7, "doctr.models.classification.mobilenet_v3_small_r", false]], "normalize (class in doctr.transforms)": [[8, "doctr.transforms.Normalize", false]], "ocr_predictor() (in module doctr.models)": [[7, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[5, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms)": [[8, "doctr.transforms.OneOf", false]], "page (class in doctr.io)": [[6, "doctr.io.Page", false]], "parseq() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.parseq", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[7, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms)": [[8, "doctr.transforms.RandomApply", false]], "randombrightness (class in doctr.transforms)": [[8, "doctr.transforms.RandomBrightness", false]], "randomcontrast (class in doctr.transforms)": [[8, "doctr.transforms.RandomContrast", false]], "randomcrop (class in doctr.transforms)": [[8, "doctr.transforms.RandomCrop", false]], "randomgamma (class in doctr.transforms)": [[8, "doctr.transforms.RandomGamma", false]], "randomhorizontalflip (class in doctr.transforms)": [[8, "doctr.transforms.RandomHorizontalFlip", false]], "randomhue (class in doctr.transforms)": [[8, "doctr.transforms.RandomHue", false]], "randomjpegquality (class in doctr.transforms)": [[8, "doctr.transforms.RandomJpegQuality", false]], "randomrotate (class in doctr.transforms)": [[8, "doctr.transforms.RandomRotate", false]], "randomsaturation (class in doctr.transforms)": [[8, "doctr.transforms.RandomSaturation", false]], "randomshadow (class in doctr.transforms)": [[8, "doctr.transforms.RandomShadow", false]], "read_html() (in module doctr.io)": [[6, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[6, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[6, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[6, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[5, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms)": [[8, "doctr.transforms.Resize", false]], "resnet18() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[7, "doctr.models.classification.resnet50", false]], "sar_resnet31() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[6, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[6, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[5, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[9, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[9, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[9, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[9, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[5, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[5, "doctr.datasets.SVT", false]], "synthesize_page() (in module doctr.utils.visualization)": [[9, "doctr.utils.visualization.synthesize_page", false]], "synthtext (class in doctr.datasets)": [[5, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[9, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[7, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[7, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[7, "doctr.models.classification.textnet_tiny", false]], "togray (class in doctr.transforms)": [[8, "doctr.transforms.ToGray", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[9, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[9, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[9, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[9, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[7, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[9, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[7, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[7, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[7, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[5, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[6, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[5, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.datasets": [[5, 0, 1, "", "CORD"], [5, 0, 1, "", "CharacterGenerator"], [5, 0, 1, "", "DetectionDataset"], [5, 0, 1, "", "DocArtefacts"], [5, 0, 1, "", "FUNSD"], [5, 0, 1, "", "IC03"], [5, 0, 1, "", "IC13"], [5, 0, 1, "", "IIIT5K"], [5, 0, 1, "", "IIITHWS"], [5, 0, 1, "", "IMGUR5K"], [5, 0, 1, "", "MJSynth"], [5, 0, 1, "", "OCRDataset"], [5, 0, 1, "", "RecognitionDataset"], [5, 0, 1, "", "SROIE"], [5, 0, 1, "", "SVHN"], [5, 0, 1, "", "SVT"], [5, 0, 1, "", "SynthText"], [5, 0, 1, "", "WILDRECEIPT"], [5, 0, 1, "", "WordGenerator"], [5, 1, 1, "", "encode_sequences"]], "doctr.datasets.loader": [[5, 0, 1, "", "DataLoader"]], "doctr.io": [[6, 0, 1, "", "Artefact"], [6, 0, 1, "", "Block"], [6, 0, 1, "", "Document"], [6, 0, 1, "", "DocumentFile"], [6, 0, 1, "", "Line"], [6, 0, 1, "", "Page"], [6, 0, 1, "", "Word"], [6, 1, 1, "", "decode_img_as_tensor"], [6, 1, 1, "", "read_html"], [6, 1, 1, "", "read_img_as_numpy"], [6, 1, 1, "", "read_img_as_tensor"], [6, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[6, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[6, 2, 1, "", "from_images"], [6, 2, 1, "", "from_pdf"], [6, 2, 1, "", "from_url"]], "doctr.io.Page": [[6, 2, 1, "", "show"]], "doctr.models": [[7, 1, 1, "", "kie_predictor"], [7, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[7, 1, 1, "", "crop_orientation_predictor"], [7, 1, 1, "", "magc_resnet31"], [7, 1, 1, "", "mobilenet_v3_large"], [7, 1, 1, "", "mobilenet_v3_large_r"], [7, 1, 1, "", "mobilenet_v3_small"], [7, 1, 1, "", "mobilenet_v3_small_orientation"], [7, 1, 1, "", "mobilenet_v3_small_r"], [7, 1, 1, "", "resnet18"], [7, 1, 1, "", "resnet31"], [7, 1, 1, "", "resnet34"], [7, 1, 1, "", "resnet50"], [7, 1, 1, "", "textnet_base"], [7, 1, 1, "", "textnet_small"], [7, 1, 1, "", "textnet_tiny"], [7, 1, 1, "", "vgg16_bn_r"], [7, 1, 1, "", "vit_b"], [7, 1, 1, "", "vit_s"]], "doctr.models.detection": [[7, 1, 1, "", "db_mobilenet_v3_large"], [7, 1, 1, "", "db_resnet50"], [7, 1, 1, "", "detection_predictor"], [7, 1, 1, "", "fast_base"], [7, 1, 1, "", "fast_small"], [7, 1, 1, "", "fast_tiny"], [7, 1, 1, "", "linknet_resnet18"], [7, 1, 1, "", "linknet_resnet34"], [7, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[7, 1, 1, "", "from_hub"], [7, 1, 1, "", "login_to_hub"], [7, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[7, 1, 1, "", "crnn_mobilenet_v3_large"], [7, 1, 1, "", "crnn_mobilenet_v3_small"], [7, 1, 1, "", "crnn_vgg16_bn"], [7, 1, 1, "", "master"], [7, 1, 1, "", "parseq"], [7, 1, 1, "", "recognition_predictor"], [7, 1, 1, "", "sar_resnet31"], [7, 1, 1, "", "vitstr_base"], [7, 1, 1, "", "vitstr_small"]], "doctr.transforms": [[8, 0, 1, "", "ChannelShuffle"], [8, 0, 1, "", "ColorInversion"], [8, 0, 1, "", "Compose"], [8, 0, 1, "", "GaussianBlur"], [8, 0, 1, "", "GaussianNoise"], [8, 0, 1, "", "LambdaTransformation"], [8, 0, 1, "", "Normalize"], [8, 0, 1, "", "OneOf"], [8, 0, 1, "", "RandomApply"], [8, 0, 1, "", "RandomBrightness"], [8, 0, 1, "", "RandomContrast"], [8, 0, 1, "", "RandomCrop"], [8, 0, 1, "", "RandomGamma"], [8, 0, 1, "", "RandomHorizontalFlip"], [8, 0, 1, "", "RandomHue"], [8, 0, 1, "", "RandomJpegQuality"], [8, 0, 1, "", "RandomRotate"], [8, 0, 1, "", "RandomSaturation"], [8, 0, 1, "", "RandomShadow"], [8, 0, 1, "", "Resize"], [8, 0, 1, "", "ToGray"]], "doctr.utils.metrics": [[9, 0, 1, "", "DetectionMetric"], [9, 0, 1, "", "LocalizationConfusion"], [9, 0, 1, "", "OCRMetric"], [9, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[9, 2, 1, "", "summary"], [9, 2, 1, "", "update"]], "doctr.utils.visualization": [[9, 1, 1, "", "synthesize_page"], [9, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [1, 6, 7, 9, 13], "0": [1, 3, 5, 8, 9, 11, 14, 16], "00": 16, "01": 16, "0123456789": 5, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 5, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 5, "02": [], "02562": 7, "03": 16, "035": 16, "0361328125": 16, "04": [], "05": 16, "06": 16, "06640625": 16, "07": 16, "08": [8, 16], "09": 16, "0966796875": 16, "1": [3, 5, 6, 7, 8, 9, 11, 14, 16], "10": [5, 9, 16], "100": [5, 8, 9, 14, 16], "1000": 16, "101": 5, "1024": [7, 9, 11, 16], "104": 5, "106": 5, "108": 5, "1095": 14, "11": 16, "110": 9, "1107": 14, "114": 5, "115": [], "1156": 14, "116": 5, "118": 5, "11800h": 16, "11th": 16, "12": [3, 16], "120": 5, "123": 5, "126": 5, "1268": 14, "128": [7, 11, 15, 16], "13": [9, 16], "130": 5, "13068": 14, "131": 5, "1337891": 14, "1357421875": 16, "1396484375": 16, "14": 16, "1420": 16, "14470v1": 5, "149": 14, "15": 16, "150": [9, 16], "1552": 16, "16": [7, 15, 16], "1630859375": 16, "1684": 16, "16x16": 7, "17": 16, "1778": 16, "1782": 16, "18": 7, "185546875": 16, "1900": 16, "1910": 7, "19342": 14, "19370": 14, "195": 5, "19598": 14, "199": 16, "1999": 16, "2": [3, 4, 5, 6, 8, 16], "20": 16, "200": 9, "2000": 14, "2003": [4, 5], "2012": 5, "2013": [4, 5], "2015": 5, "2019": 4, "2023": [], "207901": 14, "21": 16, "2103": 5, "2186": 14, "21888": 14, "22": 16, "224": [7, 8], "225": 8, "22672": 14, "229": [8, 14], "23": 16, "233": 14, "234": 5, "236": [], "24": 16, "246": 14, "249": 14, "25": 16, "2504": 16, "255": [6, 7, 8, 9, 16], "256": 7, "257": 14, "26": 16, "26032": 14, "264": 11, "27": 16, "2700": 14, "2710": 16, "2749": 11, "28": 16, "287": 11, "29": 16, "296": 11, "299": 11, "2d": 16, "3": [3, 4, 6, 7, 8, 9, 15, 16], "30": 16, "300": 14, "3000": 14, "301": 11, "30595": 16, "30ghz": 16, "31": 7, "32": [5, 7, 8, 11, 14, 15, 16], "3232421875": 16, "33": [8, 16], "33402": 14, "33608": 14, "34": [7, 16], "340": 16, "3456": 16, "35": [], "3515625": 16, "36": [], "360": 14, "37": [5, 16], "38": 16, "39": 16, "4": [7, 8, 9, 16], "40": 16, "406": 8, "41": 16, "42": 16, "43": 16, "44": 16, "45": 16, "456": 8, "46": 16, "47": 16, "472": 14, "48": [5, 16], "485": 8, "49": 16, "49377": 14, "5": [5, 8, 9, 16], "50": [7, 14, 16], "51": 16, "51171875": 16, "512": 7, "52": [5, 16], "529": 16, "53": 16, "54": 16, "540": 16, "5478515625": 16, "55": 16, "56": 16, "57": 16, "58": 16, "580": 16, "5810546875": 16, "583": 16, "59": 16, "597": 16, "5k": [4, 5], "5m": 16, "6": [8, 16], "60": 8, "600": [7, 9, 16], "61": 16, "62": 16, "626": 14, "63": 16, "64": [7, 8, 16], "641": 16, "647": 14, "65": 16, "66": 16, "67": 16, "68": 16, "69": 16, "693": 11, "694": 11, "695": 11, "6m": 16, "7": 16, "70": [9, 16], "707470": 14, "71": 16, "7100000": 14, "7141797": 14, "7149": 14, "72": 16, "72dpi": 6, "73": 16, "73257": 14, "74": 16, "75": [8, 16], "7581382": 14, "76": 16, "77": 16, "772": 11, "772875": 14, "78": 16, "785": 11, "79": 16, "793533": 14, "796": 14, "798": 11, "7m": 16, "8": [3, 7, 8, 16], "80": 16, "800": [7, 9, 14, 16], "81": 16, "82": 16, "83": 16, "84": 16, "849": 14, "85": 16, "8564453125": 16, "857": 16, "85875": 14, "86": 16, "8603515625": 16, "87": 16, "8707": 14, "88": 16, "89": 16, "9": 16, "90": 16, "90k": 5, "90kdict32px": 5, "91": 16, "914085328578949": 16, "92": 16, "93": 16, "94": [5, 16], "95": [9, 16], "9578408598899841": 16, "96": 16, "97": [], "98": 16, "99": 16, "9949972033500671": 16, "A": [1, 2, 4, 5, 6, 7, 10, 15], "As": 2, "Be": 16, "Being": 1, "By": 12, "For": [1, 2, 3, 11, 16], "If": [2, 3, 6, 7, 11, 16], "In": [2, 5, 14], "It": [8, 13, 15], "Its": [4, 7], "No": [1, 16], "Of": 5, "Or": [], "The": [1, 2, 5, 6, 9, 12, 16], "Then": 7, "To": [2, 3, 12, 13, 16], "_": [1, 5, 7], "__call__": 16, "_build": 2, "_i": 9, "ab": 5, "abc": [], "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 5, "abdef": [5, 14], "abl": [14, 16], "about": [1, 14, 16], "abov": 16, "abstract": [], "abstractdataset": 5, "abus": 1, "accept": 1, "access": [4, 6, 14, 16], "account": [1, 13], "accur": 16, "accuraci": 9, "achiev": 15, "act": 1, "action": 1, "activ": 4, "ad": [2, 7, 8], "adapt": 1, "add": [8, 9, 13, 16], "add_hook": 16, "add_label": 9, "addit": [2, 3, 6], "addition": [2, 16], "address": [1, 6], "adjust": 8, "advanc": 1, "advantag": 15, "advis": 2, "aesthet": [4, 5], "affect": 1, "after": [13, 16], "ag": 1, "again": 7, "aggreg": [9, 14], "aggress": 1, "align": [1, 6], "all": [1, 2, 5, 6, 8, 9, 14, 16], "allow": 1, "along": 16, "alreadi": 2, "also": [1, 7, 13, 14, 16], "alwai": 14, "an": [1, 2, 4, 5, 6, 7, 9, 15, 16], "analysi": 6, "ancient_greek": 5, "andrej": [], "angl": [6, 8], "ani": [1, 5, 6, 7, 8, 9, 16], "annot": 5, "anot": 14, "anoth": [3, 7, 11, 14], "answer": 1, "anyascii": [], "anyon": 4, "anyth": [], "api": [2, 4], "apolog": 1, "apologi": 1, "app": 2, "appear": 1, "appli": [1, 5, 8], "applic": [4, 7], "appoint": 1, "appreci": 13, "appropri": [1, 2, 16], "ar": [1, 2, 3, 5, 6, 8, 9, 10, 14, 16], "arab": 5, "arabic_diacrit": 5, "arabic_lett": 5, "arabic_punctu": 5, "arbitrarili": [4, 7], "arch": [7, 13], "architectur": [4, 7, 13], "area": 16, "arg": [], "argument": [5, 6, 7, 9, 16], "around": 1, "arrai": [6, 8, 9], "art": 4, "artefact": [9, 10, 16], "artefact_typ": 6, "artefactdetector": [], "articl": [], "artifici": [4, 5], "arxiv": [5, 7], "asarrai": 9, "ascii_lett": 5, "aspect": [4, 7, 8, 16], "assess": 9, "assign": 9, "associ": 6, "assum": 7, "assume_straight_pag": [7, 16], "astyp": [7, 9, 16], "attack": 1, "attend": [4, 7], "attent": [1, 7], "autom": 4, "automat": 16, "autoregress": [4, 7], "avail": [1, 4, 8], "averag": [8, 16], "avoid": [1, 3], "aw": [4, 16], "awar": 16, "azur": 16, "b": [7, 9, 16], "b_j": 9, "back": 2, "backbon": 7, "backend": 16, "background": 14, "bangla": [], "bar": [], "bar_cod": 14, "baranovskij": [], "base": [4, 7], "baselin": [4, 7, 16], "batch": [5, 7, 8, 14, 16], "batch_siz": [5, 11, 14, 15], "bblanchon": 3, "bbox": 16, "becaus": 12, "been": [2, 9, 14, 16], "befor": [5, 7, 8, 16], "begin": 9, "behavior": [1, 16], "being": [9, 16], "belong": 16, "benchmark": 16, "best": 1, "better": [10, 16], "between": [8, 9, 16], "bgr": 6, "bilinear": 8, "bin_thresh": 16, "binar": [4, 7, 16], "binari": [6, 15, 16], "bit": 15, "blank": 9, "block": [9, 16], "block_1_1": 16, "blue": 9, "blur": 8, "bmvc": 5, "bn": 13, "bodi": [1, 16], "bool": [5, 6, 7, 8, 9], "boolean": [7, 16], "both": [4, 5, 8, 14, 16], "bottom": [7, 16], "bound": [5, 6, 7, 8, 9, 16], "box": [5, 6, 7, 8, 9, 14, 16], "box_thresh": 16, "brew": 3, "bright": 8, "broadcast": 9, "browser": [2, 4], "build": [2, 3], "built": 2, "byte": [6, 16], "c": [3, 6, 9], "c_j": 9, "cach": [2, 5, 12], "cache_sampl": 5, "cairo": 3, "call": [], "callabl": [5, 8], "can": [2, 3, 11, 12, 13, 14, 16], "capabl": [2, 10, 16], "case": [5, 9], "cf": 16, "cfg": 16, "challeng": 5, "challenge2_test_task12_imag": 5, "challenge2_test_task1_gt": 5, "challenge2_training_task12_imag": 5, "challenge2_training_task1_gt": 5, "chang": 12, "channel": [1, 2, 6, 8], "channel_prior": 3, "channelshuffl": 8, "charact": [4, 5, 6, 9, 14, 16], "charactergener": [5, 14], "characterist": 1, "charg": 16, "charset": 16, "chart": 6, "check": [2, 13, 16], "checkpoint": 7, "chip": 3, "christian": [], "ci": 2, "clarifi": 1, "clariti": 1, "class": [1, 5, 6, 8, 9, 16], "class_nam": 11, "classif": 14, "classif_mobilenet_v3_smal": 7, "classmethod": 6, "clear": 2, "clone": 3, "close": 2, "co": 13, "code": [4, 6], "codecov": 2, "colab": 10, "collate_fn": 5, "collect": 6, "color": [8, 9], "colorinvers": 8, "column": 6, "com": [1, 3, 6, 7, 13], "combin": 16, "come": 15, "command": 2, "comment": 1, "commit": 1, "common": [1, 8, 9, 15], "commun": 1, "compar": 4, "comparison": [9, 16], "competit": 5, "compil": [10, 16], "complaint": 1, "complementari": 9, "complet": 2, "compon": 16, "compos": [5, 16], "comprehens": 16, "comput": [5, 9, 15, 16], "conf_threshold": [], "confid": [6, 9, 16], "config": [3, 7], "configur": 7, "confus": 9, "consecut": [8, 16], "consequ": 1, "consid": [1, 2, 5, 6, 9, 16], "consist": 16, "consolid": [4, 5], "constant": 8, "construct": 1, "consum": 9, "contact": 1, "contain": [5, 14], "content": [5, 6, 9, 16], "context": 7, "contib": [], "continu": 1, "contrast": 8, "contrast_factor": 8, "contrib": [], "contribut": 1, "contributor": 2, "convers": 6, "convert": [6, 8], "convert_target_to_rel": [], "convolut": 7, "cool": [], "coordin": [6, 16], "cord": [4, 5, 14, 16], "core": [9, 16], "corner": 16, "correct": 8, "correspond": [3, 6, 16], "could": 1, "counterpart": 9, "cover": 2, "coverag": 2, "cpu": [4, 11], "creat": 13, "crnn": [4, 7, 13], "crnn_mobilenet_v3_larg": [7, 13, 16], "crnn_mobilenet_v3_smal": [7, 15, 16], "crnn_vgg16_bn": [7, 11, 13, 16], "crop": [7, 8, 14, 16], "crop_bboxes_from_imag": [], "crop_orient": [], "crop_orientation_predictor": 7, "crop_param": [], "croporientationpredictor": 7, "cuda": 15, "currenc": 5, "current": [2, 16], "custom": [13, 16], "custom_crop_orientation_model": [], "custom_page_orientation_model": [], "customhook": 16, "cvit": 4, "czczup": 7, "czech": 5, "d": [5, 14], "danish": 5, "data": [4, 5, 6, 8, 9, 11, 13], "dataload": 14, "dataset": [7, 11, 16], "dataset_info": 5, "date": [11, 16], "db": 13, "db_mobilenet_v3_larg": [7, 13, 16], "db_resnet34": 16, "db_resnet50": [7, 11, 13, 16], "db_resnet50_rot": [], "dbnet": [4, 7], "deal": [], "decis": 1, "decod": 6, "decode_img_as_tensor": 6, "decode_sequ": [], "dedic": [], "deem": 1, "deep": [7, 16], "def": 16, "default": [3, 6, 9, 11, 12, 16], "defer": 14, "defin": [9, 15], "degre": 8, "degress": 6, "delet": 2, "delimit": 16, "delta": 8, "demo": [2, 4], "demonstr": 1, "depend": [2, 3, 4], "deploi": 2, "deploy": 4, "derogatori": 1, "describ": [7, 9], "descript": 10, "design": 8, "desir": 6, "det_arch": [7, 11, 13, 15], "det_b": [], "det_model": [11, 13], "det_param": 11, "det_predictor": [11, 16], "detail": [11, 16], "detect": [5, 9, 10, 11], "detect_languag": 7, "detect_orient": 7, "detection_predictor": [7, 16], "detection_task": [], "detectiondataset": [5, 14], "detectionmetr": 9, "detectionpredictor": [7, 11], "detector": [4, 7], "deterior": 7, "determin": 1, "dev": [2, 12], "develop": 3, "deviat": 8, "devic": 15, "dict": [6, 9, 16], "dictionari": [6, 9], "differ": 1, "differenti": [4, 7], "digit": [4, 5, 14], "dimens": [6, 9, 16], "dimension": 8, "direct": 5, "directli": [13, 16], "directori": [2, 12], "disabl": [1, 12, 16], "disable_crop_orient": [], "disable_page_orient": [], "disclaim": 16, "discuss": 2, "disparag": 1, "displai": [6, 9], "display_artefact": 9, "distribut": 8, "div": 16, "divers": 1, "divid": 6, "do": [2, 3, 7], "doc": [2, 6, 15, 16], "docartefact": [5, 14], "docstr": 2, "doctr": [3, 11, 12, 13, 14, 16], "doctr_cache_dir": 12, "doctr_multiprocessing_dis": 12, "document": [5, 7, 9, 10, 14, 16], "documentbuild": 16, "documentfil": [6, 13], "doesn": [], "don": [11, 16], "done": 8, "download": [5, 14], "download_from_url": [], "downsiz": 7, "draw": [8, 9], "draw_proba": 9, "drop": 5, "drop_last": 5, "dtype": [6, 7, 8, 9, 15], "dual": [4, 5], "dummi": 13, "dummy_img": 16, "dummy_input": 15, "dure": 1, "dutch": 5, "dynam": 5, "dynamic_seq_length": 5, "e": [1, 2, 3, 6, 7], "each": [4, 5, 6, 7, 8, 9, 14, 16], "eas": 2, "easi": [4, 9, 13], "easili": [6, 9, 11, 13, 14, 16], "econom": 1, "edit": 1, "educ": 1, "effect": [], "effici": [2, 4, 5, 7], "either": [9, 16], "element": [5, 6, 7, 9, 16], "els": 2, "email": 1, "empathi": 1, "en": 16, "enabl": [5, 6], "enclos": 6, "encod": [4, 5, 6, 7, 16], "encode_sequ": 5, "encode_str": [], "encount": 2, "encrypt": 6, "end": [4, 5, 7, 9], "english": [5, 14], "enough": [2, 16], "ensur": 2, "entri": 5, "environ": [1, 12], "eo": 5, "equiv": 16, "estim": 7, "etc": 6, "ethnic": 1, "evalu": [14, 16], "event": 1, "everyon": 1, "everyth": [2, 16], "exact": [9, 16], "exampl": [1, 2, 4, 5, 7, 13, 16], "exchang": 15, "execut": 16, "exist": 13, "expand": 8, "expect": [6, 8, 9], "experi": 1, "explan": [1, 16], "explicit": 1, "exploit": [4, 7], "export": [6, 7, 9, 10, 16], "export_as_straight_box": [7, 16], "export_as_xml": 16, "export_model_to_onnx": 15, "express": [1, 8], "extens": 6, "extern": [1, 14], "extra": 3, "extract": [4, 5], "extractor": 7, "f_": 9, "f_a": 9, "factor": 8, "fair": 1, "fairli": 1, "fals": [5, 6, 7, 8, 9, 11, 16], "famili": 9, "faq": 1, "fascan": 13, "fast": [4, 5, 7], "fast_bas": [7, 16], "fast_smal": [7, 16], "fast_tini": [7, 16], "faster": [4, 7, 15], "fasterrcnn_mobilenet_v3_large_fpn": 7, "favorit": 16, "featur": [3, 7, 9, 10], "feedback": 1, "feel": [2, 13], "felix92": 13, "few": [3, 15, 16], "figsiz": 9, "figur": 9, "file": [2, 5], "final": 7, "find": [2, 3, 14], "fine": [], "finnish": 5, "first": [2, 5], "firsthand": 5, "fit": [7, 16], "flag": 16, "flip": 8, "float": [6, 8, 9, 15], "float32": [6, 7, 8, 15], "fn": 8, "focu": 13, "focus": [1, 5], "folder": 5, "follow": [1, 2, 3, 5, 8, 9, 11, 12, 13, 16], "font": [5, 9], "font_famili": [5, 9], "font_siz": 9, "foral": 9, "forc": 2, "forg": 3, "form": [4, 5, 16], "format": [6, 9, 11, 14, 15, 16], "forpost": [4, 5], "forum": 2, "found": [], "fp16": 15, "frac": 9, "framework": [3, 13, 14, 16], "free": [1, 2, 13], "french": [5, 11, 13, 16], "friendli": 4, "from": [1, 4, 5, 6, 7, 8, 9, 10, 11, 14, 15, 16], "from_hub": [7, 13], "from_imag": [6, 13], "from_pdf": 6, "from_url": 6, "full": [5, 9, 16], "function": [5, 8, 9], "funsd": [4, 5, 14, 16], "further": 14, "futur": 5, "g": [6, 7], "g_": 9, "g_x": 9, "gallagh": [], "gamma": 8, "gaussian": 8, "gaussianblur": 8, "gaussiannois": 8, "gdk": 3, "gen": 16, "gender": 1, "gener": [2, 4, 7], "generic_cyrillic_lett": [], "geom": [], "geometri": [4, 6, 16], "geq": 9, "german": [5, 11, 13], "get": 16, "git": 13, "github": [2, 3, 7, 13], "give": 1, "given": [5, 6, 8, 9, 16], "global": 7, "go": 16, "good": 15, "googl": 2, "googlevis": 4, "gpu": [4, 15], "gracefulli": 1, "graph": [4, 5, 6], "grayscal": 8, "ground": 9, "groung": 9, "group": [4, 16], "gt": 9, "gt_box": 9, "gt_label": 9, "gtk": 3, "guid": 2, "guidanc": 14, "gvision": 16, "h": [6, 7, 8], "h_": 9, "ha": [2, 5, 9, 14], "handl": [14, 16], "handwrit": 5, "handwritten": 14, "harass": 1, "hardwar": [], "harm": 1, "hat": 9, "have": [1, 2, 9, 11, 13, 14, 16], "head": [7, 16], "healthi": 1, "hebrew": 5, "height": 6, "hello": [9, 16], "help": 15, "here": [3, 8, 10, 14, 16], "hf": 7, "hf_hub_download": 7, "high": 6, "higher": [3, 5, 16], "hindi": [], "hindi_digit": 5, "hocr": 16, "homebrew": 3, "hook": 16, "horizont": [6, 8], "hous": 5, "how": [2, 11, 13, 14], "howev": 14, "hsv": 8, "html": [1, 2, 6, 16], "http": [1, 3, 5, 6, 7, 13, 16], "hub": 7, "hue": 8, "huggingfac": 7, "hw": 5, "i": [1, 2, 5, 6, 7, 8, 9, 12, 13, 14, 15], "i7": 16, "ibrahimov": [], "ic03": [4, 5, 14], "ic13": [4, 5, 14], "icdar": [4, 5], "icdar2019": 5, "id": 16, "ident": 1, "identifi": 4, "iiit": [4, 5], "iiit5k": [5, 14], "iiithw": [4, 5, 14], "imag": [4, 5, 6, 7, 8, 9, 13, 14, 16], "imagenet": 7, "imageri": 1, "images_90k_norm": 5, "imagetensor": [], "imagetransform": [], "img": [5, 8, 14], "img_cont": 6, "img_fold": [5, 14], "img_path": 6, "img_transform": 5, "imgur5k": [4, 5, 14], "imgur5k_annot": 5, "imlist": 5, "impact": 1, "implement": [5, 6, 7, 8, 9, 16], "import": [5, 6, 7, 8, 9, 11, 13, 14, 15, 16], "improv": 7, "inappropri": 1, "incid": 1, "includ": [1, 3, 5, 14, 15], "inclus": 1, "increas": 8, "independ": [], "index": [2, 6], "indic": 9, "individu": 1, "infer": [4, 7, 8], "inform": [1, 2, 4, 5, 14], "initi": [], "input": [2, 6, 7, 8, 15, 16], "input_crop": 7, "input_pag": [7, 9, 16], "input_seq": [], "input_shap": 15, "input_str": [], "input_tensor": 7, "inspir": [1, 8], "instal": 13, "instanc": [1, 16], "instanti": [7, 16], "instead": [5, 6, 7], "insult": 1, "int": [5, 6, 8, 9], "int64": [8, 9], "integ": 9, "integr": [4, 13, 14], "intel": 16, "interact": [1, 6, 9], "interfac": 13, "interoper": 15, "interpol": 8, "interpret": [5, 6], "intersect": 9, "invert": 8, "investig": 1, "invis": 1, "involv": [1, 16], "io": 13, "iou": 9, "iou_thresh": 9, "iou_threshold": [], "irregular": [4, 7, 14], "isn": 5, "issu": [1, 2, 13], "italian": 5, "iter": [5, 8, 14, 16], "its": [6, 7, 8, 9, 14, 16], "itself": [7, 13], "j": 9, "jame": [], "job": 2, "join": 2, "jpeg": 8, "jpegqual": 8, "jpg": [5, 6, 13], "json": [5, 14, 16], "json_output": 16, "jump": 2, "just": 1, "kei": [4, 5], "kera": [7, 15], "kernel": [4, 7, 8], "kernel_shap": 8, "keywoard": 7, "keyword": [5, 6, 7, 9], "kie": [7, 11], "kie_predictor": [7, 11], "kiepredictor": 7, "kind": 1, "know": 2, "kwarg": [5, 6, 7, 9], "l": 9, "l_j": 9, "label": [5, 8, 9, 14], "label_fil": [5, 14], "label_fold": 5, "label_path": [5, 14], "labels_path": [5, 14], "ladder": 1, "lambda": 8, "lambdatransform": 8, "lang": 16, "languag": [1, 4, 5, 6, 7, 13, 16], "larg": [7, 13], "largest": 9, "last": [3, 5], "latenc": 7, "later": 2, "latest": [3, 16], "latin": 5, "layer": 15, "layout": 16, "lead": 1, "leader": 1, "learn": [1, 4, 7, 15, 16], "least": 3, "left": [9, 16], "legacy_french": 5, "length": [5, 16], "less": [15, 16], "level": [1, 5, 9, 16], "leverag": 10, "lf": 13, "libffi": 3, "librari": [2, 3, 10, 11], "light": 4, "lightweight": [], "like": 1, "limits_": 9, "line": [4, 7, 9, 16], "line_1_1": 16, "link": 11, "linknet": [4, 7], "linknet_resnet18": [7, 11, 16], "linknet_resnet18_rot": [], "linknet_resnet34": [7, 15, 16], "linknet_resnet50": [7, 16], "linux": [], "list": [5, 6, 8, 9, 13], "ll": 9, "load": [4, 5, 7], "load_state_dict": 11, "load_weight": 11, "loc_pr": 16, "local": [2, 4, 5, 7, 9, 14, 16], "localis": 5, "localizationconfus": 9, "locat": [2, 6, 16], "login": 7, "login_to_hub": [7, 13], "logo": [6, 14], "love": 13, "lower": [8, 9, 16], "m": [2, 9, 16], "m1": 3, "macbook": 3, "machin": 15, "maco": 3, "made": 4, "magc_resnet31": 7, "mai": [1, 2], "mail": 1, "main": 10, "maintain": 4, "mainten": 2, "make": [1, 2, 9, 12, 13, 15, 16], "mani": [14, 16], "manipul": 16, "map": [5, 7], "map_loc": 11, "mask": [], "mask_label": [], "mask_shap": 9, "master": [4, 7, 16], "match": [9, 16], "mathcal": 9, "matplotlib": [6, 9], "max": [5, 8, 9], "max_angl": 8, "max_area": 8, "max_char": [5, 14], "max_delta": 8, "max_font_s": [], "max_gain": 8, "max_gamma": 8, "max_qual": 8, "max_ratio": 8, "maximum": [5, 8], "maxval": [7, 8], "mbox": 9, "mean": [8, 9, 11], "meaniou": 9, "meant": [6, 15], "measur": 16, "media": 1, "median": 7, "meet": 11, "member": 1, "memori": [9, 12, 15], "mention": 16, "merg": 5, "messag": 2, "meta": 16, "metadata": 15, "metal": 3, "method": [6, 8, 16], "metric": [9, 16], "middl": 16, "might": [15, 16], "min": 8, "min_area": 8, "min_char": [5, 14], "min_font_s": [], "min_gain": 8, "min_gamma": 8, "min_qual": 8, "min_ratio": 8, "min_val": 8, "minde": [1, 3, 4, 7], "minim": [2, 4], "minimalist": [4, 7], "minimum": [3, 5, 8, 9, 16], "minval": 8, "miss": 3, "mistak": 1, "mixed_float16": 15, "mixed_precis": 15, "mjsynth": [4, 5, 14], "mnt": 5, "mobilenet": [7, 13], "mobilenet_v3_larg": 7, "mobilenet_v3_large_r": 7, "mobilenet_v3_smal": 7, "mobilenet_v3_small_crop_orient": [], "mobilenet_v3_small_orient": 7, "mobilenet_v3_small_page_orient": [], "mobilenet_v3_small_r": 7, "mobilenetv3": 7, "modal": [4, 5], "mode": 3, "model": [5, 9, 12, 14], "model_nam": [7, 13, 15], "model_path": 15, "moder": 1, "modif": 2, "modifi": [7, 12, 16], "modul": [6, 7, 8, 9, 16], "moment": [], "more": [2, 9, 14, 16], "moscardi": [], "most": 16, "mozilla": 1, "multi": [4, 7], "multiclass": [], "multilingu": [5, 13], "multipl": [5, 6, 8, 16], "multipli": 8, "multiprocess": 12, "my": 7, "my_awesome_model": 13, "my_hook": 16, "n": [5, 9], "name": [5, 7, 15, 16], "nation": 1, "natur": [1, 4, 5], "nb": [], "ndarrai": [5, 6, 8, 9], "necessari": [3, 11, 12], "need": [2, 3, 5, 9, 11, 12, 13, 16], "neg": 8, "nest": 16, "netraj": [], "network": [4, 5, 7, 15], "neural": [4, 5, 7, 15], "new": [2, 9], "next": [5, 14], "nois": 8, "noisi": [4, 5], "non": [4, 5, 6, 7, 8, 9], "none": [5, 6, 7, 8, 9, 16], "normal": [7, 8], "norwegian": 5, "note": [0, 2, 5, 7, 13, 15], "now": 2, "np": [7, 8, 9, 16], "num_output_channel": 8, "num_sampl": [5, 14], "num_work": 5, "number": [5, 8, 9, 16], "numpi": [6, 7, 9, 16], "o": 3, "obb": [], "obj_detect": 13, "object": [5, 9, 10, 16], "objectness_scor": [], "oblig": 1, "obtain": 16, "occupi": 15, "ocr": [4, 5, 7, 9, 13, 14], "ocr_carea": 16, "ocr_db_crnn": 9, "ocr_lin": 16, "ocr_pag": 16, "ocr_par": 16, "ocr_predictor": [7, 11, 13, 15, 16], "ocrdataset": [5, 14], "ocrmetr": 9, "ocrpredictor": [7, 11], "ocrx_word": 16, "offens": 1, "offici": [1, 7], "offlin": 1, "offset": 8, "onc": 16, "one": [2, 5, 7, 8, 11, 13, 16], "oneof": 8, "ones": [5, 8, 9], "onli": [2, 7, 8, 9, 13, 14, 15, 16], "onlin": 1, "onnx": [], "onnxruntim": [], "onnxtr": [], "opac": 8, "opacity_rang": 8, "open": [1, 2, 13, 15], "opinion": 1, "optic": [4, 16], "optim": 4, "option": [5, 7, 11], "order": [2, 5, 6, 8], "org": [1, 5, 7, 16], "organ": 6, "orient": [1, 6, 7, 16], "orientationpredictor": [], "other": [1, 2], "otherwis": [1, 6, 9], "our": [2, 7, 16], "out": [2, 7, 8, 9, 16], "out_box": [], "outpout": 16, "output": [6, 8, 15], "output_s": [6, 8], "outsid": 12, "over": [3, 5, 9, 16], "overal": [1, 7], "overlai": 6, "overview": [], "overwrit": [], "overwritten": 13, "own": 4, "p": [8, 9, 16], "packag": [2, 4, 9, 12, 14], "pad": [5, 7, 8, 16], "page": [3, 5, 7, 9, 16], "page1": 6, "page2": 6, "page_1": 16, "page_idx": [6, 16], "page_orientation_predictor": [], "page_param": [], "pair": 9, "pango": 3, "paper": 7, "par_1_1": 16, "paragraph": 16, "paragraph_break": 16, "parallel": [], "param": [8, 16], "paramet": [4, 6, 7, 15], "pars": [4, 5], "parseq": [4, 7, 13, 16], "part": [5, 8, 16], "parti": 3, "partial": 16, "particip": 1, "pass": [5, 6, 7, 16], "password": 6, "patch": [7, 9], "path": [5, 6, 14], "path_to_checkpoint": 11, "path_to_custom_model": [], "path_to_pt": 11, "patil": [], "pattern": 1, "pdf": [6, 7, 10], "pdfpage": 6, "peopl": 1, "per": [8, 16], "perform": [4, 6, 7, 8, 9, 12, 15, 16], "period": 1, "permiss": 1, "permut": [4, 7], "persian_lett": 5, "person": [1, 14], "phase": 16, "photo": 14, "physic": [1, 6], "pick": 8, "pictur": 6, "pip": [2, 3], "pipelin": 16, "pixbuf": 3, "pixel": [6, 8, 16], "pleas": 2, "plot": 9, "plt": 9, "plug": 13, "plugin": 3, "png": 6, "point": 15, "polici": 12, "polish": 5, "polit": 1, "polygon": [5, 9, 16], "pool": 7, "portugues": 5, "posit": [1, 9], "possibl": [2, 9, 13, 16], "post": [1, 16], "postprocessor": 16, "potenti": 7, "power": 4, "ppageno": 16, "pre": [2, 7], "pre_transform_multiclass": [], "precis": [9, 16], "pred": 9, "pred_box": 9, "pred_label": 9, "predefin": 14, "predict": [6, 7, 9, 16], "predictor": [4, 6, 7, 11, 13, 15], "prefer": 14, "preinstal": [], "preprocessor": [11, 16], "prerequisit": 13, "present": 10, "preserv": [7, 8, 16], "preserve_aspect_ratio": [6, 7, 8, 11, 16], "pretrain": [4, 7, 9, 11, 15, 16], "pretrained_backbon": [7, 11], "print": 16, "prior": 5, "privaci": 1, "privat": 1, "probabl": 8, "problem": 2, "procedur": 8, "process": [2, 4, 6, 11, 16], "processor": 16, "produc": [10, 16], "product": 15, "profession": 1, "project": [2, 14], "promptli": 1, "proper": 2, "properli": 5, "provid": [1, 2, 4, 13, 14, 16], "public": [1, 4], "publicli": 16, "publish": 1, "pull": 13, "punctuat": 5, "pure": 5, "purpos": 2, "push_to_hf_hub": [7, 13], "py": 13, "pypdfium2": [3, 6], "pyplot": [6, 9], "python": 2, "python3": 13, "pytorch": [3, 4, 7, 8, 11, 13, 15, 16], "q": 2, "qr": 6, "qr_code": 14, "qualiti": 8, "question": 1, "quickli": 4, "quicktour": 10, "r": 16, "race": 1, "ramdisk": 5, "rand": [7, 8, 9, 15, 16], "random": [7, 8, 9, 16], "randomappli": 8, "randombright": 8, "randomcontrast": 8, "randomcrop": 8, "randomgamma": 8, "randomhorizontalflip": 8, "randomhu": 8, "randomjpegqu": 8, "randomli": 8, "randomres": [], "randomrot": 8, "randomsatur": 8, "randomshadow": 8, "rang": 8, "rassi": 13, "ratio": [7, 8, 16], "raw": [6, 9], "re": 15, "read": [4, 5, 7], "read_html": 6, "read_img": [], "read_img_as_numpi": 6, "read_img_as_tensor": 6, "read_pdf": 6, "readi": 15, "real": [4, 7, 8], "realli": [], "reason": [1, 4, 5], "rebuild": 2, "rebuilt": 2, "recal": [9, 16], "receipt": [4, 5, 16], "reco_arch": [7, 11, 13, 15], "reco_b": [], "reco_model": [11, 13], "reco_param": 11, "reco_predictor": 11, "recogn": 16, "recognit": [5, 9, 11], "recognition_predictor": [7, 16], "recognition_task": [5, 14], "recognitiondataset": [5, 14], "recognitionpredictor": [7, 11], "rectangular": 7, "red": 9, "reduc": [3, 8], "refer": [2, 3, 11, 13, 14, 16], "regardless": 1, "region": 16, "regroup": 9, "regular": 14, "reject": 1, "rel": [6, 8, 9, 16], "relat": 6, "releas": [0, 3], "relev": [], "religion": 1, "remov": 1, "render": [6, 16], "repo": 7, "repo_id": [7, 13], "report": 1, "repositori": [5, 7, 13], "repres": [1, 9, 15, 16], "represent": [4, 7], "request": [1, 13], "requir": [3, 8], "research": 4, "residu": 7, "resiz": [8, 16], "resnet": 7, "resnet18": [7, 13], "resnet31": 7, "resnet34": 7, "resnet50": [7, 13], "resolv": 6, "resolve_block": 16, "resolve_lin": 16, "resourc": 14, "respect": 1, "respons": 9, "rest": [2, 8, 9], "restrict": 12, "result": [2, 5, 6, 10, 13, 16], "return": 16, "reusabl": 16, "review": 1, "rgb": [6, 8], "rgb_mode": 6, "rgb_output": 6, "right": [1, 7, 9], "roboflow": [], "robust": [4, 5], "root": 5, "rotat": [5, 6, 7, 8, 9, 14, 16], "run": [2, 3, 7], "same": [2, 6, 9, 14, 16], "sampl": [5, 14, 16], "sample_transform": 5, "samplecompos": [], "sanjin": [], "sar": [4, 7], "sar_resnet31": [7, 16], "satur": 8, "save": [7, 14], "scale": [6, 7, 8, 9], "scale_rang": [], "scan": [4, 5], "scene": [4, 5, 7], "score": 9, "script": [2, 14], "seamless": 4, "seamlessli": [4, 16], "search": 7, "searchabl": 10, "sec": 16, "second": 16, "section": [11, 13, 15, 16], "secur": [1, 12], "see": [1, 2], "seen": 16, "segment": [4, 7, 16], "self": 16, "semant": [4, 7], "send": 16, "sens": 9, "sensit": 14, "separ": 16, "sequenc": [4, 5, 6, 7, 9, 16], "sequenti": [8, 16], "seri": 1, "seriou": 1, "set": [1, 3, 5, 7, 9, 12, 16], "set_global_polici": 15, "sever": [6, 8, 16], "sex": 1, "sexual": 1, "shade": 8, "shape": [4, 6, 7, 8, 9, 16], "share": [12, 14], "shift": 8, "shm": 12, "should": [2, 5, 6, 8, 9], "show": [4, 6, 7, 9, 11, 13], "showcas": 2, "shuffl": [5, 8], "side": 9, "signatur": 6, "signific": 14, "simpl": [4, 7], "simpler": 7, "sinc": [5, 14], "singl": [1, 2, 4, 5], "single_img_doc": [], "size": [1, 5, 6, 8, 9, 16], "skew": 16, "slack": 2, "slightli": 7, "small": [2, 7], "smallest": 6, "smooth": [], "smoothing_factor": [], "snapshot_download": 7, "snippet": 16, "so": [2, 3, 5, 7, 13, 14], "social": 1, "socio": 1, "some": [3, 10, 13, 14], "someth": 2, "somewher": 2, "soon": 15, "sort": 1, "sourc": [5, 6, 7, 8, 9, 13], "space": [1, 16], "span": 16, "spanish": 5, "spatial": [4, 5, 6, 9], "specif": [2, 3, 9, 11, 14, 16], "specifi": [1, 5, 6], "speed": [4, 7], "sphinx": 2, "sroie": [4, 5, 14], "stabl": 3, "stackoverflow": 2, "stage": 4, "standalon": [], "standard": 8, "start": 5, "state": [4, 9], "static": 9, "statist": [], "statu": 1, "std": [8, 11], "step": 12, "still": 16, "str": [5, 6, 7, 8, 9], "straight": [5, 7, 14, 16], "straighten": [], "straighten_pag": 7, "straigten_pag": [], "stream": 6, "street": [4, 5], "strict": 3, "strictli": 9, "string": [5, 6, 9, 16], "strive": 3, "strong": [4, 7], "structur": [15, 16], "subset": [5, 16], "suggest": [2, 13], "sum": 9, "summari": 9, "support": [15, 16], "sustain": 1, "svhn": [4, 5, 14], "svt": [5, 14], "swedish": 5, "symmetr": [7, 8, 16], "symmetric_pad": [7, 8, 16], "synthes": 9, "synthesize_pag": 9, "synthet": 4, "synthtext": [4, 5, 14], "system": 16, "t": [2, 5, 11, 16], "tabl": 13, "take": [1, 5, 16], "target": [5, 6, 8, 9, 14], "target_s": 5, "task": [4, 5, 7, 13, 14, 16], "task2": 5, "team": 3, "techminde": 3, "templat": [2, 4], "tensor": [5, 6, 8, 16], "tensorflow": [3, 4, 6, 7, 8, 11, 13, 15, 16], "tensorspec": 15, "term": 1, "test": [5, 14], "test_set": 5, "text": [5, 6, 7, 9, 14], "text_output": 16, "textmatch": 9, "textnet": 7, "textnet_bas": 7, "textnet_smal": 7, "textnet_tini": 7, "textract": [4, 16], "textstylebrush": [4, 5], "textual": [4, 5, 6, 7, 16], "tf": [3, 6, 7, 8, 13, 15], "than": [2, 3, 9, 13], "thank": 2, "thei": [1, 9], "them": [3, 5, 16], "thi": [1, 2, 3, 5, 9, 11, 12, 13, 14, 15, 16], "thing": [15, 16], "third": 3, "those": [1, 3, 6, 16], "threaten": 1, "threshold": 16, "through": [1, 8, 14], "tilman": 13, "time": [1, 4, 7, 9, 14], "tini": 7, "titl": [6, 16], "tm": 16, "tmp": 12, "togeth": [2, 6], "tograi": 8, "tool": 14, "top": [9, 16], "topic": 2, "torch": [3, 8, 11, 13, 15], "torchvis": 8, "total": 11, "toward": [1, 3], "train": [2, 5, 7, 8, 13, 14, 15, 16], "train_it": [5, 14], "train_load": [5, 14], "train_pytorch": 13, "train_set": [5, 14], "train_tensorflow": 13, "trainabl": [4, 7], "tranform": 8, "transcrib": 16, "transfer": [4, 5], "transfo": 8, "transform": [4, 5, 7], "translat": 1, "troll": 1, "true": [5, 6, 7, 8, 9, 11, 12, 13, 14, 15, 16], "truth": 9, "tune": 15, "tupl": [5, 6, 8, 9], "turn": [], "two": [6, 12], "txt": 5, "type": [6, 9, 13, 15, 16], "typic": 16, "u": [1, 2], "ucsd": 5, "udac": 2, "uint8": [6, 7, 9, 16], "ukrainian": [], "unaccept": 1, "underli": [14, 16], "underneath": 6, "understand": [4, 5, 16], "unidecod": 9, "uniform": [7, 8], "uniformli": 8, "uninterrupt": [6, 16], "union": 9, "unit": [], "unittest": 2, "unknown": [], "unknown_char": [], "unlock": 6, "unoffici": 7, "unprofession": 1, "unsolicit": 1, "unsupervis": 4, "unwelcom": 1, "up": [7, 16], "updat": 9, "upgrad": 2, "upper": [5, 8], "uppercas": 14, "url": 6, "us": [1, 2, 3, 5, 7, 9, 11, 12, 13, 16], "usabl": 16, "usag": [12, 15], "use_broadcast": 9, "use_polygon": [5, 9, 14], "useabl": 16, "useless": [], "user": [3, 4, 6, 10], "utf": 16, "util": 15, "v1": 13, "v3": [7, 13, 16], "valid": 14, "valu": [2, 6, 8, 16], "valuabl": 4, "variabl": 12, "varieti": 5, "veri": 7, "verma": [], "version": [1, 2, 3, 15, 16], "vgg": 7, "vgg16": 13, "vgg16_bn_r": 7, "via": 1, "video": [], "vietnames": 5, "view": [4, 5], "viewpoint": 1, "violat": 1, "visibl": 1, "vision": [4, 5, 7], "visiondataset": 5, "visiontransform": 7, "visual": 4, "visualize_pag": 9, "vit_": 7, "vit_b": 7, "vitstr": [4, 7, 15], "vitstr_bas": [7, 16], "vitstr_smal": [7, 11, 15, 16], "viz": [], "vocab": [11, 13, 14, 16], "vocab_nam": [], "vocabulari": [5, 11, 13], "w": [6, 7, 8, 9], "w3": 16, "wa": 1, "wai": [1, 4, 14], "want": [2, 15, 16], "warmup": 16, "wasn": 2, "we": [1, 2, 3, 4, 6, 8, 13, 14, 15, 16], "weasyprint": 6, "web": [2, 6], "websit": 5, "weight": 11, "welcom": 1, "well": [1, 15], "were": [1, 6, 16], "what": 1, "when": [1, 2, 7], "whenev": 2, "where": [2, 6, 8, 9], "whether": [2, 5, 6, 8, 9, 14, 16], "which": [1, 7, 12, 14, 16], "whichev": 3, "while": [8, 16], "why": 1, "width": 6, "wiki": 1, "wildreceipt": [4, 5, 14], "window": [3, 7, 9], "wish": 2, "within": 1, "without": [1, 5, 7], "wonder": 2, "word": [4, 5, 7, 9, 16], "word_1_1": 16, "word_1_2": 16, "word_1_3": 16, "wordgener": [5, 14], "words_onli": 9, "work": [12, 16], "worker": 5, "workflow": 2, "worklow": 2, "world": [9, 16], "worth": 7, "would": [], "wrap": 16, "wrapper": [5, 8], "write": 12, "written": [1, 6], "www": [1, 6, 16], "x": [6, 8, 9], "x_ascend": 16, "x_descend": 16, "x_i": 9, "x_size": 16, "x_wconf": 16, "xhtml": 16, "xmax": 6, "xmin": 6, "xml": 16, "xml_bytes_str": 16, "xml_element": 16, "xml_output": 16, "xmln": 16, "y": 9, "y_i": 9, "y_j": 9, "yet": [], "ymax": 6, "ymin": 6, "yolov8": [], "yolov8_artefact": [], "you": [2, 3, 5, 6, 7, 11, 12, 13, 14, 15, 16], "your": [2, 4, 6, 9, 16], "yoursit": 6, "yugesh": [], "zero": [8, 9], "zoo": [], "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 5, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 5, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 5, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 5, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 5, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": [], "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 5, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 5, "\u00e4\u00f6\u00e4\u00f6": 5, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 5, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 5, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 5, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 5, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 5, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": [], "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": [], "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": [], "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 5, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 5, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 5, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 5, "\u067e\u0686\u06a2\u06a4\u06af": 5, "\u0905": [], "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": [], "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": [], "\u0950": [], "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": [], "\u09bd": [], "\u09ce": [], "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": []}, "titles": ["Changelog", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 2, "0": 0, "01": 0, "02": 0, "03": 0, "04": [], "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 1], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 1], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": [], "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 1], "31": 0, "4": [0, 1], "5": 0, "6": 0, "7": 0, "8": 0, "9": [], "advanc": 16, "approach": 16, "architectur": 16, "arg": [5, 6, 7, 8, 9], "artefact": 6, "artefactdetect": [], "attribut": 1, "avail": [14, 16], "aw": 12, "ban": 1, "block": 6, "bug": 2, "changelog": 0, "choos": [14, 16], "classif": [7, 13], "code": [1, 2], "codebas": 2, "commit": 2, "commun": 13, "compos": 8, "conda": 3, "conduct": 1, "connect": 2, "continu": 2, "contrib": [], "contribut": 2, "contributor": 1, "convent": 13, "correct": 1, "coven": 1, "custom": [5, 11], "data": 14, "dataload": 5, "dataset": [4, 5, 14], "detect": [4, 7, 13, 14, 16], "develop": 2, "do": 16, "doctr": [2, 4, 5, 6, 7, 8, 9, 10, 15], "document": [2, 4, 6], "end": 16, "enforc": 1, "evalu": 9, "export": 15, "factori": 7, "featur": [2, 4], "feedback": 2, "file": 6, "from": 13, "gener": [5, 14], "git": 3, "guidelin": 1, "half": 15, "hub": 13, "huggingfac": 13, "i": 16, "infer": 15, "instal": [2, 3], "integr": 2, "io": 6, "lambda": 12, "let": 2, "line": 6, "linux": 3, "load": [11, 13, 14], "loader": 5, "main": 4, "mode": 2, "model": [4, 7, 11, 13, 15, 16], "modifi": 2, "modul": [], "name": 13, "notebook": 10, "object": 14, "ocr": 16, "onli": 3, "onnx": 15, "optim": 15, "option": 16, "orient": [], "our": 1, "output": 16, "own": [11, 14], "packag": 3, "page": 6, "perman": 1, "pipelin": [], "pledg": 1, "precis": 15, "predictor": 16, "prepar": 15, "prerequisit": 3, "pretrain": 13, "push": 13, "python": 3, "qualiti": 2, "question": 2, "read": 6, "readi": 14, "recognit": [4, 7, 13, 14, 16], "reconstitut": [], "report": 2, "request": 2, "resourc": [], "respons": 1, "return": [5, 6, 7, 9], "right": 16, "scope": 1, "share": 13, "should": 16, "stage": 16, "standard": 1, "structur": [2, 6], "style": 2, "support": [4, 5, 8], "synthet": [5, 14], "task": 9, "temporari": 1, "test": 2, "text": [4, 16], "train": 11, "transform": 8, "two": 16, "unit": 2, "us": [14, 15], "util": 9, "v0": 0, "verif": 2, "via": 3, "visual": 9, "vocab": 5, "warn": 1, "what": 16, "word": 6, "your": [11, 13, 14, 15], "zoo": [4, 7]}})
\ No newline at end of file
diff --git a/v0.9.0/searchindex.js b/v0.9.0/searchindex.js
index 645170147c..ed7fdaedb5 100644
--- a/v0.9.0/searchindex.js
+++ b/v0.9.0/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"alltitles": {"1. Correction": [[1, "correction"]], "2. Warning": [[1, "warning"]], "3. Temporary Ban": [[1, "temporary-ban"]], "4. Permanent Ban": [[1, "permanent-ban"]], "AWS Lambda": [[13, null]], "Advanced options": [[18, "advanced-options"]], "Args:": [[6, "args"], [6, "id4"], [6, "id7"], [6, "id10"], [6, "id13"], [6, "id16"], [6, "id19"], [6, "id22"], [6, "id25"], [6, "id29"], [6, "id32"], [6, "id37"], [6, "id40"], [6, "id46"], [6, "id49"], [6, "id50"], [6, "id51"], [6, "id54"], [6, "id57"], [6, "id60"], [6, "id61"], [7, "args"], [7, "id2"], [7, "id3"], [7, "id4"], [7, "id5"], [7, "id6"], [7, "id7"], [7, "id10"], [7, "id12"], [7, "id14"], [7, "id16"], [7, "id20"], [7, "id24"], [7, "id28"], [8, "args"], [8, "id3"], [8, "id8"], [8, "id13"], [8, "id17"], [8, "id21"], [8, "id26"], [8, "id31"], [8, "id36"], [8, "id41"], [8, "id46"], [8, "id50"], [8, "id54"], [8, "id59"], [8, "id63"], [8, "id68"], [8, "id73"], [8, "id77"], [8, "id81"], [8, "id85"], [8, "id90"], [8, "id95"], [8, "id99"], [8, "id104"], [8, "id109"], [8, "id114"], [8, "id119"], [8, "id123"], [8, "id127"], [8, "id132"], [8, "id137"], [8, "id142"], [8, "id146"], [8, "id150"], [8, "id155"], [8, "id159"], [8, "id163"], [8, "id167"], [8, "id169"], [8, "id171"], [8, "id173"], [9, "args"], [9, "id1"], [9, "id2"], [9, "id3"], [9, "id4"], [9, "id5"], [9, "id6"], [9, "id7"], [9, "id8"], [9, "id9"], [9, "id10"], [9, "id11"], [9, "id12"], [9, "id13"], [9, "id14"], [9, "id15"], [9, "id16"], [9, "id17"], [9, "id18"], [9, "id19"], [10, "args"], [10, "id3"], [10, "id4"], [10, "id5"], [10, "id6"], [10, "id7"], [10, "id8"], [10, "id9"]], "Artefact": [[7, "artefact"]], "ArtefactDetection": [[15, "artefactdetection"]], "Attribution": [[1, "attribution"]], "Available Datasets": [[16, "available-datasets"]], "Available architectures": [[18, "available-architectures"], [18, "id1"], [18, "id2"]], "Available contribution modules": [[15, "available-contribution-modules"]], "Block": [[7, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[16, null]], "Choosing the right model": [[18, null]], "Classification": [[14, "classification"]], "Code quality": [[2, "code-quality"]], "Code style verification": [[2, "code-style-verification"]], "Codebase structure": [[2, "codebase-structure"]], "Commits": [[2, "commits"]], "Composing transformations": [[9, "composing-transformations"]], "Continuous Integration": [[2, "continuous-integration"]], "Contributing to docTR": [[2, null]], "Contributor Covenant Code of Conduct": [[1, null]], "Custom dataset loader": [[6, "custom-dataset-loader"]], "Data Loading": [[16, "data-loading"]], "Dataloader": [[6, "dataloader"]], "Detection": [[14, "detection"], [16, "detection"]], "Detection predictors": [[18, "detection-predictors"]], "Developer mode installation": [[2, "developer-mode-installation"]], "Developing docTR": [[2, "developing-doctr"]], "Document": [[7, "document"]], "Document structure": [[7, "document-structure"]], "End-to-End OCR": [[18, "end-to-end-ocr"]], "Enforcement": [[1, "enforcement"]], "Enforcement Guidelines": [[1, "enforcement-guidelines"]], "Enforcement Responsibilities": [[1, "enforcement-responsibilities"]], "Export to ONNX": [[17, "export-to-onnx"]], "Feature requests & bug report": [[2, "feature-requests-bug-report"]], "Feedback": [[2, "feedback"]], "File reading": [[7, "file-reading"]], "Half-precision": [[17, "half-precision"]], "Installation": [[3, null]], "Integrate contributions into your pipeline": [[15, null]], "Let\u2019s connect": [[2, "let-s-connect"]], "Line": [[7, "line"]], "Loading from Huggingface Hub": [[14, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[12, "loading-your-custom-trained-model"]], "Main Features": [[4, "main-features"]], "Model optimization": [[17, "model-optimization"]], "Model zoo": [[4, "model-zoo"]], "Modifying the documentation": [[2, "modifying-the-documentation"]], "Naming conventions": [[14, "naming-conventions"]], "Object Detection": [[16, "object-detection"]], "Our Pledge": [[1, "our-pledge"]], "Our Standards": [[1, "our-standards"]], "Page": [[7, "page"]], "Preparing your model for inference": [[17, null]], "Prerequisites": [[3, "prerequisites"]], "Pretrained community models": [[14, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[14, "pushing-to-the-huggingface-hub"]], "Questions": [[2, "questions"]], "Recognition": [[14, "recognition"], [16, "recognition"]], "Recognition predictors": [[18, "recognition-predictors"]], "Returns:": [[6, "returns"], [7, "returns"], [7, "id11"], [7, "id13"], [7, "id15"], [7, "id19"], [7, "id23"], [7, "id27"], [7, "id31"], [8, "returns"], [8, "id6"], [8, "id11"], [8, "id16"], [8, "id20"], [8, "id24"], [8, "id29"], [8, "id34"], [8, "id39"], [8, "id44"], [8, "id49"], [8, "id53"], [8, "id57"], [8, "id62"], [8, "id66"], [8, "id71"], [8, "id76"], [8, "id80"], [8, "id84"], [8, "id88"], [8, "id93"], [8, "id98"], [8, "id102"], [8, "id107"], [8, "id112"], [8, "id117"], [8, "id122"], [8, "id126"], [8, "id130"], [8, "id135"], [8, "id140"], [8, "id145"], [8, "id149"], [8, "id153"], [8, "id158"], [8, "id162"], [8, "id166"], [8, "id168"], [8, "id170"], [8, "id172"], [10, "returns"]], "Scope": [[1, "scope"]], "Share your model with the community": [[14, null]], "Supported Vocabs": [[6, "supported-vocabs"]], "Supported contribution modules": [[5, "supported-contribution-modules"]], "Supported datasets": [[4, "supported-datasets"]], "Supported transformations": [[9, "supported-transformations"]], "Synthetic dataset generator": [[6, "synthetic-dataset-generator"], [16, "synthetic-dataset-generator"]], "Task evaluation": [[10, "task-evaluation"]], "Text Detection": [[18, "text-detection"]], "Text Recognition": [[18, "text-recognition"]], "Text detection models": [[4, "text-detection-models"]], "Text recognition models": [[4, "text-recognition-models"]], "Train your own model": [[12, null]], "Two-stage approaches": [[18, "two-stage-approaches"]], "Unit tests": [[2, "unit-tests"]], "Use your own datasets": [[16, "use-your-own-datasets"]], "Using your ONNX exported model": [[17, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[3, "via-conda-only-for-linux"]], "Via Git": [[3, "via-git"]], "Via Python Package": [[3, "via-python-package"]], "Visualization": [[10, "visualization"]], "What should I do with the output?": [[18, "what-should-i-do-with-the-output"]], "Word": [[7, "word"]], "docTR Notebooks": [[11, null]], "docTR Vocabs": [[6, "id62"]], "docTR: Document Text Recognition": [[4, null]], "doctr.contrib": [[5, null]], "doctr.datasets": [[6, null], [6, "datasets"]], "doctr.io": [[7, null]], "doctr.models": [[8, null]], "doctr.models.classification": [[8, "doctr-models-classification"]], "doctr.models.detection": [[8, "doctr-models-detection"]], "doctr.models.factory": [[8, "doctr-models-factory"]], "doctr.models.recognition": [[8, "doctr-models-recognition"]], "doctr.models.zoo": [[8, "doctr-models-zoo"]], "doctr.transforms": [[9, null]], "doctr.utils": [[10, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]]}, "docnames": ["changelog", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[7, "doctr.io.Artefact", false]], "block (class in doctr.io)": [[7, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms)": [[9, "doctr.transforms.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[6, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms)": [[9, "doctr.transforms.ColorInversion", false]], "compose (class in doctr.transforms)": [[9, "doctr.transforms.Compose", false]], "cord (class in doctr.datasets)": [[6, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[8, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[8, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[8, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[8, "doctr.models.classification.crop_orientation_predictor", false]], "dataloader (class in doctr.datasets.loader)": [[6, "doctr.datasets.loader.DataLoader", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[8, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[8, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[7, "doctr.io.decode_img_as_tensor", false]], "detection_predictor() (in module doctr.models.detection)": [[8, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[6, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[10, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[6, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[7, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[7, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[6, "doctr.datasets.encode_sequences", false]], "fast_base() (in module doctr.models.detection)": [[8, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[8, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[8, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[8, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[7, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[7, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[7, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[6, "doctr.datasets.FUNSD", false]], "gaussianblur (class in doctr.transforms)": [[9, "doctr.transforms.GaussianBlur", false]], "gaussiannoise (class in doctr.transforms)": [[9, "doctr.transforms.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[6, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[6, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[6, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[6, "doctr.datasets.IIITHWS", false]], "imgur5k (class in doctr.datasets)": [[6, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[8, "doctr.models.kie_predictor", false]], "lambdatransformation (class in doctr.transforms)": [[9, "doctr.transforms.LambdaTransformation", false]], "line (class in doctr.io)": [[7, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[8, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[8, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[8, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[10, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[8, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[8, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[8, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[6, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[8, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[8, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[8, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[8, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[8, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[8, "doctr.models.classification.mobilenet_v3_small_r", false]], "normalize (class in doctr.transforms)": [[9, "doctr.transforms.Normalize", false]], "ocr_predictor() (in module doctr.models)": [[8, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[6, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[10, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms)": [[9, "doctr.transforms.OneOf", false]], "page (class in doctr.io)": [[7, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[8, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[8, "doctr.models.recognition.parseq", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[8, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms)": [[9, "doctr.transforms.RandomApply", false]], "randombrightness (class in doctr.transforms)": [[9, "doctr.transforms.RandomBrightness", false]], "randomcontrast (class in doctr.transforms)": [[9, "doctr.transforms.RandomContrast", false]], "randomcrop (class in doctr.transforms)": [[9, "doctr.transforms.RandomCrop", false]], "randomgamma (class in doctr.transforms)": [[9, "doctr.transforms.RandomGamma", false]], "randomhorizontalflip (class in doctr.transforms)": [[9, "doctr.transforms.RandomHorizontalFlip", false]], "randomhue (class in doctr.transforms)": [[9, "doctr.transforms.RandomHue", false]], "randomjpegquality (class in doctr.transforms)": [[9, "doctr.transforms.RandomJpegQuality", false]], "randomresize (class in doctr.transforms)": [[9, "doctr.transforms.RandomResize", false]], "randomrotate (class in doctr.transforms)": [[9, "doctr.transforms.RandomRotate", false]], "randomsaturation (class in doctr.transforms)": [[9, "doctr.transforms.RandomSaturation", false]], "randomshadow (class in doctr.transforms)": [[9, "doctr.transforms.RandomShadow", false]], "read_html() (in module doctr.io)": [[7, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[7, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[7, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[7, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[8, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[6, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms)": [[9, "doctr.transforms.Resize", false]], "resnet18() (in module doctr.models.classification)": [[8, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[8, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[8, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[8, "doctr.models.classification.resnet50", false]], "sar_resnet31() (in module doctr.models.recognition)": [[8, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[7, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[7, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[6, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[10, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[10, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[10, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[10, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[6, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[6, "doctr.datasets.SVT", false]], "synthtext (class in doctr.datasets)": [[6, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[10, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[8, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[8, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[8, "doctr.models.classification.textnet_tiny", false]], "togray (class in doctr.transforms)": [[9, "doctr.transforms.ToGray", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[10, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[10, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[10, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[10, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[8, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[10, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[8, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[8, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[8, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[8, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[6, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[7, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[6, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.datasets": [[6, 0, 1, "", "CORD"], [6, 0, 1, "", "CharacterGenerator"], [6, 0, 1, "", "DetectionDataset"], [6, 0, 1, "", "DocArtefacts"], [6, 0, 1, "", "FUNSD"], [6, 0, 1, "", "IC03"], [6, 0, 1, "", "IC13"], [6, 0, 1, "", "IIIT5K"], [6, 0, 1, "", "IIITHWS"], [6, 0, 1, "", "IMGUR5K"], [6, 0, 1, "", "MJSynth"], [6, 0, 1, "", "OCRDataset"], [6, 0, 1, "", "RecognitionDataset"], [6, 0, 1, "", "SROIE"], [6, 0, 1, "", "SVHN"], [6, 0, 1, "", "SVT"], [6, 0, 1, "", "SynthText"], [6, 0, 1, "", "WILDRECEIPT"], [6, 0, 1, "", "WordGenerator"], [6, 1, 1, "", "encode_sequences"]], "doctr.datasets.loader": [[6, 0, 1, "", "DataLoader"]], "doctr.io": [[7, 0, 1, "", "Artefact"], [7, 0, 1, "", "Block"], [7, 0, 1, "", "Document"], [7, 0, 1, "", "DocumentFile"], [7, 0, 1, "", "Line"], [7, 0, 1, "", "Page"], [7, 0, 1, "", "Word"], [7, 1, 1, "", "decode_img_as_tensor"], [7, 1, 1, "", "read_html"], [7, 1, 1, "", "read_img_as_numpy"], [7, 1, 1, "", "read_img_as_tensor"], [7, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[7, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[7, 2, 1, "", "from_images"], [7, 2, 1, "", "from_pdf"], [7, 2, 1, "", "from_url"]], "doctr.io.Page": [[7, 2, 1, "", "show"]], "doctr.models": [[8, 1, 1, "", "kie_predictor"], [8, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[8, 1, 1, "", "crop_orientation_predictor"], [8, 1, 1, "", "magc_resnet31"], [8, 1, 1, "", "mobilenet_v3_large"], [8, 1, 1, "", "mobilenet_v3_large_r"], [8, 1, 1, "", "mobilenet_v3_small"], [8, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [8, 1, 1, "", "mobilenet_v3_small_page_orientation"], [8, 1, 1, "", "mobilenet_v3_small_r"], [8, 1, 1, "", "page_orientation_predictor"], [8, 1, 1, "", "resnet18"], [8, 1, 1, "", "resnet31"], [8, 1, 1, "", "resnet34"], [8, 1, 1, "", "resnet50"], [8, 1, 1, "", "textnet_base"], [8, 1, 1, "", "textnet_small"], [8, 1, 1, "", "textnet_tiny"], [8, 1, 1, "", "vgg16_bn_r"], [8, 1, 1, "", "vit_b"], [8, 1, 1, "", "vit_s"]], "doctr.models.detection": [[8, 1, 1, "", "db_mobilenet_v3_large"], [8, 1, 1, "", "db_resnet50"], [8, 1, 1, "", "detection_predictor"], [8, 1, 1, "", "fast_base"], [8, 1, 1, "", "fast_small"], [8, 1, 1, "", "fast_tiny"], [8, 1, 1, "", "linknet_resnet18"], [8, 1, 1, "", "linknet_resnet34"], [8, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[8, 1, 1, "", "from_hub"], [8, 1, 1, "", "login_to_hub"], [8, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[8, 1, 1, "", "crnn_mobilenet_v3_large"], [8, 1, 1, "", "crnn_mobilenet_v3_small"], [8, 1, 1, "", "crnn_vgg16_bn"], [8, 1, 1, "", "master"], [8, 1, 1, "", "parseq"], [8, 1, 1, "", "recognition_predictor"], [8, 1, 1, "", "sar_resnet31"], [8, 1, 1, "", "vitstr_base"], [8, 1, 1, "", "vitstr_small"]], "doctr.transforms": [[9, 0, 1, "", "ChannelShuffle"], [9, 0, 1, "", "ColorInversion"], [9, 0, 1, "", "Compose"], [9, 0, 1, "", "GaussianBlur"], [9, 0, 1, "", "GaussianNoise"], [9, 0, 1, "", "LambdaTransformation"], [9, 0, 1, "", "Normalize"], [9, 0, 1, "", "OneOf"], [9, 0, 1, "", "RandomApply"], [9, 0, 1, "", "RandomBrightness"], [9, 0, 1, "", "RandomContrast"], [9, 0, 1, "", "RandomCrop"], [9, 0, 1, "", "RandomGamma"], [9, 0, 1, "", "RandomHorizontalFlip"], [9, 0, 1, "", "RandomHue"], [9, 0, 1, "", "RandomJpegQuality"], [9, 0, 1, "", "RandomResize"], [9, 0, 1, "", "RandomRotate"], [9, 0, 1, "", "RandomSaturation"], [9, 0, 1, "", "RandomShadow"], [9, 0, 1, "", "Resize"], [9, 0, 1, "", "ToGray"]], "doctr.utils.metrics": [[10, 0, 1, "", "DetectionMetric"], [10, 0, 1, "", "LocalizationConfusion"], [10, 0, 1, "", "OCRMetric"], [10, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[10, 2, 1, "", "summary"], [10, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[10, 2, 1, "", "summary"], [10, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[10, 2, 1, "", "summary"], [10, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[10, 2, 1, "", "summary"], [10, 2, 1, "", "update"]], "doctr.utils.visualization": [[10, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [1, 7, 8, 10, 14, 17], "0": [1, 3, 6, 9, 10, 12, 15, 16, 18], "00": 18, "01": 18, "0123456789": 6, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 6, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 6, "02": [], "02562": 8, "03": 18, "035": 18, "0361328125": 18, "04": 18, "05": 18, "06": 18, "06640625": 18, "07": 18, "08": [9, 18], "09": 18, "0966796875": 18, "1": [3, 6, 7, 8, 9, 10, 12, 16, 18], "10": [6, 10, 18], "100": [6, 9, 10, 16, 18], "1000": 18, "101": 6, "1024": [8, 12, 18], "104": 6, "106": 6, "108": 6, "1095": 16, "11": 18, "110": 10, "1107": 16, "114": 6, "115": [], "1156": 16, "116": 6, "118": 6, "11800h": 18, "11th": 18, "12": [3, 18], "120": 6, "123": 6, "126": 6, "1268": 16, "128": [8, 12, 17, 18], "13": 18, "130": 6, "13068": 16, "131": 6, "1337891": 16, "1357421875": 18, "1396484375": 18, "14": 18, "1420": 18, "14470v1": 6, "149": 16, "15": 18, "150": [10, 18], "1552": 18, "16": [8, 17, 18], "1630859375": 18, "1684": 18, "16x16": 8, "17": 18, "1778": 18, "1782": 18, "18": [8, 18], "185546875": 18, "1900": 18, "1910": 8, "19342": 16, "19370": 16, "195": 6, "19598": 16, "199": 18, "1999": 18, "2": [3, 4, 6, 7, 9, 15, 18], "20": 18, "200": 10, "2000": 16, "2003": [4, 6], "2012": 6, "2013": [4, 6], "2015": 6, "2019": 4, "2023": [], "207901": 16, "21": 18, "2103": 6, "2186": 16, "21888": 16, "22": 18, "224": [8, 9], "225": 9, "22672": 16, "229": [9, 16], "23": 18, "233": 16, "234": 6, "236": [], "24": 18, "246": 16, "249": 16, "25": 18, "2504": 18, "255": [7, 8, 9, 10, 18], "256": 8, "257": 16, "26": 18, "26032": 16, "264": 12, "27": 18, "2700": 16, "2710": 18, "2749": 12, "28": 18, "287": 12, "29": 18, "296": 12, "299": 12, "2d": 18, "3": [3, 4, 7, 8, 9, 10, 17, 18], "30": 18, "300": 16, "3000": 16, "301": 12, "30595": 18, "30ghz": 18, "31": 8, "32": [6, 8, 9, 12, 16, 17, 18], "3232421875": 18, "33": [9, 18], "33402": 16, "33608": 16, "34": [8, 18], "340": 18, "3456": 18, "35": [], "3515625": 18, "36": 18, "360": 16, "37": [6, 18], "38": 18, "39": 18, "4": [8, 9, 10, 18], "40": 18, "406": 9, "41": 18, "42": 18, "43": 18, "44": 18, "45": 18, "456": 9, "46": 18, "47": 18, "472": 16, "48": [6, 18], "485": 9, "49": 18, "49377": 16, "5": [6, 9, 10, 15, 18], "50": [8, 16, 18], "51": 18, "51171875": 18, "512": 8, "52": [6, 18], "529": 18, "53": 18, "54": 18, "540": 18, "5478515625": 18, "55": 18, "56": 18, "57": 18, "58": 18, "580": 18, "5810546875": 18, "583": 18, "59": 18, "597": 18, "5k": [4, 6], "5m": 18, "6": [9, 18], "60": 9, "600": [8, 10, 18], "61": 18, "62": 18, "626": 16, "63": 18, "64": [8, 9, 18], "641": 18, "647": 16, "65": 18, "66": 18, "67": 18, "68": 18, "69": 18, "693": 12, "694": 12, "695": 12, "6m": 18, "7": 18, "70": [6, 10, 18], "707470": 16, "71": [6, 18], "7100000": 16, "7141797": 16, "7149": 16, "72": 18, "72dpi": 7, "73": 18, "73257": 16, "74": 18, "75": [9, 18], "7581382": 16, "76": 18, "77": 18, "772": 12, "772875": 16, "78": 18, "785": 12, "79": 18, "793533": 16, "796": 16, "798": 12, "7m": 18, "8": [8, 9, 18], "80": 18, "800": [8, 10, 16, 18], "81": 18, "82": 18, "83": 18, "84": 18, "849": 16, "85": 18, "8564453125": 18, "857": 18, "85875": 16, "86": 18, "8603515625": 18, "87": 18, "8707": 16, "88": 18, "89": 18, "9": [3, 9, 18], "90": 18, "90k": 6, "90kdict32px": 6, "91": 18, "914085328578949": 18, "92": 18, "93": 18, "94": [6, 18], "95": [10, 18], "9578408598899841": 18, "96": 18, "97": 18, "98": 18, "99": 18, "9949972033500671": 18, "A": [1, 2, 4, 6, 7, 8, 11, 17], "As": 2, "Be": 18, "Being": 1, "By": 13, "For": [1, 2, 3, 12, 18], "If": [2, 7, 8, 12, 18], "In": [2, 6, 16], "It": [9, 14, 15, 17], "Its": [4, 8], "No": [1, 18], "Of": 6, "Or": [15, 17], "The": [1, 2, 6, 7, 10, 13, 15, 17, 18], "Then": 8, "To": [2, 3, 13, 14, 15, 17, 18], "_": [1, 6, 8], "__call__": 18, "_build": 2, "_i": 10, "ab": 6, "abc": 17, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 6, "abdef": [6, 16], "abl": [16, 18], "about": [1, 16, 18], "abov": 18, "abstract": [], "abstractdataset": 6, "abus": 1, "accept": 1, "access": [4, 7, 16, 18], "account": [1, 14], "accur": 18, "accuraci": 10, "achiev": 17, "act": 1, "action": 1, "activ": 4, "ad": [2, 8, 9], "adapt": 1, "add": [9, 10, 14, 18], "add_hook": 18, "add_label": 10, "addit": [2, 3, 7, 15], "addition": [2, 18], "address": [1, 7], "adjust": 9, "advanc": 1, "advantag": 17, "advis": 2, "aesthet": [4, 6], "affect": 1, "after": [14, 18], "ag": 1, "again": 8, "aggreg": [10, 16], "aggress": 1, "align": [1, 7, 9], "all": [1, 2, 5, 6, 7, 9, 10, 15, 16, 18], "allow": [1, 17], "along": 18, "alreadi": [2, 17], "also": [1, 8, 14, 15, 16, 18], "alwai": 16, "an": [1, 2, 4, 6, 7, 8, 10, 15, 17, 18], "analysi": [7, 15], "ancient_greek": 6, "andrej": [], "angl": [7, 9], "ani": [1, 6, 7, 8, 9, 10, 17, 18], "annot": 6, "anot": 16, "anoth": [8, 12, 16], "answer": 1, "anyascii": 10, "anyon": 4, "anyth": 15, "api": [2, 4], "apolog": 1, "apologi": 1, "app": 2, "appear": 1, "appli": [1, 6, 9], "applic": [4, 8], "appoint": 1, "appreci": 14, "appropri": [1, 2, 18], "ar": [1, 2, 3, 5, 6, 7, 9, 10, 11, 15, 16, 18], "arab": 6, "arabic_diacrit": 6, "arabic_lett": 6, "arabic_punctu": 6, "arbitrarili": [4, 8], "arch": [8, 14], "architectur": [4, 8, 14, 15], "area": 18, "arg": [], "argument": [6, 7, 8, 10, 18], "around": 1, "arrai": [7, 9, 10], "art": [4, 15], "artefact": [10, 11, 15, 18], "artefact_typ": 7, "artefactdetector": [], "articl": [], "artifici": [4, 6], "arxiv": [6, 8], "asarrai": 10, "ascii_lett": 6, "aspect": [4, 8, 9, 18], "assess": 10, "assign": 10, "associ": 7, "assum": 8, "assume_straight_pag": [8, 18], "astyp": [8, 10, 18], "attack": 1, "attend": [4, 8], "attent": [1, 8], "autom": 4, "automat": 18, "autoregress": [4, 8], "avail": [1, 4, 5, 9], "averag": [9, 18], "avoid": [1, 3], "aw": [4, 18], "awar": 18, "azur": 18, "b": [8, 10, 18], "b_j": 10, "back": 2, "backbon": 8, "backend": 18, "background": 16, "bangla": 6, "bar": 15, "bar_cod": 16, "baranovskij": [], "base": [4, 8, 15], "baselin": [4, 8, 18], "batch": [6, 8, 9, 15, 16, 18], "batch_siz": [6, 12, 15, 16, 17], "bblanchon": 3, "bbox": 18, "becaus": 13, "been": [2, 10, 16, 18], "befor": [6, 8, 9, 18], "begin": 10, "behavior": [1, 18], "being": [10, 18], "belong": 18, "benchmark": 18, "best": 1, "better": [11, 18], "between": [9, 10, 18], "bgr": 7, "bilinear": 9, "bin_thresh": 18, "binar": [4, 8, 18], "binari": [7, 17, 18], "bit": 17, "blank": [], "block": [10, 18], "block_1_1": 18, "blue": [], "blur": 9, "bmvc": 6, "bn": 14, "bodi": [1, 18], "bool": [6, 7, 8, 9, 10], "boolean": [8, 18], "both": [4, 6, 9, 16, 18], "bottom": [8, 18], "bound": [6, 7, 8, 9, 10, 15, 18], "box": [6, 7, 8, 9, 10, 15, 16, 18], "box_thresh": 18, "brew": [], "bright": 9, "broadcast": [], "browser": [2, 4], "build": [2, 3, 17], "built": 2, "byte": [7, 18], "c": [3, 7, 10], "c_j": 10, "cach": [2, 6, 13], "cache_sampl": 6, "cairo": [], "call": 17, "callabl": [6, 9], "can": [2, 3, 12, 13, 14, 15, 16, 18], "capabl": [2, 11, 18], "case": [6, 10], "cf": 18, "cfg": 18, "challeng": 6, "challenge2_test_task12_imag": 6, "challenge2_test_task1_gt": 6, "challenge2_training_task12_imag": 6, "challenge2_training_task1_gt": 6, "chang": [13, 18], "channel": [1, 2, 7, 9], "channel_prior": 3, "channelshuffl": 9, "charact": [4, 6, 7, 10, 16, 18], "charactergener": [6, 16], "characterist": 1, "charg": 18, "charset": 18, "chart": 7, "check": [2, 14, 18], "checkpoint": 8, "chip": 3, "christian": [], "ci": 2, "clarifi": 1, "clariti": 1, "class": [1, 6, 7, 9, 10, 18], "class_nam": 12, "classif": 16, "classif_mobilenet_v3_smal": [], "classmethod": 7, "clear": 2, "clone": 3, "close": 2, "co": 14, "code": [4, 7, 15], "codecov": 2, "colab": 11, "collate_fn": 6, "collect": [7, 15], "color": 9, "colorinvers": 9, "column": 7, "com": [1, 3, 7, 8, 14], "combin": 18, "come": [], "command": [2, 15], "comment": 1, "commit": 1, "common": [1, 9, 10, 17], "commun": 1, "compar": 4, "comparison": [10, 18], "competit": 6, "compil": [11, 18], "complaint": 1, "complementari": 10, "complet": 2, "compon": 18, "compos": [6, 18], "comprehens": 18, "comput": [6, 10, 17, 18], "conf_threshold": 15, "confid": [7, 18], "config": [3, 8], "configur": 8, "confus": 10, "consecut": [9, 18], "consequ": 1, "consid": [1, 2, 6, 7, 10, 18], "consist": 18, "consolid": [4, 6], "constant": 9, "construct": 1, "consum": [], "contact": 1, "contain": [5, 6, 16], "content": [6, 7, 18], "context": 8, "contib": 3, "continu": 1, "contrast": 9, "contrast_factor": 9, "contrib": [3, 15], "contribut": 1, "contributor": 2, "convers": 7, "convert": [7, 9], "convert_target_to_rel": [], "convolut": 8, "cool": [], "coordin": [7, 18], "cord": [4, 6, 16, 18], "core": [10, 18], "corner": 18, "correct": 9, "correspond": [3, 7, 9, 18], "could": [1, 15], "counterpart": 10, "cover": 2, "coverag": 2, "cpu": [4, 12, 17], "creat": 14, "crnn": [4, 8, 14], "crnn_mobilenet_v3_larg": [8, 14, 18], "crnn_mobilenet_v3_smal": [8, 17, 18], "crnn_vgg16_bn": [8, 12, 14, 18], "crop": [7, 8, 9, 16, 18], "crop_bboxes_from_imag": [], "crop_orient": [7, 18], "crop_orientation_predictor": 8, "crop_param": [], "croporientationpredictor": [], "cuda": 17, "currenc": 6, "current": [2, 18], "custom": [14, 15, 17, 18], "custom_crop_orientation_model": [], "custom_page_orientation_model": [], "customhook": 18, "cvit": 4, "czczup": 8, "czech": 6, "d": [6, 16], "danish": 6, "data": [4, 6, 7, 9, 10, 12, 14], "dataload": 16, "dataset": [8, 12, 18], "dataset_info": 6, "date": [12, 18], "db": 14, "db_mobilenet_v3_larg": [8, 14, 18], "db_resnet34": 18, "db_resnet50": [8, 12, 14, 18], "db_resnet50_rot": [], "dbnet": [4, 8], "deal": [], "decis": 1, "decod": 7, "decode_img_as_tensor": 7, "decode_sequ": [], "dedic": 17, "deem": 1, "deep": [8, 18], "def": 18, "default": [3, 7, 12, 13, 18], "defer": 16, "defin": [10, 17], "degre": [7, 9], "degress": 7, "delet": 2, "delimit": 18, "delta": 9, "demo": [2, 4], "demonstr": 1, "depend": [2, 3, 4, 18], "deploi": 2, "deploy": 4, "derogatori": 1, "describ": 8, "descript": 11, "design": 9, "desir": 7, "det_arch": [8, 12, 14, 17], "det_b": 18, "det_model": [12, 14, 17], "det_param": 12, "det_predictor": [12, 18], "detail": [12, 18], "detect": [6, 7, 10, 11, 12, 15], "detect_languag": 8, "detect_orient": 8, "detection_predictor": [8, 18], "detection_task": [], "detectiondataset": [6, 16], "detectionmetr": 10, "detectionpredictor": [8, 12], "detector": [4, 8, 15], "deterior": 8, "determin": 1, "dev": [2, 13], "develop": 3, "deviat": 9, "devic": 17, "dict": [7, 10, 18], "dictionari": [7, 10], "differ": 1, "differenti": [4, 8], "digit": [4, 6, 16], "dimens": [7, 10, 18], "dimension": 9, "direct": 6, "directli": [14, 18], "directori": [2, 13], "disabl": [1, 13, 18], "disable_crop_orient": [], "disable_page_orient": [], "disclaim": 18, "discuss": 2, "disparag": 1, "displai": [7, 10], "display_artefact": 10, "distribut": 9, "div": 18, "divers": 1, "divid": 7, "do": [2, 3, 8], "doc": [2, 7, 15, 17, 18], "docartefact": [6, 16], "docstr": 2, "doctr": [3, 12, 13, 14, 15, 16, 17, 18], "doctr_cache_dir": 13, "doctr_multiprocessing_dis": 13, "document": [6, 8, 10, 11, 15, 16, 17, 18], "documentbuild": 18, "documentfil": [7, 14, 15, 17], "doesn": 17, "don": [12, 18], "done": 9, "download": [6, 16], "download_from_url": [], "downsiz": 8, "draw": 9, "draw_proba": [], "drop": 6, "drop_last": 6, "dtype": [7, 8, 9, 10, 17], "dual": [4, 6], "dummi": 14, "dummy_img": 18, "dummy_input": 17, "dure": 1, "dutch": 6, "dynam": [6, 15], "dynamic_seq_length": 6, "e": [1, 2, 3, 7, 8], "each": [4, 6, 7, 8, 9, 10, 16, 18], "eas": 2, "easi": [4, 10, 14, 17], "easili": [7, 10, 12, 14, 16, 18], "econom": 1, "edit": 1, "educ": 1, "effect": [], "effici": [2, 4, 6, 8], "either": [10, 18], "element": [6, 7, 8, 18], "els": [2, 15], "email": 1, "empathi": 1, "en": 18, "enabl": [6, 7], "enclos": 7, "encod": [4, 6, 7, 8, 18], "encode_sequ": 6, "encode_str": [], "encount": 2, "encrypt": 7, "end": [4, 6, 8, 10], "english": [6, 16], "enough": [2, 18], "ensur": 2, "entri": 6, "environ": [1, 13], "eo": 6, "equiv": 18, "estim": 8, "etc": [7, 15], "ethnic": 1, "evalu": [16, 18], "event": 1, "everyon": 1, "everyth": [2, 18], "exact": [10, 18], "exampl": [1, 2, 4, 6, 8, 14, 18], "exchang": 17, "execut": 18, "exist": 14, "expand": 9, "expect": [7, 9, 10], "experi": 1, "explan": [1, 18], "explicit": 1, "exploit": [4, 8], "export": [7, 8, 10, 11, 15, 18], "export_as_straight_box": [8, 18], "export_as_xml": 18, "export_model_to_onnx": 17, "express": [1, 9], "extens": 7, "extern": [1, 16], "extra": [], "extract": [4, 6], "extractor": 8, "f_": 10, "f_a": 10, "factor": 9, "fair": 1, "fairli": 1, "fals": [6, 7, 8, 9, 10, 12, 18], "famili": [], "faq": 1, "fascan": 14, "fast": [4, 6, 8], "fast_bas": [8, 18], "fast_smal": [8, 18], "fast_tini": [8, 18], "faster": [4, 8, 17], "fasterrcnn_mobilenet_v3_large_fpn": 8, "favorit": 18, "featur": [3, 8, 10, 11, 15], "feedback": 1, "feel": [2, 14], "felix92": 14, "few": [17, 18], "figsiz": 10, "figur": [10, 15], "file": [2, 6], "final": 8, "find": [2, 16], "fine": [], "finnish": 6, "first": [2, 6], "firsthand": 6, "fit": [8, 18], "flag": 18, "flip": 9, "float": [7, 9, 10, 17], "float32": [7, 8, 9, 17], "fn": 9, "focu": 14, "focus": [1, 6], "folder": 6, "follow": [1, 2, 3, 6, 9, 10, 12, 13, 14, 15, 18], "font": 6, "font_famili": 6, "font_siz": [], "foral": 10, "forc": 2, "forg": 3, "form": [4, 6, 18], "format": [7, 10, 12, 16, 17, 18], "forpost": [4, 6], "forum": 2, "found": [], "fp16": 17, "frac": 10, "framework": [3, 14, 16, 18], "free": [1, 2, 14], "french": [6, 12, 14, 18], "friendli": 4, "from": [1, 4, 6, 7, 8, 9, 10, 11, 12, 15, 16, 17, 18], "from_hub": [8, 14], "from_imag": [7, 14, 15, 17], "from_pdf": 7, "from_url": 7, "full": [6, 10, 18], "function": [6, 9, 10, 15], "funsd": [4, 6, 16, 18], "further": 16, "futur": 6, "g": [7, 8], "g_": 10, "g_x": 10, "gallagh": [], "gamma": 9, "gaussian": 9, "gaussianblur": 9, "gaussiannois": 9, "gdk": [], "gen": 18, "gender": 1, "gener": [2, 4, 7, 8], "generic_cyrillic_lett": [], "geom": [], "geometri": [4, 7, 18], "geq": 10, "german": [6, 12, 14], "get": [17, 18], "git": 14, "github": [2, 3, 8, 14], "give": [1, 15], "given": [6, 7, 9, 10, 18], "global": 8, "go": 18, "good": 17, "googl": 2, "googlevis": 4, "gpu": [4, 15, 17], "gracefulli": 1, "graph": [4, 6, 7], "grayscal": 9, "ground": 10, "groung": 10, "group": [4, 18], "gt": 10, "gt_box": 10, "gt_label": 10, "gtk": [], "guid": 2, "guidanc": 16, "gvision": 18, "h": [7, 8, 9], "h_": 10, "ha": [2, 6, 10, 16], "handl": [16, 18], "handwrit": 6, "handwritten": 16, "harass": 1, "hardwar": 18, "harm": 1, "hat": 10, "have": [1, 2, 10, 12, 14, 16, 17, 18], "head": [8, 18], "healthi": 1, "hebrew": 6, "height": [7, 9], "hello": [10, 18], "help": 17, "here": [5, 9, 11, 15, 16, 18], "hf": 8, "hf_hub_download": 8, "high": 7, "higher": [3, 6, 18], "hindi": 6, "hindi_digit": 6, "hocr": 18, "homebrew": [], "hook": 18, "horizont": [7, 9], "hous": 6, "how": [2, 12, 14, 16], "howev": 16, "hsv": 9, "html": [1, 2, 3, 7, 18], "http": [1, 3, 6, 7, 8, 14, 18], "hub": 8, "hue": 9, "huggingfac": 8, "hw": 6, "i": [1, 2, 6, 7, 8, 9, 10, 13, 14, 15, 16, 17], "i7": 18, "ibrahimov": [], "ic03": [4, 6, 16], "ic13": [4, 6, 16], "icdar": [4, 6], "icdar2019": 6, "id": 18, "ident": 1, "identifi": 4, "iiit": [4, 6], "iiit5k": [6, 16], "iiithw": [4, 6, 16], "imag": [4, 6, 7, 8, 9, 10, 14, 15, 16, 18], "imagenet": 8, "imageri": 1, "images_90k_norm": 6, "imagetensor": [], "imagetransform": [], "img": [6, 9, 16, 17], "img_cont": 7, "img_fold": [6, 16], "img_path": 7, "img_transform": 6, "imgur5k": [4, 6, 16], "imgur5k_annot": 6, "imlist": 6, "impact": 1, "implement": [6, 7, 8, 9, 10, 18], "import": [6, 7, 8, 9, 10, 12, 14, 15, 16, 17, 18], "improv": 8, "inappropri": 1, "incid": 1, "includ": [1, 6, 16, 17], "inclus": 1, "increas": 9, "independ": 9, "index": [2, 7], "indic": 10, "individu": 1, "infer": [4, 8, 9, 15], "inform": [1, 2, 4, 6, 16], "input": [2, 7, 8, 9, 17, 18], "input_crop": 8, "input_pag": [8, 10, 18], "input_seq": [], "input_shap": 17, "input_str": [], "input_tensor": 8, "inspir": [1, 9], "instal": [14, 15, 17], "instanc": [1, 18], "instanti": [8, 18], "instead": [6, 7, 8], "insult": 1, "int": [6, 7, 9], "int64": 10, "integ": 10, "integr": [4, 14, 16], "intel": 18, "interact": [1, 7, 10], "interfac": [14, 17], "interoper": 17, "interpol": 9, "interpret": [6, 7], "intersect": 10, "invert": 9, "investig": 1, "invis": 1, "involv": [1, 18], "io": [14, 15, 17], "iou": 10, "iou_thresh": 10, "iou_threshold": 15, "irregular": [4, 8, 16], "isn": 6, "issu": [1, 2, 14], "italian": 6, "iter": [6, 9, 16, 18], "its": [7, 8, 9, 10, 16, 18], "itself": [8, 14], "j": 10, "jame": [], "job": 2, "join": 2, "jpeg": 9, "jpegqual": 9, "jpg": [6, 7, 14, 17], "json": [6, 16, 18], "json_output": 18, "jump": 2, "just": 1, "kei": [4, 6], "kera": [8, 17], "kernel": [4, 8, 9], "kernel_shap": 9, "keywoard": 8, "keyword": [6, 7, 8, 10], "kie": [8, 12], "kie_predictor": [8, 12], "kiepredictor": 8, "kind": 1, "know": [2, 17], "kwarg": [6, 7, 8, 10], "l": 10, "l_j": 10, "label": [6, 10, 15, 16], "label_fil": [6, 16], "label_fold": 6, "label_path": [6, 16], "labels_path": [6, 16], "ladder": 1, "lambda": 9, "lambdatransform": 9, "lang": 18, "languag": [1, 4, 6, 7, 8, 14, 18], "larg": [8, 14], "largest": 10, "last": [3, 6], "latenc": 8, "later": 2, "latest": 18, "latin": 6, "layer": 17, "layout": 18, "lead": 1, "leader": 1, "learn": [1, 4, 8, 17, 18], "least": 3, "left": [10, 18], "legacy_french": 6, "length": [6, 18], "less": [17, 18], "level": [1, 6, 10, 18], "leverag": 11, "lf": 14, "libffi": [], "librari": [2, 3, 11, 12], "light": 4, "lightweight": 17, "like": 1, "limits_": 10, "line": [4, 8, 10, 18], "line_1_1": 18, "link": 12, "linknet": [4, 8], "linknet_resnet18": [8, 12, 17, 18], "linknet_resnet18_rot": [], "linknet_resnet34": [8, 17, 18], "linknet_resnet50": [8, 18], "linux": [], "list": [6, 7, 9, 10, 14], "ll": 10, "load": [4, 6, 8, 15, 17], "load_state_dict": 12, "load_weight": 12, "loc_pr": 18, "local": [2, 4, 6, 8, 10, 16, 18], "localis": 6, "localizationconfus": 10, "locat": [2, 7, 18], "login": 8, "login_to_hub": [8, 14], "logo": [7, 15, 16], "love": 14, "lower": [9, 10, 18], "m": [2, 10, 18], "m1": 3, "macbook": 3, "machin": 17, "maco": [], "made": 4, "magc_resnet31": 8, "mai": [1, 2], "mail": 1, "main": 11, "maintain": 4, "mainten": 2, "make": [1, 2, 10, 13, 14, 17, 18], "mani": [16, 18], "manipul": 18, "map": [6, 8], "map_loc": 12, "mask": [], "mask_label": [], "mask_shap": [], "master": [4, 8, 18], "match": [10, 18], "mathcal": 10, "matplotlib": [7, 10], "max": [6, 9, 10], "max_angl": 9, "max_area": 9, "max_char": [6, 16], "max_delta": 9, "max_font_s": [], "max_gain": 9, "max_gamma": 9, "max_qual": 9, "max_ratio": 9, "maximum": [6, 9], "maxval": [8, 9], "mbox": 10, "mean": [9, 10, 12], "meaniou": 10, "meant": [7, 17], "measur": 18, "media": 1, "median": 8, "meet": 12, "member": 1, "memori": [13, 17], "mention": 18, "merg": 6, "messag": 2, "meta": 18, "metadata": 17, "metal": 3, "method": [7, 9, 18], "metric": [10, 18], "middl": 18, "might": [17, 18], "min": 9, "min_area": 9, "min_char": [6, 16], "min_font_s": [], "min_gain": 9, "min_gamma": 9, "min_qual": 9, "min_ratio": 9, "min_val": 9, "minde": [1, 3, 4, 8], "minim": [2, 4], "minimalist": [4, 8], "minimum": [3, 6, 9, 10, 18], "minval": 9, "miss": 3, "mistak": 1, "mixed_float16": 17, "mixed_precis": 17, "mjsynth": [4, 6, 16], "mnt": 6, "mobilenet": [8, 14], "mobilenet_v3_larg": 8, "mobilenet_v3_large_r": 8, "mobilenet_v3_smal": 8, "mobilenet_v3_small_crop_orient": 8, "mobilenet_v3_small_orient": [], "mobilenet_v3_small_page_orient": 8, "mobilenet_v3_small_r": 8, "mobilenetv3": 8, "modal": [4, 6], "mode": 3, "model": [6, 10, 13, 15, 16], "model_nam": [8, 14, 17], "model_path": [15, 17], "moder": 1, "modif": 2, "modifi": [8, 13, 18], "modul": [3, 7, 8, 9, 10, 18], "moment": [], "more": [2, 16, 18], "moscardi": [], "most": 18, "mozilla": 1, "multi": [4, 8], "multiclass": [], "multilingu": [6, 14], "multipl": [6, 7, 9, 18], "multipli": 9, "multiprocess": 13, "my": 8, "my_awesome_model": 14, "my_hook": 18, "n": [6, 10], "name": [6, 8, 17, 18], "nation": 1, "natur": [1, 4, 6], "nb": [], "ndarrai": [6, 7, 9, 10], "necessari": [3, 12, 13], "need": [2, 3, 6, 10, 12, 13, 14, 15, 18], "neg": 9, "nest": 18, "netraj": [], "network": [4, 6, 8, 17], "neural": [4, 6, 8, 17], "new": [2, 10], "next": [6, 16], "nois": 9, "noisi": [4, 6], "non": [4, 6, 7, 8, 9, 10], "none": [6, 7, 8, 9, 10, 18], "normal": [8, 9], "norwegian": 6, "note": [0, 2, 6, 8, 14, 15, 17], "now": 2, "np": [8, 9, 10, 18], "num_output_channel": 9, "num_sampl": [6, 16], "num_work": [], "number": [6, 9, 10, 18], "numpi": [7, 8, 10, 18], "o": 3, "obb": 15, "obj_detect": 14, "object": [6, 7, 10, 11, 15, 18], "objectness_scor": [7, 18], "oblig": 1, "obtain": 18, "occupi": 17, "ocr": [4, 6, 8, 10, 14, 16], "ocr_carea": 18, "ocr_db_crnn": 10, "ocr_lin": 18, "ocr_pag": 18, "ocr_par": 18, "ocr_predictor": [8, 12, 14, 17, 18], "ocrdataset": [6, 16], "ocrmetr": 10, "ocrpredictor": [8, 12], "ocrx_word": 18, "offens": 1, "offici": [1, 8], "offlin": 1, "offset": 9, "onc": 18, "one": [2, 6, 8, 9, 12, 14, 18], "oneof": 9, "ones": [6, 10], "onli": [2, 8, 9, 10, 14, 16, 17, 18], "onlin": 1, "onnx": 15, "onnxruntim": [15, 17], "onnxtr": 17, "opac": 9, "opacity_rang": 9, "open": [1, 2, 14, 17], "opinion": 1, "optic": [4, 18], "optim": [4, 18], "option": [6, 8, 12], "order": [2, 6, 7, 9], "org": [1, 6, 8, 18], "organ": 7, "orient": [1, 7, 8, 15, 18], "orientationpredictor": 8, "other": [1, 2], "otherwis": [1, 7, 10], "our": [2, 8, 18], "out": [2, 8, 9, 10, 18], "out_box": [], "outpout": 18, "output": [7, 9, 17], "output_s": [7, 9], "outsid": 13, "over": [6, 10, 18], "overal": [1, 8], "overlai": 7, "overview": 15, "overwrit": [], "overwritten": 14, "own": 4, "p": [9, 18], "packag": [2, 4, 10, 13, 15, 16, 17], "pad": [6, 8, 9, 18], "page": [3, 6, 8, 10, 18], "page1": 7, "page2": 7, "page_1": 18, "page_idx": [7, 18], "page_orientation_predictor": 8, "page_param": [], "pair": 10, "pango": [], "paper": 8, "par_1_1": 18, "paragraph": 18, "paragraph_break": 18, "parallel": [], "param": [9, 18], "paramet": [4, 7, 8, 17], "pars": [4, 6], "parseq": [4, 8, 14, 17, 18], "part": [6, 9, 18], "parti": 3, "partial": 18, "particip": 1, "pass": [6, 7, 8, 18], "password": 7, "patch": [8, 10], "path": [6, 7, 15, 16, 17], "path_to_checkpoint": 12, "path_to_custom_model": 17, "path_to_pt": 12, "patil": [], "pattern": 1, "pdf": [7, 8, 11], "pdfpage": 7, "peopl": 1, "per": [9, 18], "perform": [4, 7, 8, 9, 10, 13, 17, 18], "period": 1, "permiss": 1, "permut": [4, 8], "persian_lett": 6, "person": [1, 16], "phase": 18, "photo": 16, "physic": [1, 7], "pick": 9, "pictur": 7, "pip": [2, 3, 15, 17], "pipelin": 18, "pixbuf": [], "pixel": [7, 9, 18], "pleas": 2, "plot": 10, "plt": 10, "plug": 14, "plugin": 3, "png": 7, "point": 17, "polici": 13, "polish": 6, "polit": 1, "polygon": [6, 10, 18], "pool": 8, "portugues": 6, "posit": [1, 10], "possibl": [2, 10, 14, 18], "post": [1, 18], "postprocessor": 18, "potenti": 8, "power": 4, "ppageno": 18, "pre": [2, 8, 17], "pre_transform_multiclass": [], "precis": [10, 18], "pred": 10, "pred_box": 10, "pred_label": 10, "predefin": 16, "predict": [7, 8, 10, 18], "predictor": [4, 7, 8, 12, 14, 17], "prefer": 16, "preinstal": 3, "preprocessor": [12, 18], "prerequisit": 14, "present": 11, "preserv": [8, 9, 18], "preserve_aspect_ratio": [7, 8, 9, 12, 18], "pretrain": [4, 8, 10, 12, 17, 18], "pretrained_backbon": [8, 12], "print": 18, "prior": 6, "privaci": 1, "privat": 1, "probabl": 9, "problem": 2, "procedur": 9, "process": [2, 4, 7, 12, 18], "processor": 18, "produc": [11, 18], "product": 17, "profession": 1, "project": [2, 16], "promptli": 1, "proper": 2, "properli": 6, "provid": [1, 2, 4, 14, 15, 16, 18], "public": [1, 4], "publicli": 18, "publish": 1, "pull": 14, "punctuat": 6, "pure": 6, "purpos": 2, "push_to_hf_hub": [8, 14], "py": 14, "pypdfium2": [3, 7], "pyplot": [7, 10], "python": [2, 15], "python3": 14, "pytorch": [3, 4, 8, 9, 12, 14, 17, 18], "q": 2, "qr": [7, 15], "qr_code": 16, "qualiti": 9, "question": 1, "quickli": 4, "quicktour": 11, "r": 18, "race": 1, "ramdisk": 6, "rand": [8, 9, 10, 17, 18], "random": [8, 9, 10, 18], "randomappli": 9, "randombright": 9, "randomcontrast": 9, "randomcrop": 9, "randomgamma": 9, "randomhorizontalflip": 9, "randomhu": 9, "randomjpegqu": 9, "randomli": 9, "randomres": 9, "randomrot": 9, "randomsatur": 9, "randomshadow": 9, "rang": 9, "rassi": 14, "ratio": [8, 9, 18], "raw": [7, 10], "re": 17, "read": [4, 6, 8], "read_html": 7, "read_img": [], "read_img_as_numpi": 7, "read_img_as_tensor": 7, "read_pdf": 7, "readi": 17, "real": [4, 8, 9], "realli": [], "reason": [1, 4, 6], "rebuild": 2, "rebuilt": 2, "recal": [10, 18], "receipt": [4, 6, 18], "reco_arch": [8, 12, 14, 17], "reco_b": 18, "reco_model": [12, 14, 17], "reco_param": 12, "reco_predictor": 12, "recogn": 18, "recognit": [6, 10, 12], "recognition_predictor": [8, 18], "recognition_task": [6, 16], "recognitiondataset": [6, 16], "recognitionpredictor": [8, 12], "rectangular": 8, "red": [], "reduc": [3, 9], "refer": [2, 3, 12, 14, 15, 16, 18], "regardless": 1, "region": 18, "regroup": 10, "regular": 16, "reject": 1, "rel": [7, 9, 10, 18], "relat": 7, "releas": [0, 3], "relev": 15, "religion": 1, "remov": 1, "render": [7, 18], "repo": 8, "repo_id": [8, 14], "report": 1, "repositori": [6, 8, 14], "repres": [1, 17, 18], "represent": [4, 8], "request": [1, 14], "requir": [3, 9, 17], "research": 4, "residu": 8, "resiz": [9, 18], "resnet": 8, "resnet18": [8, 14], "resnet31": 8, "resnet34": 8, "resnet50": [8, 14], "resolv": 7, "resolve_block": 18, "resolve_lin": 18, "resourc": 16, "respect": 1, "respons": [], "rest": [2, 9, 10], "restrict": 13, "result": [2, 6, 7, 11, 14, 17, 18], "return": 18, "reusabl": 18, "review": 1, "rgb": [7, 9], "rgb_mode": 7, "rgb_output": 7, "right": [1, 8, 10], "roboflow": [], "robust": [4, 6], "root": 6, "rotat": [6, 7, 8, 9, 10, 16, 18], "run": [2, 3, 8], "same": [2, 7, 10, 16, 17, 18], "sampl": [6, 16, 18], "sample_transform": 6, "samplecompos": [], "sanjin": [], "sar": [4, 8], "sar_resnet31": [8, 18], "satur": 9, "save": [8, 16], "scale": [7, 8, 9, 10], "scale_rang": 9, "scan": [4, 6], "scene": [4, 6, 8], "score": [7, 10], "script": [2, 16], "seamless": 4, "seamlessli": [4, 18], "search": 8, "searchabl": 11, "sec": 18, "second": 18, "section": [12, 14, 15, 17, 18], "secur": [1, 13], "see": [1, 2], "seen": 18, "segment": [4, 8, 18], "self": 18, "semant": [4, 8], "send": 18, "sens": 10, "sensit": 16, "separ": 18, "sequenc": [4, 6, 7, 8, 10, 18], "sequenti": [9, 18], "seri": 1, "seriou": 1, "set": [1, 3, 6, 8, 10, 13, 15, 18], "set_global_polici": 17, "sever": [7, 9, 18], "sex": 1, "sexual": 1, "shade": 9, "shape": [4, 7, 8, 9, 10, 18], "share": [13, 16], "shift": 9, "shm": 13, "should": [2, 6, 7, 9, 10], "show": [4, 7, 8, 10, 12, 14, 15], "showcas": 2, "shuffl": [6, 9], "side": 10, "signatur": 7, "signific": 16, "simpl": [4, 8, 17], "simpler": 8, "sinc": [6, 16], "singl": [1, 2, 4, 6], "single_img_doc": 17, "size": [1, 6, 7, 9, 15, 18], "skew": 18, "slack": 2, "slightli": 8, "small": [2, 8], "smallest": 7, "smooth": [], "smoothing_factor": [], "snapshot_download": 8, "snippet": 18, "so": [2, 3, 6, 8, 14, 16], "social": 1, "socio": 1, "some": [3, 11, 14, 16], "someth": 2, "somewher": 2, "soon": [], "sort": 1, "sourc": [6, 7, 8, 9, 10, 14], "space": [1, 18], "span": 18, "spanish": 6, "spatial": [4, 6, 7], "specif": [2, 3, 10, 12, 16, 18], "specifi": [1, 6, 7], "speed": [4, 8], "sphinx": 2, "sroie": [4, 6, 16], "stabl": 3, "stackoverflow": 2, "stage": 4, "standalon": [], "standard": 9, "start": 6, "state": [4, 10, 15], "static": 10, "statist": [], "statu": 1, "std": [9, 12], "step": 13, "still": 18, "str": [6, 7, 8, 9, 10], "straight": [6, 8, 16, 18], "straighten": [], "straighten_pag": 8, "straigten_pag": [], "stream": 7, "street": [4, 6], "strict": 3, "strictli": 10, "string": [6, 7, 10, 18], "strive": 3, "strong": [4, 8], "structur": [17, 18], "subset": [6, 18], "suggest": [2, 14], "sum": 10, "summari": 10, "support": [3, 15, 17, 18], "sustain": 1, "svhn": [4, 6, 16], "svt": [6, 16], "swedish": 6, "symmetr": [8, 9, 18], "symmetric_pad": [8, 9, 18], "synthes": [], "synthesize_pag": [], "synthet": 4, "synthtext": [4, 6, 16], "system": 18, "t": [2, 6, 12, 17, 18], "tabl": [14, 15], "take": [1, 6, 18], "target": [6, 7, 9, 10, 16], "target_s": 6, "task": [4, 6, 8, 14, 16, 18], "task2": 6, "team": 3, "techminde": 3, "templat": [2, 4], "tensor": [6, 7, 9, 18], "tensorflow": [3, 4, 7, 8, 9, 12, 14, 17, 18], "tensorspec": 17, "term": 1, "test": [6, 16], "test_set": 6, "text": [6, 7, 8, 10, 16], "text_output": 18, "textmatch": 10, "textnet": 8, "textnet_bas": 8, "textnet_smal": 8, "textnet_tini": 8, "textract": [4, 18], "textstylebrush": [4, 6], "textual": [4, 6, 7, 8, 18], "tf": [3, 7, 8, 9, 14, 17], "than": [2, 10, 14], "thank": 2, "thei": [1, 10], "them": [6, 18], "thi": [1, 2, 3, 5, 6, 9, 10, 12, 13, 14, 16, 17, 18], "thing": [17, 18], "third": 3, "those": [1, 7, 18], "threaten": 1, "threshold": 18, "through": [1, 9, 15, 16], "tilman": 14, "time": [1, 4, 8, 10, 16], "tini": 8, "titl": [7, 18], "tm": 18, "tmp": 13, "togeth": [2, 7], "tograi": 9, "tool": 16, "top": [10, 17, 18], "topic": 2, "torch": [3, 9, 12, 14, 17], "torchvis": 9, "total": 12, "toward": [1, 3], "train": [2, 6, 8, 9, 14, 15, 16, 17, 18], "train_it": [6, 16], "train_load": [6, 16], "train_pytorch": 14, "train_set": [6, 16], "train_tensorflow": 14, "trainabl": [4, 8], "tranform": 9, "transcrib": 18, "transfer": [4, 6], "transfo": 9, "transform": [4, 6, 8], "translat": 1, "troll": 1, "true": [6, 7, 8, 9, 10, 12, 13, 14, 16, 17, 18], "truth": 10, "tune": 17, "tupl": [6, 7, 9, 10], "turn": [], "two": [7, 13], "txt": 6, "type": [7, 10, 14, 17, 18], "typic": 18, "u": [1, 2], "ucsd": 6, "udac": 2, "uint8": [7, 8, 10, 18], "ukrainian": [], "unaccept": 1, "underli": [16, 18], "underneath": 7, "understand": [4, 6, 18], "unidecod": [], "uniform": [8, 9], "uniformli": 9, "uninterrupt": [7, 18], "union": 10, "unit": [], "unittest": 2, "unknown": [], "unknown_char": [], "unlock": 7, "unoffici": 8, "unprofession": 1, "unsolicit": 1, "unsupervis": 4, "unwelcom": 1, "up": [8, 18], "updat": 10, "upgrad": 2, "upper": [6, 9], "uppercas": 16, "url": 7, "us": [1, 2, 3, 6, 8, 10, 12, 13, 14, 15, 18], "usabl": 18, "usag": [13, 17], "use_broadcast": [], "use_polygon": [6, 10, 16], "useabl": 18, "user": [4, 7, 11], "utf": 18, "util": 17, "v1": 14, "v3": [8, 14, 18], "valid": 16, "valu": [2, 7, 9, 18], "valuabl": 4, "variabl": 13, "varieti": 6, "veri": 8, "verma": [], "version": [1, 2, 3, 17, 18], "vgg": 8, "vgg16": 14, "vgg16_bn_r": 8, "via": 1, "video": [], "vietnames": 6, "view": [4, 6], "viewpoint": 1, "violat": 1, "visibl": 1, "vision": [4, 6, 8], "visiondataset": 6, "visiontransform": 8, "visual": [3, 4, 15], "visualize_pag": 10, "vit_": 8, "vit_b": 8, "vitstr": [4, 8, 17], "vitstr_bas": [8, 18], "vitstr_smal": [8, 12, 17, 18], "viz": 3, "vocab": [12, 14, 16, 17, 18], "vocab_nam": [], "vocabulari": [6, 12, 14], "w": [7, 8, 9, 10], "w3": 18, "wa": 1, "wai": [1, 4, 16], "want": [2, 17, 18], "warmup": 18, "wasn": 2, "we": [1, 2, 3, 4, 7, 9, 14, 16, 17, 18], "weasyprint": 7, "web": [2, 7], "websit": 6, "weight": 12, "welcom": 1, "well": [1, 17], "were": [1, 7, 18], "what": 1, "when": [1, 2, 8], "whenev": 2, "where": [2, 7, 9, 10], "whether": [2, 6, 7, 9, 10, 16, 18], "which": [1, 8, 13, 15, 16, 18], "whichev": 3, "while": [9, 18], "why": 1, "width": [7, 9], "wiki": 1, "wildreceipt": [4, 6, 16], "window": [8, 10], "wish": 2, "within": 1, "without": [1, 6, 8], "wonder": 2, "word": [4, 6, 8, 10, 18], "word_1_1": 18, "word_1_2": 18, "word_1_3": 18, "wordgener": [6, 16], "words_onli": 10, "work": [13, 18], "worker": [], "workflow": 2, "worklow": 2, "world": [10, 18], "worth": 8, "wrap": 18, "wrapper": [6, 9], "write": 13, "written": [1, 7], "www": [1, 7, 18], "x": [7, 9, 10], "x_ascend": 18, "x_descend": 18, "x_i": 10, "x_size": 18, "x_wconf": 18, "xhtml": 18, "xmax": 7, "xmin": 7, "xml": 18, "xml_bytes_str": 18, "xml_element": 18, "xml_output": 18, "xmln": 18, "y": 10, "y_i": 10, "y_j": 10, "yet": 15, "ymax": 7, "ymin": 7, "yolov8": 15, "yolov8_artefact": [], "you": [2, 3, 6, 7, 8, 12, 13, 14, 15, 16, 17, 18], "your": [2, 4, 7, 10, 18], "yoursit": 7, "yugesh": [], "zero": [9, 10], "zoo": [], "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 6, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 6, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 6, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 6, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 6, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": [], "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 6, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 6, "\u00e4\u00f6\u00e4\u00f6": 6, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 6, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 6, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 6, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 6, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 6, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": [], "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": [], "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": [], "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 6, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 6, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 6, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 6, "\u067e\u0686\u06a2\u06a4\u06af": 6, "\u0905": 6, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 6, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 6, "\u0950": 6, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 6, "\u09bd": 6, "\u09ce": 6, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 6}, "titles": ["Changelog", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 2, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 1], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 1], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": [], "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 1], "31": 0, "4": [0, 1], "5": 0, "6": 0, "7": 0, "8": 0, "9": [], "advanc": 18, "approach": 18, "architectur": 18, "arg": [6, 7, 8, 9, 10], "artefact": 7, "artefactdetect": 15, "attribut": 1, "avail": [15, 16, 18], "aw": 13, "ban": 1, "block": 7, "bug": 2, "changelog": 0, "choos": [16, 18], "classif": [8, 14], "code": [1, 2], "codebas": 2, "commit": 2, "commun": 14, "compos": 9, "conda": 3, "conduct": 1, "connect": 2, "continu": 2, "contrib": 5, "contribut": [2, 5, 15], "contributor": 1, "convent": 14, "correct": 1, "coven": 1, "custom": [6, 12], "data": 16, "dataload": 6, "dataset": [4, 6, 16], "detect": [4, 8, 14, 16, 18], "develop": 2, "do": 18, "doctr": [2, 4, 5, 6, 7, 8, 9, 10, 11], "document": [2, 4, 7], "end": 18, "enforc": 1, "evalu": 10, "export": 17, "factori": 8, "featur": [2, 4], "feedback": 2, "file": 7, "from": 14, "gener": [6, 16], "git": 3, "guidelin": 1, "half": 17, "hub": 14, "huggingfac": 14, "i": 18, "infer": 17, "instal": [2, 3], "integr": [2, 15], "io": 7, "lambda": 13, "let": 2, "line": 7, "linux": 3, "load": [12, 14, 16], "loader": 6, "main": 4, "mode": 2, "model": [4, 8, 12, 14, 17, 18], "modifi": 2, "modul": [5, 15], "name": 14, "notebook": 11, "object": 16, "ocr": 18, "onli": 3, "onnx": 17, "optim": 17, "option": 18, "orient": [], "our": 1, "output": 18, "own": [12, 16], "packag": 3, "page": 7, "perman": 1, "pipelin": 15, "pledg": 1, "precis": 17, "predictor": 18, "prepar": 17, "prerequisit": 3, "pretrain": 14, "push": 14, "python": 3, "qualiti": 2, "question": 2, "read": 7, "readi": 16, "recognit": [4, 8, 14, 16, 18], "reconstitut": [], "report": 2, "request": 2, "resourc": [], "respons": 1, "return": [6, 7, 8, 10], "right": 18, "scope": 1, "share": 14, "should": 18, "stage": 18, "standard": 1, "structur": [2, 7], "style": 2, "support": [4, 5, 6, 9], "synthet": [6, 16], "task": 10, "temporari": 1, "test": 2, "text": [4, 18], "train": 12, "transform": 9, "two": 18, "unit": 2, "us": [16, 17], "util": 10, "v0": 0, "verif": 2, "via": 3, "visual": 10, "vocab": 6, "warn": 1, "what": 18, "word": 7, "your": [12, 14, 15, 16, 17], "zoo": [4, 8]}})
\ No newline at end of file
+Search.setIndex({"alltitles": {"1. Correction": [[1, "correction"]], "2. Warning": [[1, "warning"]], "3. Temporary Ban": [[1, "temporary-ban"]], "4. Permanent Ban": [[1, "permanent-ban"]], "AWS Lambda": [[13, null]], "Advanced options": [[18, "advanced-options"]], "Args:": [[6, "args"], [6, "id4"], [6, "id7"], [6, "id10"], [6, "id13"], [6, "id16"], [6, "id19"], [6, "id22"], [6, "id25"], [6, "id29"], [6, "id32"], [6, "id37"], [6, "id40"], [6, "id46"], [6, "id49"], [6, "id50"], [6, "id51"], [6, "id54"], [6, "id57"], [6, "id60"], [6, "id61"], [7, "args"], [7, "id2"], [7, "id3"], [7, "id4"], [7, "id5"], [7, "id6"], [7, "id7"], [7, "id10"], [7, "id12"], [7, "id14"], [7, "id16"], [7, "id20"], [7, "id24"], [7, "id28"], [8, "args"], [8, "id3"], [8, "id8"], [8, "id13"], [8, "id17"], [8, "id21"], [8, "id26"], [8, "id31"], [8, "id36"], [8, "id41"], [8, "id46"], [8, "id50"], [8, "id54"], [8, "id59"], [8, "id63"], [8, "id68"], [8, "id73"], [8, "id77"], [8, "id81"], [8, "id85"], [8, "id90"], [8, "id95"], [8, "id99"], [8, "id104"], [8, "id109"], [8, "id114"], [8, "id119"], [8, "id123"], [8, "id127"], [8, "id132"], [8, "id137"], [8, "id142"], [8, "id146"], [8, "id150"], [8, "id155"], [8, "id159"], [8, "id163"], [8, "id167"], [8, "id169"], [8, "id171"], [8, "id173"], [9, "args"], [9, "id1"], [9, "id2"], [9, "id3"], [9, "id4"], [9, "id5"], [9, "id6"], [9, "id7"], [9, "id8"], [9, "id9"], [9, "id10"], [9, "id11"], [9, "id12"], [9, "id13"], [9, "id14"], [9, "id15"], [9, "id16"], [9, "id17"], [9, "id18"], [9, "id19"], [10, "args"], [10, "id3"], [10, "id4"], [10, "id5"], [10, "id6"], [10, "id7"], [10, "id8"], [10, "id9"]], "Artefact": [[7, "artefact"]], "ArtefactDetection": [[15, "artefactdetection"]], "Attribution": [[1, "attribution"]], "Available Datasets": [[16, "available-datasets"]], "Available architectures": [[18, "available-architectures"], [18, "id1"], [18, "id2"]], "Available contribution modules": [[15, "available-contribution-modules"]], "Block": [[7, "block"]], "Changelog": [[0, null]], "Choose a ready to use dataset": [[16, null]], "Choosing the right model": [[18, null]], "Classification": [[14, "classification"]], "Code quality": [[2, "code-quality"]], "Code style verification": [[2, "code-style-verification"]], "Codebase structure": [[2, "codebase-structure"]], "Commits": [[2, "commits"]], "Composing transformations": [[9, "composing-transformations"]], "Continuous Integration": [[2, "continuous-integration"]], "Contributing to docTR": [[2, null]], "Contributor Covenant Code of Conduct": [[1, null]], "Custom dataset loader": [[6, "custom-dataset-loader"]], "Data Loading": [[16, "data-loading"]], "Dataloader": [[6, "dataloader"]], "Detection": [[14, "detection"], [16, "detection"]], "Detection predictors": [[18, "detection-predictors"]], "Developer mode installation": [[2, "developer-mode-installation"]], "Developing docTR": [[2, "developing-doctr"]], "Document": [[7, "document"]], "Document structure": [[7, "document-structure"]], "End-to-End OCR": [[18, "end-to-end-ocr"]], "Enforcement": [[1, "enforcement"]], "Enforcement Guidelines": [[1, "enforcement-guidelines"]], "Enforcement Responsibilities": [[1, "enforcement-responsibilities"]], "Export to ONNX": [[17, "export-to-onnx"]], "Feature requests & bug report": [[2, "feature-requests-bug-report"]], "Feedback": [[2, "feedback"]], "File reading": [[7, "file-reading"]], "Half-precision": [[17, "half-precision"]], "Installation": [[3, null]], "Integrate contributions into your pipeline": [[15, null]], "Let\u2019s connect": [[2, "let-s-connect"]], "Line": [[7, "line"]], "Loading from Huggingface Hub": [[14, "loading-from-huggingface-hub"]], "Loading your custom trained model": [[12, "loading-your-custom-trained-model"]], "Main Features": [[4, "main-features"]], "Model optimization": [[17, "model-optimization"]], "Model zoo": [[4, "model-zoo"]], "Modifying the documentation": [[2, "modifying-the-documentation"]], "Naming conventions": [[14, "naming-conventions"]], "Object Detection": [[16, "object-detection"]], "Our Pledge": [[1, "our-pledge"]], "Our Standards": [[1, "our-standards"]], "Page": [[7, "page"]], "Preparing your model for inference": [[17, null]], "Prerequisites": [[3, "prerequisites"]], "Pretrained community models": [[14, "pretrained-community-models"]], "Pushing to the Huggingface Hub": [[14, "pushing-to-the-huggingface-hub"]], "Questions": [[2, "questions"]], "Recognition": [[14, "recognition"], [16, "recognition"]], "Recognition predictors": [[18, "recognition-predictors"]], "Returns:": [[6, "returns"], [7, "returns"], [7, "id11"], [7, "id13"], [7, "id15"], [7, "id19"], [7, "id23"], [7, "id27"], [7, "id31"], [8, "returns"], [8, "id6"], [8, "id11"], [8, "id16"], [8, "id20"], [8, "id24"], [8, "id29"], [8, "id34"], [8, "id39"], [8, "id44"], [8, "id49"], [8, "id53"], [8, "id57"], [8, "id62"], [8, "id66"], [8, "id71"], [8, "id76"], [8, "id80"], [8, "id84"], [8, "id88"], [8, "id93"], [8, "id98"], [8, "id102"], [8, "id107"], [8, "id112"], [8, "id117"], [8, "id122"], [8, "id126"], [8, "id130"], [8, "id135"], [8, "id140"], [8, "id145"], [8, "id149"], [8, "id153"], [8, "id158"], [8, "id162"], [8, "id166"], [8, "id168"], [8, "id170"], [8, "id172"], [10, "returns"]], "Scope": [[1, "scope"]], "Share your model with the community": [[14, null]], "Supported Vocabs": [[6, "supported-vocabs"]], "Supported contribution modules": [[5, "supported-contribution-modules"]], "Supported datasets": [[4, "supported-datasets"]], "Supported transformations": [[9, "supported-transformations"]], "Synthetic dataset generator": [[6, "synthetic-dataset-generator"], [16, "synthetic-dataset-generator"]], "Task evaluation": [[10, "task-evaluation"]], "Text Detection": [[18, "text-detection"]], "Text Recognition": [[18, "text-recognition"]], "Text detection models": [[4, "text-detection-models"]], "Text recognition models": [[4, "text-recognition-models"]], "Train your own model": [[12, null]], "Two-stage approaches": [[18, "two-stage-approaches"]], "Unit tests": [[2, "unit-tests"]], "Use your own datasets": [[16, "use-your-own-datasets"]], "Using your ONNX exported model": [[17, "using-your-onnx-exported-model"]], "Via Conda (Only for Linux)": [[3, "via-conda-only-for-linux"]], "Via Git": [[3, "via-git"]], "Via Python Package": [[3, "via-python-package"]], "Visualization": [[10, "visualization"]], "What should I do with the output?": [[18, "what-should-i-do-with-the-output"]], "Word": [[7, "word"]], "docTR Notebooks": [[11, null]], "docTR Vocabs": [[6, "id62"]], "docTR: Document Text Recognition": [[4, null]], "doctr.contrib": [[5, null]], "doctr.datasets": [[6, null], [6, "datasets"]], "doctr.io": [[7, null]], "doctr.models": [[8, null]], "doctr.models.classification": [[8, "doctr-models-classification"]], "doctr.models.detection": [[8, "doctr-models-detection"]], "doctr.models.factory": [[8, "doctr-models-factory"]], "doctr.models.recognition": [[8, "doctr-models-recognition"]], "doctr.models.zoo": [[8, "doctr-models-zoo"]], "doctr.transforms": [[9, null]], "doctr.utils": [[10, null]], "v0.1.0 (2021-03-05)": [[0, "v0-1-0-2021-03-05"]], "v0.1.1 (2021-03-18)": [[0, "v0-1-1-2021-03-18"]], "v0.2.0 (2021-05-11)": [[0, "v0-2-0-2021-05-11"]], "v0.2.1 (2021-05-28)": [[0, "v0-2-1-2021-05-28"]], "v0.3.0 (2021-07-02)": [[0, "v0-3-0-2021-07-02"]], "v0.3.1 (2021-08-27)": [[0, "v0-3-1-2021-08-27"]], "v0.4.0 (2021-10-01)": [[0, "v0-4-0-2021-10-01"]], "v0.4.1 (2021-11-22)": [[0, "v0-4-1-2021-11-22"]], "v0.5.0 (2021-12-31)": [[0, "v0-5-0-2021-12-31"]], "v0.5.1 (2022-03-22)": [[0, "v0-5-1-2022-03-22"]], "v0.6.0 (2022-09-29)": [[0, "v0-6-0-2022-09-29"]], "v0.7.0 (2023-09-09)": [[0, "v0-7-0-2023-09-09"]], "v0.8.0 (2024-02-28)": [[0, "v0-8-0-2024-02-28"]], "v0.8.1 (2024-03-04)": [[0, "v0-8-1-2024-03-04"]]}, "docnames": ["changelog", "contributing/code_of_conduct", "contributing/contributing", "getting_started/installing", "index", "modules/contrib", "modules/datasets", "modules/io", "modules/models", "modules/transforms", "modules/utils", "notebooks", "using_doctr/custom_models_training", "using_doctr/running_on_aws", "using_doctr/sharing_models", "using_doctr/using_contrib_modules", "using_doctr/using_datasets", "using_doctr/using_model_export", "using_doctr/using_models"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1}, "filenames": ["changelog.rst", "contributing/code_of_conduct.md", "contributing/contributing.md", "getting_started/installing.rst", "index.rst", "modules/contrib.rst", "modules/datasets.rst", "modules/io.rst", "modules/models.rst", "modules/transforms.rst", "modules/utils.rst", "notebooks.rst", "using_doctr/custom_models_training.rst", "using_doctr/running_on_aws.rst", "using_doctr/sharing_models.rst", "using_doctr/using_contrib_modules.rst", "using_doctr/using_datasets.rst", "using_doctr/using_model_export.rst", "using_doctr/using_models.rst"], "indexentries": {"artefact (class in doctr.io)": [[7, "doctr.io.Artefact", false]], "block (class in doctr.io)": [[7, "doctr.io.Block", false]], "channelshuffle (class in doctr.transforms)": [[9, "doctr.transforms.ChannelShuffle", false]], "charactergenerator (class in doctr.datasets)": [[6, "doctr.datasets.CharacterGenerator", false]], "colorinversion (class in doctr.transforms)": [[9, "doctr.transforms.ColorInversion", false]], "compose (class in doctr.transforms)": [[9, "doctr.transforms.Compose", false]], "cord (class in doctr.datasets)": [[6, "doctr.datasets.CORD", false]], "crnn_mobilenet_v3_large() (in module doctr.models.recognition)": [[8, "doctr.models.recognition.crnn_mobilenet_v3_large", false]], "crnn_mobilenet_v3_small() (in module doctr.models.recognition)": [[8, "doctr.models.recognition.crnn_mobilenet_v3_small", false]], "crnn_vgg16_bn() (in module doctr.models.recognition)": [[8, "doctr.models.recognition.crnn_vgg16_bn", false]], "crop_orientation_predictor() (in module doctr.models.classification)": [[8, "doctr.models.classification.crop_orientation_predictor", false]], "dataloader (class in doctr.datasets.loader)": [[6, "doctr.datasets.loader.DataLoader", false]], "db_mobilenet_v3_large() (in module doctr.models.detection)": [[8, "doctr.models.detection.db_mobilenet_v3_large", false]], "db_resnet50() (in module doctr.models.detection)": [[8, "doctr.models.detection.db_resnet50", false]], "decode_img_as_tensor() (in module doctr.io)": [[7, "doctr.io.decode_img_as_tensor", false]], "detection_predictor() (in module doctr.models.detection)": [[8, "doctr.models.detection.detection_predictor", false]], "detectiondataset (class in doctr.datasets)": [[6, "doctr.datasets.DetectionDataset", false]], "detectionmetric (class in doctr.utils.metrics)": [[10, "doctr.utils.metrics.DetectionMetric", false]], "docartefacts (class in doctr.datasets)": [[6, "doctr.datasets.DocArtefacts", false]], "document (class in doctr.io)": [[7, "doctr.io.Document", false]], "documentfile (class in doctr.io)": [[7, "doctr.io.DocumentFile", false]], "encode_sequences() (in module doctr.datasets)": [[6, "doctr.datasets.encode_sequences", false]], "fast_base() (in module doctr.models.detection)": [[8, "doctr.models.detection.fast_base", false]], "fast_small() (in module doctr.models.detection)": [[8, "doctr.models.detection.fast_small", false]], "fast_tiny() (in module doctr.models.detection)": [[8, "doctr.models.detection.fast_tiny", false]], "from_hub() (in module doctr.models.factory)": [[8, "doctr.models.factory.from_hub", false]], "from_images() (doctr.io.documentfile class method)": [[7, "doctr.io.DocumentFile.from_images", false]], "from_pdf() (doctr.io.documentfile class method)": [[7, "doctr.io.DocumentFile.from_pdf", false]], "from_url() (doctr.io.documentfile class method)": [[7, "doctr.io.DocumentFile.from_url", false]], "funsd (class in doctr.datasets)": [[6, "doctr.datasets.FUNSD", false]], "gaussianblur (class in doctr.transforms)": [[9, "doctr.transforms.GaussianBlur", false]], "gaussiannoise (class in doctr.transforms)": [[9, "doctr.transforms.GaussianNoise", false]], "ic03 (class in doctr.datasets)": [[6, "doctr.datasets.IC03", false]], "ic13 (class in doctr.datasets)": [[6, "doctr.datasets.IC13", false]], "iiit5k (class in doctr.datasets)": [[6, "doctr.datasets.IIIT5K", false]], "iiithws (class in doctr.datasets)": [[6, "doctr.datasets.IIITHWS", false]], "imgur5k (class in doctr.datasets)": [[6, "doctr.datasets.IMGUR5K", false]], "kie_predictor() (in module doctr.models)": [[8, "doctr.models.kie_predictor", false]], "lambdatransformation (class in doctr.transforms)": [[9, "doctr.transforms.LambdaTransformation", false]], "line (class in doctr.io)": [[7, "doctr.io.Line", false]], "linknet_resnet18() (in module doctr.models.detection)": [[8, "doctr.models.detection.linknet_resnet18", false]], "linknet_resnet34() (in module doctr.models.detection)": [[8, "doctr.models.detection.linknet_resnet34", false]], "linknet_resnet50() (in module doctr.models.detection)": [[8, "doctr.models.detection.linknet_resnet50", false]], "localizationconfusion (class in doctr.utils.metrics)": [[10, "doctr.utils.metrics.LocalizationConfusion", false]], "login_to_hub() (in module doctr.models.factory)": [[8, "doctr.models.factory.login_to_hub", false]], "magc_resnet31() (in module doctr.models.classification)": [[8, "doctr.models.classification.magc_resnet31", false]], "master() (in module doctr.models.recognition)": [[8, "doctr.models.recognition.master", false]], "mjsynth (class in doctr.datasets)": [[6, "doctr.datasets.MJSynth", false]], "mobilenet_v3_large() (in module doctr.models.classification)": [[8, "doctr.models.classification.mobilenet_v3_large", false]], "mobilenet_v3_large_r() (in module doctr.models.classification)": [[8, "doctr.models.classification.mobilenet_v3_large_r", false]], "mobilenet_v3_small() (in module doctr.models.classification)": [[8, "doctr.models.classification.mobilenet_v3_small", false]], "mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)": [[8, "doctr.models.classification.mobilenet_v3_small_crop_orientation", false]], "mobilenet_v3_small_page_orientation() (in module doctr.models.classification)": [[8, "doctr.models.classification.mobilenet_v3_small_page_orientation", false]], "mobilenet_v3_small_r() (in module doctr.models.classification)": [[8, "doctr.models.classification.mobilenet_v3_small_r", false]], "normalize (class in doctr.transforms)": [[9, "doctr.transforms.Normalize", false]], "ocr_predictor() (in module doctr.models)": [[8, "doctr.models.ocr_predictor", false]], "ocrdataset (class in doctr.datasets)": [[6, "doctr.datasets.OCRDataset", false]], "ocrmetric (class in doctr.utils.metrics)": [[10, "doctr.utils.metrics.OCRMetric", false]], "oneof (class in doctr.transforms)": [[9, "doctr.transforms.OneOf", false]], "page (class in doctr.io)": [[7, "doctr.io.Page", false]], "page_orientation_predictor() (in module doctr.models.classification)": [[8, "doctr.models.classification.page_orientation_predictor", false]], "parseq() (in module doctr.models.recognition)": [[8, "doctr.models.recognition.parseq", false]], "push_to_hf_hub() (in module doctr.models.factory)": [[8, "doctr.models.factory.push_to_hf_hub", false]], "randomapply (class in doctr.transforms)": [[9, "doctr.transforms.RandomApply", false]], "randombrightness (class in doctr.transforms)": [[9, "doctr.transforms.RandomBrightness", false]], "randomcontrast (class in doctr.transforms)": [[9, "doctr.transforms.RandomContrast", false]], "randomcrop (class in doctr.transforms)": [[9, "doctr.transforms.RandomCrop", false]], "randomgamma (class in doctr.transforms)": [[9, "doctr.transforms.RandomGamma", false]], "randomhorizontalflip (class in doctr.transforms)": [[9, "doctr.transforms.RandomHorizontalFlip", false]], "randomhue (class in doctr.transforms)": [[9, "doctr.transforms.RandomHue", false]], "randomjpegquality (class in doctr.transforms)": [[9, "doctr.transforms.RandomJpegQuality", false]], "randomresize (class in doctr.transforms)": [[9, "doctr.transforms.RandomResize", false]], "randomrotate (class in doctr.transforms)": [[9, "doctr.transforms.RandomRotate", false]], "randomsaturation (class in doctr.transforms)": [[9, "doctr.transforms.RandomSaturation", false]], "randomshadow (class in doctr.transforms)": [[9, "doctr.transforms.RandomShadow", false]], "read_html() (in module doctr.io)": [[7, "doctr.io.read_html", false]], "read_img_as_numpy() (in module doctr.io)": [[7, "doctr.io.read_img_as_numpy", false]], "read_img_as_tensor() (in module doctr.io)": [[7, "doctr.io.read_img_as_tensor", false]], "read_pdf() (in module doctr.io)": [[7, "doctr.io.read_pdf", false]], "recognition_predictor() (in module doctr.models.recognition)": [[8, "doctr.models.recognition.recognition_predictor", false]], "recognitiondataset (class in doctr.datasets)": [[6, "doctr.datasets.RecognitionDataset", false]], "resize (class in doctr.transforms)": [[9, "doctr.transforms.Resize", false]], "resnet18() (in module doctr.models.classification)": [[8, "doctr.models.classification.resnet18", false]], "resnet31() (in module doctr.models.classification)": [[8, "doctr.models.classification.resnet31", false]], "resnet34() (in module doctr.models.classification)": [[8, "doctr.models.classification.resnet34", false]], "resnet50() (in module doctr.models.classification)": [[8, "doctr.models.classification.resnet50", false]], "sar_resnet31() (in module doctr.models.recognition)": [[8, "doctr.models.recognition.sar_resnet31", false]], "show() (doctr.io.document method)": [[7, "doctr.io.Document.show", false]], "show() (doctr.io.page method)": [[7, "doctr.io.Page.show", false]], "sroie (class in doctr.datasets)": [[6, "doctr.datasets.SROIE", false]], "summary() (doctr.utils.metrics.detectionmetric method)": [[10, "doctr.utils.metrics.DetectionMetric.summary", false]], "summary() (doctr.utils.metrics.localizationconfusion method)": [[10, "doctr.utils.metrics.LocalizationConfusion.summary", false]], "summary() (doctr.utils.metrics.ocrmetric method)": [[10, "doctr.utils.metrics.OCRMetric.summary", false]], "summary() (doctr.utils.metrics.textmatch method)": [[10, "doctr.utils.metrics.TextMatch.summary", false]], "svhn (class in doctr.datasets)": [[6, "doctr.datasets.SVHN", false]], "svt (class in doctr.datasets)": [[6, "doctr.datasets.SVT", false]], "synthtext (class in doctr.datasets)": [[6, "doctr.datasets.SynthText", false]], "textmatch (class in doctr.utils.metrics)": [[10, "doctr.utils.metrics.TextMatch", false]], "textnet_base() (in module doctr.models.classification)": [[8, "doctr.models.classification.textnet_base", false]], "textnet_small() (in module doctr.models.classification)": [[8, "doctr.models.classification.textnet_small", false]], "textnet_tiny() (in module doctr.models.classification)": [[8, "doctr.models.classification.textnet_tiny", false]], "togray (class in doctr.transforms)": [[9, "doctr.transforms.ToGray", false]], "update() (doctr.utils.metrics.detectionmetric method)": [[10, "doctr.utils.metrics.DetectionMetric.update", false]], "update() (doctr.utils.metrics.localizationconfusion method)": [[10, "doctr.utils.metrics.LocalizationConfusion.update", false]], "update() (doctr.utils.metrics.ocrmetric method)": [[10, "doctr.utils.metrics.OCRMetric.update", false]], "update() (doctr.utils.metrics.textmatch method)": [[10, "doctr.utils.metrics.TextMatch.update", false]], "vgg16_bn_r() (in module doctr.models.classification)": [[8, "doctr.models.classification.vgg16_bn_r", false]], "visualize_page() (in module doctr.utils.visualization)": [[10, "doctr.utils.visualization.visualize_page", false]], "vit_b() (in module doctr.models.classification)": [[8, "doctr.models.classification.vit_b", false]], "vit_s() (in module doctr.models.classification)": [[8, "doctr.models.classification.vit_s", false]], "vitstr_base() (in module doctr.models.recognition)": [[8, "doctr.models.recognition.vitstr_base", false]], "vitstr_small() (in module doctr.models.recognition)": [[8, "doctr.models.recognition.vitstr_small", false]], "wildreceipt (class in doctr.datasets)": [[6, "doctr.datasets.WILDRECEIPT", false]], "word (class in doctr.io)": [[7, "doctr.io.Word", false]], "wordgenerator (class in doctr.datasets)": [[6, "doctr.datasets.WordGenerator", false]]}, "objects": {"doctr.datasets": [[6, 0, 1, "", "CORD"], [6, 0, 1, "", "CharacterGenerator"], [6, 0, 1, "", "DetectionDataset"], [6, 0, 1, "", "DocArtefacts"], [6, 0, 1, "", "FUNSD"], [6, 0, 1, "", "IC03"], [6, 0, 1, "", "IC13"], [6, 0, 1, "", "IIIT5K"], [6, 0, 1, "", "IIITHWS"], [6, 0, 1, "", "IMGUR5K"], [6, 0, 1, "", "MJSynth"], [6, 0, 1, "", "OCRDataset"], [6, 0, 1, "", "RecognitionDataset"], [6, 0, 1, "", "SROIE"], [6, 0, 1, "", "SVHN"], [6, 0, 1, "", "SVT"], [6, 0, 1, "", "SynthText"], [6, 0, 1, "", "WILDRECEIPT"], [6, 0, 1, "", "WordGenerator"], [6, 1, 1, "", "encode_sequences"]], "doctr.datasets.loader": [[6, 0, 1, "", "DataLoader"]], "doctr.io": [[7, 0, 1, "", "Artefact"], [7, 0, 1, "", "Block"], [7, 0, 1, "", "Document"], [7, 0, 1, "", "DocumentFile"], [7, 0, 1, "", "Line"], [7, 0, 1, "", "Page"], [7, 0, 1, "", "Word"], [7, 1, 1, "", "decode_img_as_tensor"], [7, 1, 1, "", "read_html"], [7, 1, 1, "", "read_img_as_numpy"], [7, 1, 1, "", "read_img_as_tensor"], [7, 1, 1, "", "read_pdf"]], "doctr.io.Document": [[7, 2, 1, "", "show"]], "doctr.io.DocumentFile": [[7, 2, 1, "", "from_images"], [7, 2, 1, "", "from_pdf"], [7, 2, 1, "", "from_url"]], "doctr.io.Page": [[7, 2, 1, "", "show"]], "doctr.models": [[8, 1, 1, "", "kie_predictor"], [8, 1, 1, "", "ocr_predictor"]], "doctr.models.classification": [[8, 1, 1, "", "crop_orientation_predictor"], [8, 1, 1, "", "magc_resnet31"], [8, 1, 1, "", "mobilenet_v3_large"], [8, 1, 1, "", "mobilenet_v3_large_r"], [8, 1, 1, "", "mobilenet_v3_small"], [8, 1, 1, "", "mobilenet_v3_small_crop_orientation"], [8, 1, 1, "", "mobilenet_v3_small_page_orientation"], [8, 1, 1, "", "mobilenet_v3_small_r"], [8, 1, 1, "", "page_orientation_predictor"], [8, 1, 1, "", "resnet18"], [8, 1, 1, "", "resnet31"], [8, 1, 1, "", "resnet34"], [8, 1, 1, "", "resnet50"], [8, 1, 1, "", "textnet_base"], [8, 1, 1, "", "textnet_small"], [8, 1, 1, "", "textnet_tiny"], [8, 1, 1, "", "vgg16_bn_r"], [8, 1, 1, "", "vit_b"], [8, 1, 1, "", "vit_s"]], "doctr.models.detection": [[8, 1, 1, "", "db_mobilenet_v3_large"], [8, 1, 1, "", "db_resnet50"], [8, 1, 1, "", "detection_predictor"], [8, 1, 1, "", "fast_base"], [8, 1, 1, "", "fast_small"], [8, 1, 1, "", "fast_tiny"], [8, 1, 1, "", "linknet_resnet18"], [8, 1, 1, "", "linknet_resnet34"], [8, 1, 1, "", "linknet_resnet50"]], "doctr.models.factory": [[8, 1, 1, "", "from_hub"], [8, 1, 1, "", "login_to_hub"], [8, 1, 1, "", "push_to_hf_hub"]], "doctr.models.recognition": [[8, 1, 1, "", "crnn_mobilenet_v3_large"], [8, 1, 1, "", "crnn_mobilenet_v3_small"], [8, 1, 1, "", "crnn_vgg16_bn"], [8, 1, 1, "", "master"], [8, 1, 1, "", "parseq"], [8, 1, 1, "", "recognition_predictor"], [8, 1, 1, "", "sar_resnet31"], [8, 1, 1, "", "vitstr_base"], [8, 1, 1, "", "vitstr_small"]], "doctr.transforms": [[9, 0, 1, "", "ChannelShuffle"], [9, 0, 1, "", "ColorInversion"], [9, 0, 1, "", "Compose"], [9, 0, 1, "", "GaussianBlur"], [9, 0, 1, "", "GaussianNoise"], [9, 0, 1, "", "LambdaTransformation"], [9, 0, 1, "", "Normalize"], [9, 0, 1, "", "OneOf"], [9, 0, 1, "", "RandomApply"], [9, 0, 1, "", "RandomBrightness"], [9, 0, 1, "", "RandomContrast"], [9, 0, 1, "", "RandomCrop"], [9, 0, 1, "", "RandomGamma"], [9, 0, 1, "", "RandomHorizontalFlip"], [9, 0, 1, "", "RandomHue"], [9, 0, 1, "", "RandomJpegQuality"], [9, 0, 1, "", "RandomResize"], [9, 0, 1, "", "RandomRotate"], [9, 0, 1, "", "RandomSaturation"], [9, 0, 1, "", "RandomShadow"], [9, 0, 1, "", "Resize"], [9, 0, 1, "", "ToGray"]], "doctr.utils.metrics": [[10, 0, 1, "", "DetectionMetric"], [10, 0, 1, "", "LocalizationConfusion"], [10, 0, 1, "", "OCRMetric"], [10, 0, 1, "", "TextMatch"]], "doctr.utils.metrics.DetectionMetric": [[10, 2, 1, "", "summary"], [10, 2, 1, "", "update"]], "doctr.utils.metrics.LocalizationConfusion": [[10, 2, 1, "", "summary"], [10, 2, 1, "", "update"]], "doctr.utils.metrics.OCRMetric": [[10, 2, 1, "", "summary"], [10, 2, 1, "", "update"]], "doctr.utils.metrics.TextMatch": [[10, 2, 1, "", "summary"], [10, 2, 1, "", "update"]], "doctr.utils.visualization": [[10, 1, 1, "", "visualize_page"]]}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method"}, "terms": {"": [1, 7, 8, 10, 14, 17], "0": [1, 3, 6, 9, 10, 12, 15, 16, 18], "00": 18, "01": 18, "0123456789": 6, "0123456789abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 6, "0123456789\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 6, "02": [], "02562": 8, "03": 18, "035": 18, "0361328125": 18, "04": 18, "05": 18, "06": 18, "06640625": 18, "07": 18, "08": [9, 18], "09": 18, "0966796875": 18, "1": [3, 6, 7, 8, 9, 10, 12, 16, 18], "10": [6, 10, 18], "100": [6, 9, 10, 16, 18], "1000": 18, "101": 6, "1024": [8, 12, 18], "104": 6, "106": 6, "108": 6, "1095": 16, "11": 18, "110": 10, "1107": 16, "114": 6, "115": [], "1156": 16, "116": 6, "118": 6, "11800h": 18, "11th": 18, "12": [3, 18], "120": 6, "123": 6, "126": 6, "1268": 16, "128": [8, 12, 17, 18], "13": 18, "130": 6, "13068": 16, "131": 6, "1337891": 16, "1357421875": 18, "1396484375": 18, "14": 18, "1420": 18, "14470v1": 6, "149": 16, "15": 18, "150": [10, 18], "1552": 18, "16": [8, 17, 18], "1630859375": 18, "1684": 18, "16x16": 8, "17": 18, "1778": 18, "1782": 18, "18": [8, 18], "185546875": 18, "1900": 18, "1910": 8, "19342": 16, "19370": 16, "195": 6, "19598": 16, "199": 18, "1999": 18, "2": [3, 4, 6, 7, 9, 15, 18], "20": 18, "200": 10, "2000": 16, "2003": [4, 6], "2012": 6, "2013": [4, 6], "2015": 6, "2019": 4, "2023": [], "207901": 16, "21": 18, "2103": 6, "2186": 16, "21888": 16, "22": 18, "224": [8, 9], "225": 9, "22672": 16, "229": [9, 16], "23": 18, "233": 16, "234": 6, "236": [], "24": 18, "246": 16, "249": 16, "25": 18, "2504": 18, "255": [7, 8, 9, 10, 18], "256": 8, "257": 16, "26": 18, "26032": 16, "264": 12, "27": 18, "2700": 16, "2710": 18, "2749": 12, "28": 18, "287": 12, "29": 18, "296": 12, "299": 12, "2d": 18, "3": [3, 4, 7, 8, 9, 10, 17, 18], "30": 18, "300": 16, "3000": 16, "301": 12, "30595": 18, "30ghz": 18, "31": 8, "32": [6, 8, 9, 12, 16, 17, 18], "3232421875": 18, "33": [9, 18], "33402": 16, "33608": 16, "34": [8, 18], "340": 18, "3456": 18, "35": [], "3515625": 18, "36": 18, "360": 16, "37": [6, 18], "38": 18, "39": 18, "4": [8, 9, 10, 18], "40": 18, "406": 9, "41": 18, "42": 18, "43": 18, "44": 18, "45": 18, "456": 9, "46": 18, "47": 18, "472": 16, "48": [6, 18], "485": 9, "49": 18, "49377": 16, "5": [6, 9, 10, 15, 18], "50": [8, 16, 18], "51": 18, "51171875": 18, "512": 8, "52": [6, 18], "529": 18, "53": 18, "54": 18, "540": 18, "5478515625": 18, "55": 18, "56": 18, "57": 18, "58": 18, "580": 18, "5810546875": 18, "583": 18, "59": 18, "597": 18, "5k": [4, 6], "5m": 18, "6": [9, 18], "60": 9, "600": [8, 10, 18], "61": 18, "62": 18, "626": 16, "63": 18, "64": [8, 9, 18], "641": 18, "647": 16, "65": 18, "66": 18, "67": 18, "68": 18, "69": 18, "693": 12, "694": 12, "695": 12, "6m": 18, "7": 18, "70": [6, 10, 18], "707470": 16, "71": [6, 18], "7100000": 16, "7141797": 16, "7149": 16, "72": 18, "72dpi": 7, "73": 18, "73257": 16, "74": 18, "75": [9, 18], "7581382": 16, "76": 18, "77": 18, "772": 12, "772875": 16, "78": 18, "785": 12, "79": 18, "793533": 16, "796": 16, "798": 12, "7m": 18, "8": [8, 9, 18], "80": 18, "800": [8, 10, 16, 18], "81": 18, "82": 18, "83": 18, "84": 18, "849": 16, "85": 18, "8564453125": 18, "857": 18, "85875": 16, "86": 18, "8603515625": 18, "87": 18, "8707": 16, "88": 18, "89": 18, "9": [3, 9, 18], "90": 18, "90k": 6, "90kdict32px": 6, "91": 18, "914085328578949": 18, "92": 18, "93": 18, "94": [6, 18], "95": [10, 18], "9578408598899841": 18, "96": 18, "97": 18, "98": 18, "99": 18, "9949972033500671": 18, "A": [1, 2, 4, 6, 7, 8, 11, 17], "As": 2, "Be": 18, "Being": 1, "By": 13, "For": [1, 2, 3, 12, 18], "If": [2, 7, 8, 12, 18], "In": [2, 6, 16], "It": [9, 14, 15, 17], "Its": [4, 8], "No": [1, 18], "Of": 6, "Or": [15, 17], "The": [1, 2, 6, 7, 10, 13, 15, 17, 18], "Then": 8, "To": [2, 3, 13, 14, 15, 17, 18], "_": [1, 6, 8], "__call__": 18, "_build": 2, "_i": 10, "ab": 6, "abc": 17, "abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz": 6, "abdef": [6, 16], "abl": [16, 18], "about": [1, 16, 18], "abov": 18, "abstract": [], "abstractdataset": 6, "abus": 1, "accept": 1, "access": [4, 7, 16, 18], "account": [1, 14], "accur": 18, "accuraci": 10, "achiev": 17, "act": 1, "action": 1, "activ": 4, "ad": [2, 8, 9], "adapt": 1, "add": [9, 10, 14, 18], "add_hook": 18, "add_label": 10, "addit": [2, 3, 7, 15], "addition": [2, 18], "address": [1, 7], "adjust": 9, "advanc": 1, "advantag": 17, "advis": 2, "aesthet": [4, 6], "affect": 1, "after": [14, 18], "ag": 1, "again": 8, "aggreg": [10, 16], "aggress": 1, "align": [1, 7, 9], "all": [1, 2, 5, 6, 7, 9, 10, 15, 16, 18], "allow": [1, 17], "along": 18, "alreadi": [2, 17], "also": [1, 8, 14, 15, 16, 18], "alwai": 16, "an": [1, 2, 4, 6, 7, 8, 10, 15, 17, 18], "analysi": [7, 15], "ancient_greek": 6, "andrej": [], "angl": [7, 9], "ani": [1, 6, 7, 8, 9, 10, 17, 18], "annot": 6, "anot": 16, "anoth": [8, 12, 16], "answer": 1, "anyascii": 10, "anyon": 4, "anyth": 15, "api": [2, 4], "apolog": 1, "apologi": 1, "app": 2, "appear": 1, "appli": [1, 6, 9], "applic": [4, 8], "appoint": 1, "appreci": 14, "appropri": [1, 2, 18], "ar": [1, 2, 3, 5, 6, 7, 9, 10, 11, 15, 16, 18], "arab": 6, "arabic_diacrit": 6, "arabic_lett": 6, "arabic_punctu": 6, "arbitrarili": [4, 8], "arch": [8, 14], "architectur": [4, 8, 14, 15], "area": 18, "arg": [], "argument": [6, 7, 8, 10, 18], "around": 1, "arrai": [7, 9, 10], "art": [4, 15], "artefact": [10, 11, 15, 18], "artefact_typ": 7, "artefactdetector": [], "articl": [], "artifici": [4, 6], "arxiv": [6, 8], "asarrai": 10, "ascii_lett": 6, "aspect": [4, 8, 9, 18], "assess": 10, "assign": 10, "associ": 7, "assum": 8, "assume_straight_pag": [8, 18], "astyp": [8, 10, 18], "attack": 1, "attend": [4, 8], "attent": [1, 8], "autom": 4, "automat": 18, "autoregress": [4, 8], "avail": [1, 4, 5, 9], "averag": [9, 18], "avoid": [1, 3], "aw": [4, 18], "awar": 18, "azur": 18, "b": [8, 10, 18], "b_j": 10, "back": 2, "backbon": 8, "backend": 18, "background": 16, "bangla": 6, "bar": 15, "bar_cod": 16, "baranovskij": [], "base": [4, 8, 15], "baselin": [4, 8, 18], "batch": [6, 8, 9, 15, 16, 18], "batch_siz": [6, 12, 15, 16, 17], "bblanchon": 3, "bbox": 18, "becaus": 13, "been": [2, 10, 16, 18], "befor": [6, 8, 9, 18], "begin": 10, "behavior": [1, 18], "being": [10, 18], "belong": 18, "benchmark": 18, "best": 1, "better": [11, 18], "between": [9, 10, 18], "bgr": 7, "bilinear": 9, "bin_thresh": 18, "binar": [4, 8, 18], "binari": [7, 17, 18], "bit": 17, "blank": [], "block": [10, 18], "block_1_1": 18, "blue": [], "blur": 9, "bmvc": 6, "bn": 14, "bodi": [1, 18], "bool": [6, 7, 8, 9, 10], "boolean": [8, 18], "both": [4, 6, 9, 16, 18], "bottom": [8, 18], "bound": [6, 7, 8, 9, 10, 15, 18], "box": [6, 7, 8, 9, 10, 15, 16, 18], "box_thresh": 18, "brew": [], "bright": 9, "broadcast": [], "browser": [2, 4], "build": [2, 3, 17], "built": 2, "byte": [7, 18], "c": [3, 7, 10], "c_j": 10, "cach": [2, 6, 13], "cache_sampl": 6, "cairo": [], "call": 17, "callabl": [6, 9], "can": [2, 3, 12, 13, 14, 15, 16, 18], "capabl": [2, 11, 18], "case": [6, 10], "cf": 18, "cfg": 18, "challeng": 6, "challenge2_test_task12_imag": 6, "challenge2_test_task1_gt": 6, "challenge2_training_task12_imag": 6, "challenge2_training_task1_gt": 6, "chang": [13, 18], "channel": [1, 2, 7, 9], "channel_prior": 3, "channelshuffl": 9, "charact": [4, 6, 7, 10, 16, 18], "charactergener": [6, 16], "characterist": 1, "charg": 18, "charset": 18, "chart": 7, "check": [2, 14, 18], "checkpoint": 8, "chip": 3, "christian": [], "ci": 2, "clarifi": 1, "clariti": 1, "class": [1, 6, 7, 9, 10, 18], "class_nam": 12, "classif": 16, "classif_mobilenet_v3_smal": [], "classmethod": 7, "clear": 2, "clone": 3, "close": 2, "co": 14, "code": [4, 7, 15], "codecov": 2, "colab": 11, "collate_fn": 6, "collect": [7, 15], "color": 9, "colorinvers": 9, "column": 7, "com": [1, 3, 7, 8, 14], "combin": 18, "come": [], "command": [2, 15], "comment": 1, "commit": 1, "common": [1, 9, 10, 17], "commun": 1, "compar": 4, "comparison": [10, 18], "competit": 6, "compil": [11, 18], "complaint": 1, "complementari": 10, "complet": 2, "compon": 18, "compos": [6, 18], "comprehens": 18, "comput": [6, 10, 17, 18], "conf_threshold": 15, "confid": [7, 18], "config": [3, 8], "configur": 8, "confus": 10, "consecut": [9, 18], "consequ": 1, "consid": [1, 2, 6, 7, 10, 18], "consist": 18, "consolid": [4, 6], "constant": 9, "construct": 1, "consum": [], "contact": 1, "contain": [5, 6, 16], "content": [6, 7, 18], "context": 8, "contib": 3, "continu": 1, "contrast": 9, "contrast_factor": 9, "contrib": [3, 15], "contribut": 1, "contributor": 2, "convers": 7, "convert": [7, 9], "convert_target_to_rel": [], "convolut": 8, "cool": [], "coordin": [7, 18], "cord": [4, 6, 16, 18], "core": [10, 18], "corner": 18, "correct": 9, "correspond": [3, 7, 9, 18], "could": [1, 15], "counterpart": 10, "cover": 2, "coverag": 2, "cpu": [4, 12, 17], "creat": 14, "crnn": [4, 8, 14], "crnn_mobilenet_v3_larg": [8, 14, 18], "crnn_mobilenet_v3_smal": [8, 17, 18], "crnn_vgg16_bn": [8, 12, 14, 18], "crop": [7, 8, 9, 16, 18], "crop_bboxes_from_imag": [], "crop_orient": [7, 18], "crop_orientation_predictor": 8, "crop_param": [], "croporientationpredictor": [], "cuda": 17, "currenc": 6, "current": [2, 18], "custom": [14, 15, 17, 18], "custom_crop_orientation_model": [], "custom_page_orientation_model": [], "customhook": 18, "cvit": 4, "czczup": 8, "czech": 6, "d": [6, 16], "danish": 6, "data": [4, 6, 7, 9, 10, 12, 14], "dataload": 16, "dataset": [8, 12, 18], "dataset_info": 6, "date": [12, 18], "db": 14, "db_mobilenet_v3_larg": [8, 14, 18], "db_resnet34": 18, "db_resnet50": [8, 12, 14, 18], "db_resnet50_rot": [], "dbnet": [4, 8], "deal": [], "decis": 1, "decod": 7, "decode_img_as_tensor": 7, "decode_sequ": [], "dedic": 17, "deem": 1, "deep": [8, 18], "def": 18, "default": [3, 7, 12, 13, 18], "defer": 16, "defin": [10, 17], "degre": [7, 9], "degress": 7, "delet": 2, "delimit": 18, "delta": 9, "demo": [2, 4], "demonstr": 1, "depend": [2, 3, 4, 18], "deploi": 2, "deploy": 4, "derogatori": 1, "describ": 8, "descript": 11, "design": 9, "desir": 7, "det_arch": [8, 12, 14, 17], "det_b": 18, "det_model": [12, 14, 17], "det_param": 12, "det_predictor": [12, 18], "detail": [12, 18], "detect": [6, 7, 10, 11, 12, 15], "detect_languag": 8, "detect_orient": 8, "detection_predictor": [8, 18], "detection_task": [], "detectiondataset": [6, 16], "detectionmetr": 10, "detectionpredictor": [8, 12], "detector": [4, 8, 15], "deterior": 8, "determin": 1, "dev": [2, 13], "develop": 3, "deviat": 9, "devic": 17, "dict": [7, 10, 18], "dictionari": [7, 10], "differ": 1, "differenti": [4, 8], "digit": [4, 6, 16], "dimens": [7, 10, 18], "dimension": 9, "direct": 6, "directli": [14, 18], "directori": [2, 13], "disabl": [1, 13, 18], "disable_crop_orient": [], "disable_page_orient": [], "disclaim": 18, "discuss": 2, "disparag": 1, "displai": [7, 10], "display_artefact": 10, "distribut": 9, "div": 18, "divers": 1, "divid": 7, "do": [2, 3, 8], "doc": [2, 7, 15, 17, 18], "docartefact": [6, 16], "docstr": 2, "doctr": [3, 12, 13, 14, 15, 16, 17, 18], "doctr_cache_dir": 13, "doctr_multiprocessing_dis": 13, "document": [6, 8, 10, 11, 15, 16, 17, 18], "documentbuild": 18, "documentfil": [7, 14, 15, 17], "doesn": 17, "don": [12, 18], "done": 9, "download": [6, 16], "download_from_url": [], "downsiz": 8, "draw": 9, "draw_proba": [], "drop": 6, "drop_last": 6, "dtype": [7, 8, 9, 10, 17], "dual": [4, 6], "dummi": 14, "dummy_img": 18, "dummy_input": 17, "dure": 1, "dutch": 6, "dynam": [6, 15], "dynamic_seq_length": 6, "e": [1, 2, 3, 7, 8], "each": [4, 6, 7, 8, 9, 10, 16, 18], "eas": 2, "easi": [4, 10, 14, 17], "easili": [7, 10, 12, 14, 16, 18], "econom": 1, "edit": 1, "educ": 1, "effect": [], "effici": [2, 4, 6, 8], "either": [10, 18], "element": [6, 7, 8, 18], "els": [2, 15], "email": 1, "empathi": 1, "en": 18, "enabl": [6, 7], "enclos": 7, "encod": [4, 6, 7, 8, 18], "encode_sequ": 6, "encode_str": [], "encount": 2, "encrypt": 7, "end": [4, 6, 8, 10], "english": [6, 16], "enough": [2, 18], "ensur": 2, "entri": 6, "environ": [1, 13], "eo": 6, "equiv": 18, "estim": 8, "etc": [7, 15], "ethnic": 1, "evalu": [16, 18], "event": 1, "everyon": 1, "everyth": [2, 18], "exact": [10, 18], "exampl": [1, 2, 4, 6, 8, 14, 18], "exchang": 17, "execut": 18, "exist": 14, "expand": 9, "expect": [7, 9, 10], "experi": 1, "explan": [1, 18], "explicit": 1, "exploit": [4, 8], "export": [7, 8, 10, 11, 15, 18], "export_as_straight_box": [8, 18], "export_as_xml": 18, "export_model_to_onnx": 17, "express": [1, 9], "extens": 7, "extern": [1, 16], "extra": [], "extract": [4, 6], "extractor": 8, "f_": 10, "f_a": 10, "factor": 9, "fair": 1, "fairli": 1, "fals": [6, 7, 8, 9, 10, 12, 18], "famili": [], "faq": 1, "fascan": 14, "fast": [4, 6, 8], "fast_bas": [8, 18], "fast_smal": [8, 18], "fast_tini": [8, 18], "faster": [4, 8, 17], "fasterrcnn_mobilenet_v3_large_fpn": 8, "favorit": 18, "featur": [3, 8, 10, 11, 15], "feedback": 1, "feel": [2, 14], "felix92": 14, "few": [17, 18], "figsiz": 10, "figur": [10, 15], "file": [2, 6], "final": 8, "find": [2, 16], "fine": [], "finnish": 6, "first": [2, 6], "firsthand": 6, "fit": [8, 18], "flag": 18, "flip": 9, "float": [7, 9, 10, 17], "float32": [7, 8, 9, 17], "fn": 9, "focu": 14, "focus": [1, 6], "folder": 6, "follow": [1, 2, 3, 6, 9, 10, 12, 13, 14, 15, 18], "font": 6, "font_famili": 6, "font_siz": [], "foral": 10, "forc": 2, "forg": 3, "form": [4, 6, 18], "format": [7, 10, 12, 16, 17, 18], "forpost": [4, 6], "forum": 2, "found": [], "fp16": 17, "frac": 10, "framework": [3, 14, 16, 18], "free": [1, 2, 14], "french": [6, 12, 14, 18], "friendli": 4, "from": [1, 4, 6, 7, 8, 9, 10, 11, 12, 15, 16, 17, 18], "from_hub": [8, 14], "from_imag": [7, 14, 15, 17], "from_pdf": 7, "from_url": 7, "full": [6, 10, 18], "function": [6, 9, 10, 15], "funsd": [4, 6, 16, 18], "further": 16, "futur": 6, "g": [7, 8], "g_": 10, "g_x": 10, "gallagh": [], "gamma": 9, "gaussian": 9, "gaussianblur": 9, "gaussiannois": 9, "gdk": [], "gen": 18, "gender": 1, "gener": [2, 4, 7, 8], "generic_cyrillic_lett": [], "geom": [], "geometri": [4, 7, 18], "geq": 10, "german": [6, 12, 14], "get": [17, 18], "git": 14, "github": [2, 3, 8, 14], "give": [1, 15], "given": [6, 7, 9, 10, 18], "global": 8, "go": 18, "good": 17, "googl": 2, "googlevis": 4, "gpu": [4, 15, 17], "gracefulli": 1, "graph": [4, 6, 7], "grayscal": 9, "ground": 10, "groung": 10, "group": [4, 18], "gt": 10, "gt_box": 10, "gt_label": 10, "gtk": [], "guid": 2, "guidanc": 16, "gvision": 18, "h": [7, 8, 9], "h_": 10, "ha": [2, 6, 10, 16], "handl": [16, 18], "handwrit": 6, "handwritten": 16, "harass": 1, "hardwar": 18, "harm": 1, "hat": 10, "have": [1, 2, 10, 12, 14, 16, 17, 18], "head": [8, 18], "healthi": 1, "hebrew": 6, "height": [7, 9], "hello": [10, 18], "help": 17, "here": [5, 9, 11, 15, 16, 18], "hf": 8, "hf_hub_download": 8, "high": 7, "higher": [3, 6, 18], "hindi": 6, "hindi_digit": 6, "hocr": 18, "homebrew": [], "hook": 18, "horizont": [7, 9], "hous": 6, "how": [2, 12, 14, 16], "howev": 16, "hsv": 9, "html": [1, 2, 3, 7, 18], "http": [1, 3, 6, 7, 8, 14, 18], "hub": 8, "hue": 9, "huggingfac": 8, "hw": 6, "i": [1, 2, 6, 7, 8, 9, 10, 13, 14, 15, 16, 17], "i7": 18, "ibrahimov": [], "ic03": [4, 6, 16], "ic13": [4, 6, 16], "icdar": [4, 6], "icdar2019": 6, "id": 18, "ident": 1, "identifi": 4, "iiit": [4, 6], "iiit5k": [6, 16], "iiithw": [4, 6, 16], "imag": [4, 6, 7, 8, 9, 10, 14, 15, 16, 18], "imagenet": 8, "imageri": 1, "images_90k_norm": 6, "imagetensor": [], "imagetransform": [], "img": [6, 9, 16, 17], "img_cont": 7, "img_fold": [6, 16], "img_path": 7, "img_transform": 6, "imgur5k": [4, 6, 16], "imgur5k_annot": 6, "imlist": 6, "impact": 1, "implement": [6, 7, 8, 9, 10, 18], "import": [6, 7, 8, 9, 10, 12, 14, 15, 16, 17, 18], "improv": 8, "inappropri": 1, "incid": 1, "includ": [1, 6, 16, 17], "inclus": 1, "increas": 9, "independ": 9, "index": [2, 7], "indic": 10, "individu": 1, "infer": [4, 8, 9, 15], "inform": [1, 2, 4, 6, 16], "initi": [], "input": [2, 7, 8, 9, 17, 18], "input_crop": 8, "input_pag": [8, 10, 18], "input_seq": [], "input_shap": 17, "input_str": [], "input_tensor": 8, "inspir": [1, 9], "instal": [14, 15, 17], "instanc": [1, 18], "instanti": [8, 18], "instead": [6, 7, 8], "insult": 1, "int": [6, 7, 9], "int64": 10, "integ": 10, "integr": [4, 14, 16], "intel": 18, "interact": [1, 7, 10], "interfac": [14, 17], "interoper": 17, "interpol": 9, "interpret": [6, 7], "intersect": 10, "invert": 9, "investig": 1, "invis": 1, "involv": [1, 18], "io": [14, 15, 17], "iou": 10, "iou_thresh": 10, "iou_threshold": 15, "irregular": [4, 8, 16], "isn": 6, "issu": [1, 2, 14], "italian": 6, "iter": [6, 9, 16, 18], "its": [7, 8, 9, 10, 16, 18], "itself": [8, 14], "j": 10, "jame": [], "job": 2, "join": 2, "jpeg": 9, "jpegqual": 9, "jpg": [6, 7, 14, 17], "json": [6, 16, 18], "json_output": 18, "jump": 2, "just": 1, "kei": [4, 6], "kera": [8, 17], "kernel": [4, 8, 9], "kernel_shap": 9, "keywoard": 8, "keyword": [6, 7, 8, 10], "kie": [8, 12], "kie_predictor": [8, 12], "kiepredictor": 8, "kind": 1, "know": [2, 17], "kwarg": [6, 7, 8, 10], "l": 10, "l_j": 10, "label": [6, 10, 15, 16], "label_fil": [6, 16], "label_fold": 6, "label_path": [6, 16], "labels_path": [6, 16], "ladder": 1, "lambda": 9, "lambdatransform": 9, "lang": 18, "languag": [1, 4, 6, 7, 8, 14, 18], "larg": [8, 14], "largest": 10, "last": [3, 6], "latenc": 8, "later": 2, "latest": 18, "latin": 6, "layer": 17, "layout": 18, "lead": 1, "leader": 1, "learn": [1, 4, 8, 17, 18], "least": 3, "left": [10, 18], "legacy_french": 6, "length": [6, 18], "less": [17, 18], "level": [1, 6, 10, 18], "leverag": 11, "lf": 14, "libffi": [], "librari": [2, 3, 11, 12], "light": 4, "lightweight": 17, "like": 1, "limits_": 10, "line": [4, 8, 10, 18], "line_1_1": 18, "link": 12, "linknet": [4, 8], "linknet_resnet18": [8, 12, 17, 18], "linknet_resnet18_rot": [], "linknet_resnet34": [8, 17, 18], "linknet_resnet50": [8, 18], "linux": [], "list": [6, 7, 9, 10, 14], "ll": 10, "load": [4, 6, 8, 15, 17], "load_state_dict": 12, "load_weight": 12, "loc_pr": 18, "local": [2, 4, 6, 8, 10, 16, 18], "localis": 6, "localizationconfus": 10, "locat": [2, 7, 18], "login": 8, "login_to_hub": [8, 14], "logo": [7, 15, 16], "love": 14, "lower": [9, 10, 18], "m": [2, 10, 18], "m1": 3, "macbook": 3, "machin": 17, "maco": [], "made": 4, "magc_resnet31": 8, "mai": [1, 2], "mail": 1, "main": 11, "maintain": 4, "mainten": 2, "make": [1, 2, 10, 13, 14, 17, 18], "mani": [16, 18], "manipul": 18, "map": [6, 8], "map_loc": 12, "mask": [], "mask_label": [], "mask_shap": [], "master": [4, 8, 18], "match": [10, 18], "mathcal": 10, "matplotlib": [7, 10], "max": [6, 9, 10], "max_angl": 9, "max_area": 9, "max_char": [6, 16], "max_delta": 9, "max_font_s": [], "max_gain": 9, "max_gamma": 9, "max_qual": 9, "max_ratio": 9, "maximum": [6, 9], "maxval": [8, 9], "mbox": 10, "mean": [9, 10, 12], "meaniou": 10, "meant": [7, 17], "measur": 18, "media": 1, "median": 8, "meet": 12, "member": 1, "memori": [13, 17], "mention": 18, "merg": 6, "messag": 2, "meta": 18, "metadata": 17, "metal": 3, "method": [7, 9, 18], "metric": [10, 18], "middl": 18, "might": [17, 18], "min": 9, "min_area": 9, "min_char": [6, 16], "min_font_s": [], "min_gain": 9, "min_gamma": 9, "min_qual": 9, "min_ratio": 9, "min_val": 9, "minde": [1, 3, 4, 8], "minim": [2, 4], "minimalist": [4, 8], "minimum": [3, 6, 9, 10, 18], "minval": 9, "miss": 3, "mistak": 1, "mixed_float16": 17, "mixed_precis": 17, "mjsynth": [4, 6, 16], "mnt": 6, "mobilenet": [8, 14], "mobilenet_v3_larg": 8, "mobilenet_v3_large_r": 8, "mobilenet_v3_smal": 8, "mobilenet_v3_small_crop_orient": 8, "mobilenet_v3_small_orient": [], "mobilenet_v3_small_page_orient": 8, "mobilenet_v3_small_r": 8, "mobilenetv3": 8, "modal": [4, 6], "mode": 3, "model": [6, 10, 13, 15, 16], "model_nam": [8, 14, 17], "model_path": [15, 17], "moder": 1, "modif": 2, "modifi": [8, 13, 18], "modul": [3, 7, 8, 9, 10, 18], "moment": [], "more": [2, 16, 18], "moscardi": [], "most": 18, "mozilla": 1, "multi": [4, 8], "multiclass": [], "multilingu": [6, 14], "multipl": [6, 7, 9, 18], "multipli": 9, "multiprocess": 13, "my": 8, "my_awesome_model": 14, "my_hook": 18, "n": [6, 10], "name": [6, 8, 17, 18], "nation": 1, "natur": [1, 4, 6], "nb": [], "ndarrai": [6, 7, 9, 10], "necessari": [3, 12, 13], "need": [2, 3, 6, 10, 12, 13, 14, 15, 18], "neg": 9, "nest": 18, "netraj": [], "network": [4, 6, 8, 17], "neural": [4, 6, 8, 17], "new": [2, 10], "next": [6, 16], "nois": 9, "noisi": [4, 6], "non": [4, 6, 7, 8, 9, 10], "none": [6, 7, 8, 9, 10, 18], "normal": [8, 9], "norwegian": 6, "note": [0, 2, 6, 8, 14, 15, 17], "now": 2, "np": [8, 9, 10, 18], "num_output_channel": 9, "num_sampl": [6, 16], "num_work": [], "number": [6, 9, 10, 18], "numpi": [7, 8, 10, 18], "o": 3, "obb": 15, "obj_detect": 14, "object": [6, 7, 10, 11, 15, 18], "objectness_scor": [7, 18], "oblig": 1, "obtain": 18, "occupi": 17, "ocr": [4, 6, 8, 10, 14, 16], "ocr_carea": 18, "ocr_db_crnn": 10, "ocr_lin": 18, "ocr_pag": 18, "ocr_par": 18, "ocr_predictor": [8, 12, 14, 17, 18], "ocrdataset": [6, 16], "ocrmetr": 10, "ocrpredictor": [8, 12], "ocrx_word": 18, "offens": 1, "offici": [1, 8], "offlin": 1, "offset": 9, "onc": 18, "one": [2, 6, 8, 9, 12, 14, 18], "oneof": 9, "ones": [6, 10], "onli": [2, 8, 9, 10, 14, 16, 17, 18], "onlin": 1, "onnx": 15, "onnxruntim": [15, 17], "onnxtr": 17, "opac": 9, "opacity_rang": 9, "open": [1, 2, 14, 17], "opinion": 1, "optic": [4, 18], "optim": [4, 18], "option": [6, 8, 12], "order": [2, 6, 7, 9], "org": [1, 6, 8, 18], "organ": 7, "orient": [1, 7, 8, 15, 18], "orientationpredictor": 8, "other": [1, 2], "otherwis": [1, 7, 10], "our": [2, 8, 18], "out": [2, 8, 9, 10, 18], "out_box": [], "outpout": 18, "output": [7, 9, 17], "output_s": [7, 9], "outsid": 13, "over": [6, 10, 18], "overal": [1, 8], "overlai": 7, "overview": 15, "overwrit": [], "overwritten": 14, "own": 4, "p": [9, 18], "packag": [2, 4, 10, 13, 15, 16, 17], "pad": [6, 8, 9, 18], "page": [3, 6, 8, 10, 18], "page1": 7, "page2": 7, "page_1": 18, "page_idx": [7, 18], "page_orientation_predictor": 8, "page_param": [], "pair": 10, "pango": [], "paper": 8, "par_1_1": 18, "paragraph": 18, "paragraph_break": 18, "parallel": [], "param": [9, 18], "paramet": [4, 7, 8, 17], "pars": [4, 6], "parseq": [4, 8, 14, 17, 18], "part": [6, 9, 18], "parti": 3, "partial": 18, "particip": 1, "pass": [6, 7, 8, 18], "password": 7, "patch": [8, 10], "path": [6, 7, 15, 16, 17], "path_to_checkpoint": 12, "path_to_custom_model": 17, "path_to_pt": 12, "patil": [], "pattern": 1, "pdf": [7, 8, 11], "pdfpage": 7, "peopl": 1, "per": [9, 18], "perform": [4, 7, 8, 9, 10, 13, 17, 18], "period": 1, "permiss": 1, "permut": [4, 8], "persian_lett": 6, "person": [1, 16], "phase": 18, "photo": 16, "physic": [1, 7], "pick": 9, "pictur": 7, "pip": [2, 3, 15, 17], "pipelin": 18, "pixbuf": [], "pixel": [7, 9, 18], "pleas": 2, "plot": 10, "plt": 10, "plug": 14, "plugin": 3, "png": 7, "point": 17, "polici": 13, "polish": 6, "polit": 1, "polygon": [6, 10, 18], "pool": 8, "portugues": 6, "posit": [1, 10], "possibl": [2, 10, 14, 18], "post": [1, 18], "postprocessor": 18, "potenti": 8, "power": 4, "ppageno": 18, "pre": [2, 8, 17], "pre_transform_multiclass": [], "precis": [10, 18], "pred": 10, "pred_box": 10, "pred_label": 10, "predefin": 16, "predict": [7, 8, 10, 18], "predictor": [4, 7, 8, 12, 14, 17], "prefer": 16, "preinstal": 3, "preprocessor": [12, 18], "prerequisit": 14, "present": 11, "preserv": [8, 9, 18], "preserve_aspect_ratio": [7, 8, 9, 12, 18], "pretrain": [4, 8, 10, 12, 17, 18], "pretrained_backbon": [8, 12], "print": 18, "prior": 6, "privaci": 1, "privat": 1, "probabl": 9, "problem": 2, "procedur": 9, "process": [2, 4, 7, 12, 18], "processor": 18, "produc": [11, 18], "product": 17, "profession": 1, "project": [2, 16], "promptli": 1, "proper": 2, "properli": 6, "provid": [1, 2, 4, 14, 15, 16, 18], "public": [1, 4], "publicli": 18, "publish": 1, "pull": 14, "punctuat": 6, "pure": 6, "purpos": 2, "push_to_hf_hub": [8, 14], "py": 14, "pypdfium2": [3, 7], "pyplot": [7, 10], "python": [2, 15], "python3": 14, "pytorch": [3, 4, 8, 9, 12, 14, 17, 18], "q": 2, "qr": [7, 15], "qr_code": 16, "qualiti": 9, "question": 1, "quickli": 4, "quicktour": 11, "r": 18, "race": 1, "ramdisk": 6, "rand": [8, 9, 10, 17, 18], "random": [8, 9, 10, 18], "randomappli": 9, "randombright": 9, "randomcontrast": 9, "randomcrop": 9, "randomgamma": 9, "randomhorizontalflip": 9, "randomhu": 9, "randomjpegqu": 9, "randomli": 9, "randomres": 9, "randomrot": 9, "randomsatur": 9, "randomshadow": 9, "rang": 9, "rassi": 14, "ratio": [8, 9, 18], "raw": [7, 10], "re": 17, "read": [4, 6, 8], "read_html": 7, "read_img": [], "read_img_as_numpi": 7, "read_img_as_tensor": 7, "read_pdf": 7, "readi": 17, "real": [4, 8, 9], "realli": [], "reason": [1, 4, 6], "rebuild": 2, "rebuilt": 2, "recal": [10, 18], "receipt": [4, 6, 18], "reco_arch": [8, 12, 14, 17], "reco_b": 18, "reco_model": [12, 14, 17], "reco_param": 12, "reco_predictor": 12, "recogn": 18, "recognit": [6, 10, 12], "recognition_predictor": [8, 18], "recognition_task": [6, 16], "recognitiondataset": [6, 16], "recognitionpredictor": [8, 12], "rectangular": 8, "red": [], "reduc": [3, 9], "refer": [2, 3, 12, 14, 15, 16, 18], "regardless": 1, "region": 18, "regroup": 10, "regular": 16, "reject": 1, "rel": [7, 9, 10, 18], "relat": 7, "releas": [0, 3], "relev": 15, "religion": 1, "remov": 1, "render": [7, 18], "repo": 8, "repo_id": [8, 14], "report": 1, "repositori": [6, 8, 14], "repres": [1, 17, 18], "represent": [4, 8], "request": [1, 14], "requir": [3, 9, 17], "research": 4, "residu": 8, "resiz": [9, 18], "resnet": 8, "resnet18": [8, 14], "resnet31": 8, "resnet34": 8, "resnet50": [8, 14], "resolv": 7, "resolve_block": 18, "resolve_lin": 18, "resourc": 16, "respect": 1, "respons": [], "rest": [2, 9, 10], "restrict": 13, "result": [2, 6, 7, 11, 14, 17, 18], "return": 18, "reusabl": 18, "review": 1, "rgb": [7, 9], "rgb_mode": 7, "rgb_output": 7, "right": [1, 8, 10], "roboflow": [], "robust": [4, 6], "root": 6, "rotat": [6, 7, 8, 9, 10, 16, 18], "run": [2, 3, 8], "same": [2, 7, 10, 16, 17, 18], "sampl": [6, 16, 18], "sample_transform": 6, "samplecompos": [], "sanjin": [], "sar": [4, 8], "sar_resnet31": [8, 18], "satur": 9, "save": [8, 16], "scale": [7, 8, 9, 10], "scale_rang": 9, "scan": [4, 6], "scene": [4, 6, 8], "score": [7, 10], "script": [2, 16], "seamless": 4, "seamlessli": [4, 18], "search": 8, "searchabl": 11, "sec": 18, "second": 18, "section": [12, 14, 15, 17, 18], "secur": [1, 13], "see": [1, 2], "seen": 18, "segment": [4, 8, 18], "self": 18, "semant": [4, 8], "send": 18, "sens": 10, "sensit": 16, "separ": 18, "sequenc": [4, 6, 7, 8, 10, 18], "sequenti": [9, 18], "seri": 1, "seriou": 1, "set": [1, 3, 6, 8, 10, 13, 15, 18], "set_global_polici": 17, "sever": [7, 9, 18], "sex": 1, "sexual": 1, "shade": 9, "shape": [4, 7, 8, 9, 10, 18], "share": [13, 16], "shift": 9, "shm": 13, "should": [2, 6, 7, 9, 10], "show": [4, 7, 8, 10, 12, 14, 15], "showcas": 2, "shuffl": [6, 9], "side": 10, "signatur": 7, "signific": 16, "simpl": [4, 8, 17], "simpler": 8, "sinc": [6, 16], "singl": [1, 2, 4, 6], "single_img_doc": 17, "size": [1, 6, 7, 9, 15, 18], "skew": 18, "slack": 2, "slightli": 8, "small": [2, 8], "smallest": 7, "smooth": [], "smoothing_factor": [], "snapshot_download": 8, "snippet": 18, "so": [2, 3, 6, 8, 14, 16], "social": 1, "socio": 1, "some": [3, 11, 14, 16], "someth": 2, "somewher": 2, "soon": [], "sort": 1, "sourc": [6, 7, 8, 9, 10, 14], "space": [1, 18], "span": 18, "spanish": 6, "spatial": [4, 6, 7], "specif": [2, 3, 10, 12, 16, 18], "specifi": [1, 6, 7], "speed": [4, 8], "sphinx": 2, "sroie": [4, 6, 16], "stabl": 3, "stackoverflow": 2, "stage": 4, "standalon": [], "standard": 9, "start": 6, "state": [4, 10, 15], "static": 10, "statist": [], "statu": 1, "std": [9, 12], "step": 13, "still": 18, "str": [6, 7, 8, 9, 10], "straight": [6, 8, 16, 18], "straighten": [], "straighten_pag": 8, "straigten_pag": [], "stream": 7, "street": [4, 6], "strict": 3, "strictli": 10, "string": [6, 7, 10, 18], "strive": 3, "strong": [4, 8], "structur": [17, 18], "subset": [6, 18], "suggest": [2, 14], "sum": 10, "summari": 10, "support": [3, 15, 17, 18], "sustain": 1, "svhn": [4, 6, 16], "svt": [6, 16], "swedish": 6, "symmetr": [8, 9, 18], "symmetric_pad": [8, 9, 18], "synthes": [], "synthesize_pag": [], "synthet": 4, "synthtext": [4, 6, 16], "system": 18, "t": [2, 6, 12, 17, 18], "tabl": [14, 15], "take": [1, 6, 18], "target": [6, 7, 9, 10, 16], "target_s": 6, "task": [4, 6, 8, 14, 16, 18], "task2": 6, "team": 3, "techminde": 3, "templat": [2, 4], "tensor": [6, 7, 9, 18], "tensorflow": [3, 4, 7, 8, 9, 12, 14, 17, 18], "tensorspec": 17, "term": 1, "test": [6, 16], "test_set": 6, "text": [6, 7, 8, 10, 16], "text_output": 18, "textmatch": 10, "textnet": 8, "textnet_bas": 8, "textnet_smal": 8, "textnet_tini": 8, "textract": [4, 18], "textstylebrush": [4, 6], "textual": [4, 6, 7, 8, 18], "tf": [3, 7, 8, 9, 14, 17], "than": [2, 10, 14], "thank": 2, "thei": [1, 10], "them": [6, 18], "thi": [1, 2, 3, 5, 6, 9, 10, 12, 13, 14, 16, 17, 18], "thing": [17, 18], "third": 3, "those": [1, 7, 18], "threaten": 1, "threshold": 18, "through": [1, 9, 15, 16], "tilman": 14, "time": [1, 4, 8, 10, 16], "tini": 8, "titl": [7, 18], "tm": 18, "tmp": 13, "togeth": [2, 7], "tograi": 9, "tool": 16, "top": [10, 17, 18], "topic": 2, "torch": [3, 9, 12, 14, 17], "torchvis": 9, "total": 12, "toward": [1, 3], "train": [2, 6, 8, 9, 14, 15, 16, 17, 18], "train_it": [6, 16], "train_load": [6, 16], "train_pytorch": 14, "train_set": [6, 16], "train_tensorflow": 14, "trainabl": [4, 8], "tranform": 9, "transcrib": 18, "transfer": [4, 6], "transfo": 9, "transform": [4, 6, 8], "translat": 1, "troll": 1, "true": [6, 7, 8, 9, 10, 12, 13, 14, 16, 17, 18], "truth": 10, "tune": 17, "tupl": [6, 7, 9, 10], "turn": [], "two": [7, 13], "txt": 6, "type": [7, 10, 14, 17, 18], "typic": 18, "u": [1, 2], "ucsd": 6, "udac": 2, "uint8": [7, 8, 10, 18], "ukrainian": [], "unaccept": 1, "underli": [16, 18], "underneath": 7, "understand": [4, 6, 18], "unidecod": [], "uniform": [8, 9], "uniformli": 9, "uninterrupt": [7, 18], "union": 10, "unit": [], "unittest": 2, "unknown": [], "unknown_char": [], "unlock": 7, "unoffici": 8, "unprofession": 1, "unsolicit": 1, "unsupervis": 4, "unwelcom": 1, "up": [8, 18], "updat": 10, "upgrad": 2, "upper": [6, 9], "uppercas": 16, "url": 7, "us": [1, 2, 3, 6, 8, 10, 12, 13, 14, 15, 18], "usabl": 18, "usag": [13, 17], "use_broadcast": [], "use_polygon": [6, 10, 16], "useabl": 18, "useless": [], "user": [4, 7, 11], "utf": 18, "util": 17, "v1": 14, "v3": [8, 14, 18], "valid": 16, "valu": [2, 7, 9, 18], "valuabl": 4, "variabl": 13, "varieti": 6, "veri": 8, "verma": [], "version": [1, 2, 3, 17, 18], "vgg": 8, "vgg16": 14, "vgg16_bn_r": 8, "via": 1, "video": [], "vietnames": 6, "view": [4, 6], "viewpoint": 1, "violat": 1, "visibl": 1, "vision": [4, 6, 8], "visiondataset": 6, "visiontransform": 8, "visual": [3, 4, 15], "visualize_pag": 10, "vit_": 8, "vit_b": 8, "vitstr": [4, 8, 17], "vitstr_bas": [8, 18], "vitstr_smal": [8, 12, 17, 18], "viz": 3, "vocab": [12, 14, 16, 17, 18], "vocab_nam": [], "vocabulari": [6, 12, 14], "w": [7, 8, 9, 10], "w3": 18, "wa": 1, "wai": [1, 4, 16], "want": [2, 17, 18], "warmup": 18, "wasn": 2, "we": [1, 2, 3, 4, 7, 9, 14, 16, 17, 18], "weasyprint": 7, "web": [2, 7], "websit": 6, "weight": 12, "welcom": 1, "well": [1, 17], "were": [1, 7, 18], "what": 1, "when": [1, 2, 8], "whenev": 2, "where": [2, 7, 9, 10], "whether": [2, 6, 7, 9, 10, 16, 18], "which": [1, 8, 13, 15, 16, 18], "whichev": 3, "while": [9, 18], "why": 1, "width": [7, 9], "wiki": 1, "wildreceipt": [4, 6, 16], "window": [8, 10], "wish": 2, "within": 1, "without": [1, 6, 8], "wonder": 2, "word": [4, 6, 8, 10, 18], "word_1_1": 18, "word_1_2": 18, "word_1_3": 18, "wordgener": [6, 16], "words_onli": 10, "work": [13, 18], "worker": [], "workflow": 2, "worklow": 2, "world": [10, 18], "worth": 8, "would": [], "wrap": 18, "wrapper": [6, 9], "write": 13, "written": [1, 7], "www": [1, 7, 18], "x": [7, 9, 10], "x_ascend": 18, "x_descend": 18, "x_i": 10, "x_size": 18, "x_wconf": 18, "xhtml": 18, "xmax": 7, "xmin": 7, "xml": 18, "xml_bytes_str": 18, "xml_element": 18, "xml_output": 18, "xmln": 18, "y": 10, "y_i": 10, "y_j": 10, "yet": 15, "ymax": 7, "ymin": 7, "yolov8": 15, "yolov8_artefact": [], "you": [2, 3, 6, 7, 8, 12, 13, 14, 15, 16, 17, 18], "your": [2, 4, 7, 10, 18], "yoursit": 7, "yugesh": [], "zero": [9, 10], "zoo": [], "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7\u00e0\u00e2\u00e9\u00e8\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00e7": 6, "\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7\u00e0\u00e2\u00e9\u00e8\u00ea\u00eb\u00ee\u00ef\u00f4\u00f9\u00fb\u00fc\u00e7": 6, "\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa\u00e0\u00e8\u00e9\u00ec\u00ed\u00ee\u00f2\u00f3\u00f9\u00fa": 6, "\u00e1\u00e0\u00e2\u00e3\u00e9\u00ea\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7\u00e1\u00e0\u00e2\u00e3\u00e9\u00eb\u00ed\u00ef\u00f3\u00f4\u00f5\u00fa\u00fc\u00e7": 6, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": 6, "\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5\u00e1\u00e0\u1ea3\u1ea1\u00e3\u0103\u1eaf\u1eb1\u1eb3\u1eb5\u1eb7\u00e2\u1ea5\u1ea7\u1ea9\u1eab\u1ead\u0111\u00e9\u00e8\u1ebb\u1ebd\u1eb9\u00ea\u1ebf\u1ec1\u1ec3\u1ec5\u1ec7\u00f3\u00f2\u1ecf\u00f5\u1ecd\u00f4\u1ed1\u1ed3\u1ed5\u1ed9\u1ed7\u01a1\u1edb\u1edd\u1edf\u1ee3\u1ee1\u00fa\u00f9\u1ee7\u0169\u1ee5\u01b0\u1ee9\u1eeb\u1eed\u1eef\u1ef1i\u00ed\u00ec\u1ec9\u0129\u1ecb\u00fd\u1ef3\u1ef7\u1ef9\u1ef5": [], "\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1\u00e1\u00e9\u00ed\u00f3\u00fa\u00fc\u00f1": 6, "\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e\u00e1\u010d\u010f\u00e9\u011b\u00ed\u0148\u00f3\u0159\u0161\u0165\u00fa\u016f\u00fd\u017e": 6, "\u00e4\u00f6\u00e4\u00f6": 6, "\u00e4\u00f6\u00fc\u00df\u00e4\u00f6\u00fc\u00df": 6, "\u00e5\u00e4\u00f6\u00e5\u00e4\u00f6": 6, "\u00e6\u00f8\u00e5\u00e6\u00f8\u00e5": 6, "\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c\u0105\u0107\u0119\u0142\u0144\u00f3\u015b\u017a\u017c": 6, "\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9\u03b1\u03b2\u03b3\u03b4\u03b5\u03b6\u03b7\u03b8\u03b9\u03ba\u03bb\u03bc\u03bd\u03be\u03bf\u03c0\u03c1\u03c3\u03c4\u03c5\u03c6\u03c7\u03c8\u03c9": 6, "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f": [], "\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f0123456789": [], "\u0491\u0456\u0457\u0454\u0491\u0456\u0457\u0454": [], "\u05d0\u05d1\u05d2\u05d3\u05d4\u05d5\u05d6\u05d7\u05d8\u05d9\u05db\u05dc\u05de\u05e0\u05e1\u05e2\u05e4\u05e6\u05e7\u05e8\u05e9\u05ea": 6, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a": 6, "\u0621\u0622\u0623\u0624\u0625\u0626\u0627\u0628\u0629\u062a\u062b\u062c\u062d\u062e\u062f\u0630\u0631\u0632\u0633\u0634\u0635\u0636\u0637\u0638\u0639\u063a\u0640\u0641\u0642\u0643\u0644\u0645\u0646\u0647\u0648\u0649\u064a\u067e\u0686\u06a2\u06a4\u06af": 6, "\u0660\u0661\u0662\u0663\u0664\u0665\u0666\u0667\u0668\u0669": 6, "\u067e\u0686\u06a2\u06a4\u06af": 6, "\u0905": 6, "\u0905\u0906\u0907\u0908\u0909\u090a\u090b\u0960\u090c\u0961\u090f\u0910\u0913\u0914\u0905": 6, "\u0915\u0916\u0917\u0918\u0919\u091a\u091b\u091c\u091d\u091e\u091f\u0920\u0921\u0922\u0923\u0924\u0925\u0926\u0927\u0928\u092a\u092b\u092c\u092d\u092e\u092f\u0930\u0932\u0935\u0936\u0937\u0938\u0939\u0966\u0967\u0968\u0969\u096a\u096b\u096c\u096d\u096e\u096f": 6, "\u0950": 6, "\u0985\u0986\u0987\u0988\u0989\u098a\u098b\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a2\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9": 6, "\u09bd": 6, "\u09ce": 6, "\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef": 6}, "titles": ["Changelog", "Contributor Covenant Code of Conduct", "Contributing to docTR", "Installation", "docTR: Document Text Recognition", "doctr.contrib", "doctr.datasets", "doctr.io", "doctr.models", "doctr.transforms", "doctr.utils", "docTR Notebooks", "Train your own model", "AWS Lambda", "Share your model with the community", "Integrate contributions into your pipeline", "Choose a ready to use dataset", "Preparing your model for inference", "Choosing the right model"], "titleterms": {"": 2, "0": 0, "01": 0, "02": 0, "03": 0, "04": 0, "05": 0, "07": 0, "08": 0, "09": 0, "1": [0, 1], "10": 0, "11": 0, "12": 0, "18": 0, "2": [0, 1], "2021": 0, "2022": 0, "2023": 0, "2024": 0, "21": [], "22": 0, "27": 0, "28": 0, "29": 0, "3": [0, 1], "31": 0, "4": [0, 1], "5": 0, "6": 0, "7": 0, "8": 0, "9": [], "advanc": 18, "approach": 18, "architectur": 18, "arg": [6, 7, 8, 9, 10], "artefact": 7, "artefactdetect": 15, "attribut": 1, "avail": [15, 16, 18], "aw": 13, "ban": 1, "block": 7, "bug": 2, "changelog": 0, "choos": [16, 18], "classif": [8, 14], "code": [1, 2], "codebas": 2, "commit": 2, "commun": 14, "compos": 9, "conda": 3, "conduct": 1, "connect": 2, "continu": 2, "contrib": 5, "contribut": [2, 5, 15], "contributor": 1, "convent": 14, "correct": 1, "coven": 1, "custom": [6, 12], "data": 16, "dataload": 6, "dataset": [4, 6, 16], "detect": [4, 8, 14, 16, 18], "develop": 2, "do": 18, "doctr": [2, 4, 5, 6, 7, 8, 9, 10, 11], "document": [2, 4, 7], "end": 18, "enforc": 1, "evalu": 10, "export": 17, "factori": 8, "featur": [2, 4], "feedback": 2, "file": 7, "from": 14, "gener": [6, 16], "git": 3, "guidelin": 1, "half": 17, "hub": 14, "huggingfac": 14, "i": 18, "infer": 17, "instal": [2, 3], "integr": [2, 15], "io": 7, "lambda": 13, "let": 2, "line": 7, "linux": 3, "load": [12, 14, 16], "loader": 6, "main": 4, "mode": 2, "model": [4, 8, 12, 14, 17, 18], "modifi": 2, "modul": [5, 15], "name": 14, "notebook": 11, "object": 16, "ocr": 18, "onli": 3, "onnx": 17, "optim": 17, "option": 18, "orient": [], "our": 1, "output": 18, "own": [12, 16], "packag": 3, "page": 7, "perman": 1, "pipelin": 15, "pledg": 1, "precis": 17, "predictor": 18, "prepar": 17, "prerequisit": 3, "pretrain": 14, "push": 14, "python": 3, "qualiti": 2, "question": 2, "read": 7, "readi": 16, "recognit": [4, 8, 14, 16, 18], "reconstitut": [], "report": 2, "request": 2, "resourc": [], "respons": 1, "return": [6, 7, 8, 10], "right": 18, "scope": 1, "share": 14, "should": 18, "stage": 18, "standard": 1, "structur": [2, 7], "style": 2, "support": [4, 5, 6, 9], "synthet": [6, 16], "task": 10, "temporari": 1, "test": 2, "text": [4, 18], "train": 12, "transform": 9, "two": 18, "unit": 2, "us": [16, 17], "util": 10, "v0": 0, "verif": 2, "via": 3, "visual": 10, "vocab": 6, "warn": 1, "what": 18, "word": 7, "your": [12, 14, 15, 16, 17], "zoo": [4, 8]}})
\ No newline at end of file