[Fixes / docs] Add more vocabs / Fix Style / HF hub / API Dep (#1412)

mindee · Jan 3, 2024 · ed927bd · ed927bd
1 parent 5105f98
commit ed927bd
Show file tree

Hide file tree

Showing 169 changed files with 685 additions and 749 deletions.
diff --git a/.github/verify_pr_labels.py b/.github/verify_pr_labels.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/.github/workflows/style.yml b/.github/workflows/style.yml
@@ -22,7 +22,7 @@ jobs:
           architecture: x64
       - name: Run ruff
         run: |
-          pip install ruff
+          pip install ruff --upgrade
           ruff --version
           ruff check --diff .
 
@@ -48,7 +48,7 @@ jobs:
         run: |
           python -m pip install --upgrade pip
           pip install -e .[dev] --upgrade
-          pip install mypy
+          pip install mypy --upgrade
       - name: Run mypy
         run: |
           mypy --version

diff --git a/api/Dockerfile b/api/Dockerfile
@@ -1,4 +1,4 @@
-FROM tiangolo/uvicorn-gunicorn-fastapi:python3.8-slim
+FROM tiangolo/uvicorn-gunicorn-fastapi:python3.9-slim
 
 WORKDIR /app
 

diff --git a/api/app/config.py b/api/app/config.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/api/app/main.py b/api/app/main.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/api/app/routes/detection.py b/api/app/routes/detection.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/api/app/routes/kie.py b/api/app/routes/kie.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/api/app/routes/ocr.py b/api/app/routes/ocr.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/api/app/routes/recognition.py b/api/app/routes/recognition.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/api/app/schemas.py b/api/app/schemas.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/api/app/vision.py b/api/app/vision.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/api/pyproject.toml b/api/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "poetry.masonry.api"
 
 [tool.poetry]
 name = "doctr-api"
-version = "0.7.0a0"
+version = "0.8.0a0"
 description = "Backend template for your OCR API with docTR"
 authors = ["Mindee <[email protected]>"]
 license = "Apache-2.0"

diff --git a/demo/app.py b/demo/app.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/demo/backend/pytorch.py b/demo/backend/pytorch.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/demo/backend/tensorflow.py b/demo/backend/tensorflow.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/docs/source/changelog.rst b/docs/source/changelog.rst
@@ -1,7 +1,7 @@
 Changelog
 =========
 
-v0.7.0 (2023-09-09)
+v0.7.0 (2024-09-09)
 -------------------
 Release note: `v0.7.0 <https://github.com/mindee/doctr/releases/tag/v0.7.0>`_
 

diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/docs/source/modules/datasets.rst b/docs/source/modules/datasets.rst
@@ -121,6 +121,9 @@ of vocabs.
    * - spanish
      - 116
      - 0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~°£€¥¢฿áéíóúüñÁÉÍÓÚÜÑ¡¿
+   * - italian
+     - 120
+     - 0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~°£€¥¢฿àèéìíîòóùúÀÈÉÌÍÎÒÓÙÚ
    * - german
      - 108
      - 0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~°£€¥¢฿äöüßÄÖÜẞ
@@ -130,11 +133,32 @@ of vocabs.
    * - czech
      - 130
      - 0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~°£€¥¢฿áčďéěíňóřšťúůýžÁČĎÉĚÍŇÓŘŠŤÚŮÝŽ
+   * - polish
+     - 118
+     - 0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~°£€¥¢฿ąćęłńóśźżĄĆĘŁŃÓŚŹŻ
+   * - dutch
+     - 114
+     - 0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~°£€¥¢฿áéíóúüñÁÉÍÓÚÜÑ
+   * - norwegian
+     - 106
+     - 0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~°£€¥¢฿æøåÆØÅ
+   * - danish
+     - 106
+     - 0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&\'()*+,-./:;<=>?@[\\]^_`{|}~°£€¥¢฿æøåÆØÅ
+   * - finnish
+     - 104
+     - 0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~°£€¥¢฿äöÄÖ
+   * - swedish
+     - 106
+     - 0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~°£€¥¢฿åäöÅÄÖ
    * - vietnamese
      - 234
      - 0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~°£€¥¢฿áàảạãăắằẳẵặâấầẩẫậéèẻẽẹêếềểễệóòỏõọôốồổộỗơớờởợỡúùủũụưứừửữựiíìỉĩịýỳỷỹỵÁÀẢẠÃĂẮẰẲẴẶÂẤẦẨẪẬÉÈẺẼẸÊẾỀỂỄỆÓÒỎÕỌÔỐỒỔỘỖƠỚỜỞỢỠÚÙỦŨỤƯỨỪỬỮỰIÍÌỈĨỊÝỲỶỸỴ
    * - hebrew
      - 123
      - 0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~°£€¥¢฿אבגדהוזחטיכלמנסעפצקרשת₪
+   * - multilingual
+     - 195
+     - english & french & german & italian & spanish & portuguese & czech & polish & dutch & norwegian & danish & finnish & swedish & §
 
 .. autofunction:: encode_sequences
diff --git a/docs/source/using_doctr/sharing_models.rst b/docs/source/using_doctr/sharing_models.rst
@@ -132,3 +132,7 @@ Recognition
 +---------------------------------+---------------------------------------------------+---------------------+------------------------+
 | crnn_vgg16_bn (dummy)           | Felix92/doctr-tf-crnn-vgg16-bn-french             | french              | TensorFlow             |
 +---------------------------------+---------------------------------------------------+---------------------+------------------------+
+| crnn_vgg16_bn                   | tilman-rassy/doctr-crnn-vgg16-bn-fascan-v1        | french + german + § | PyTorch                |
++---------------------------------+---------------------------------------------------+---------------------+------------------------+
+| parseq                          | Felix92/doctr-torch-parseq-multilingual-v1        | multilingual        | PyTorch                |
++---------------------------------+---------------------------------------------------+---------------------+------------------------+
diff --git a/doctr/datasets/cord.py b/doctr/datasets/cord.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
@@ -110,9 +110,10 @@ def __init__(
                 for crop, label in zip(crops, list(text_targets)):
                     self.data.append((crop, label))
             else:
-                self.data.append(
-                    (img_path, dict(boxes=np.asarray(box_targets, dtype=int).clip(min=0), labels=list(text_targets)))
-                )
+                self.data.append((
+                    img_path,
+                    dict(boxes=np.asarray(box_targets, dtype=int).clip(min=0), labels=list(text_targets)),
+                ))
 
         self.root = tmp_root
 

diff --git a/doctr/datasets/datasets/base.py b/doctr/datasets/datasets/base.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/doctr/datasets/datasets/pytorch.py b/doctr/datasets/datasets/pytorch.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/doctr/datasets/datasets/tensorflow.py b/doctr/datasets/datasets/tensorflow.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/doctr/datasets/detection.py b/doctr/datasets/detection.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/doctr/datasets/doc_artefacts.py b/doctr/datasets/doc_artefacts.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/doctr/datasets/funsd.py b/doctr/datasets/funsd.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
@@ -101,12 +101,10 @@ def __init__(
                     if not any(char in label for char in ["☑", "☐", "\uf703", "\uf702"]):
                         self.data.append((crop, label))
             else:
-                self.data.append(
-                    (
-                        img_path,
-                        dict(boxes=np.asarray(box_targets, dtype=np_dtype), labels=list(text_targets)),
-                    )
-                )
+                self.data.append((
+                    img_path,
+                    dict(boxes=np.asarray(box_targets, dtype=np_dtype), labels=list(text_targets)),
+                ))
 
         self.root = tmp_root
 

diff --git a/doctr/datasets/generator/base.py b/doctr/datasets/generator/base.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/doctr/datasets/generator/pytorch.py b/doctr/datasets/generator/pytorch.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/doctr/datasets/generator/tensorflow.py b/doctr/datasets/generator/tensorflow.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/doctr/datasets/ic03.py b/doctr/datasets/ic03.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/doctr/datasets/ic13.py b/doctr/datasets/ic13.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/doctr/datasets/iiit5k.py b/doctr/datasets/iiit5k.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
@@ -92,9 +92,10 @@ def __init__(
                     box_targets = [[box[0], box[1], box[0] + box[2], box[1] + box[3]] for box in box_targets]
 
                 # label are casted to list where each char corresponds to the character's bounding box
-                self.data.append(
-                    (_raw_path, dict(boxes=np.asarray(box_targets, dtype=np_dtype), labels=list(_raw_label)))
-                )
+                self.data.append((
+                    _raw_path,
+                    dict(boxes=np.asarray(box_targets, dtype=np_dtype), labels=list(_raw_label)),
+                ))
 
         self.root = tmp_root
 

diff --git a/doctr/datasets/iiithws.py b/doctr/datasets/iiithws.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/doctr/datasets/imgur5k.py b/doctr/datasets/imgur5k.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/doctr/datasets/loader.py b/doctr/datasets/loader.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/doctr/datasets/mjsynth.py b/doctr/datasets/mjsynth.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/doctr/datasets/ocr.py b/doctr/datasets/ocr.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/doctr/datasets/recognition.py b/doctr/datasets/recognition.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/doctr/datasets/sroie.py b/doctr/datasets/sroie.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/doctr/datasets/svhn.py b/doctr/datasets/svhn.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/doctr/datasets/svt.py b/doctr/datasets/svt.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/doctr/datasets/synthtext.py b/doctr/datasets/synthtext.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.

diff --git a/doctr/datasets/utils.py b/doctr/datasets/utils.py
@@ -1,4 +1,4 @@
-# Copyright (C) 2021-2023, Mindee.
+# Copyright (C) 2021-2024, Mindee.
 
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.