Deploying to gh-pages from @ 9b6dea3 🚀

latest/_modules/doctr/models/classification/zoo.html

@@ -303,7 +303,7 @@ <h1>Source code for doctr.models.classification.zoo</h1><div class="highlight"><
 
 <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Any</span>
 
-<span class="kn">from</span> <span class="nn">doctr.file_utils</span> <span class="kn">import</span> <span class="n">is_tf_available</span>
+<span class="kn">from</span> <span class="nn">doctr.file_utils</span> <span class="kn">import</span> <span class="n">is_tf_available</span><span class="p">,</span> <span class="n">is_torch_available</span>
 
 <span class="kn">from</span> <span class="nn">..</span> <span class="kn">import</span> <span class="n">classification</span>
 <span class="kn">from</span> <span class="nn">..preprocessor</span> <span class="kn">import</span> <span class="n">PreProcessor</span>
@@ -346,7 +346,14 @@ <h1>Source code for doctr.models.classification.zoo</h1><div class="highlight"><
         <span class="c1"># Load directly classifier from backbone</span>
         <span class="n">_model</span> <span class="o">=</span> <span class="n">classification</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">[</span><span class="n">arch</span><span class="p">](</span><span class="n">pretrained</span><span class="o">=</span><span class="n">pretrained</span><span class="p">)</span>
     <span class="k">else</span><span class="p">:</span>
-        <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">arch</span><span class="p">,</span> <span class="n">classification</span><span class="o">.</span><span class="n">MobileNetV3</span><span class="p">):</span>
+        <span class="n">allowed_archs</span> <span class="o">=</span> <span class="p">[</span><span class="n">classification</span><span class="o">.</span><span class="n">MobileNetV3</span><span class="p">]</span>
+        <span class="k">if</span> <span class="n">is_torch_available</span><span class="p">():</span>
+            <span class="c1"># Adding the type for torch compiled models to the allowed architectures</span>
+            <span class="kn">from</span> <span class="nn">doctr.models.utils</span> <span class="kn">import</span> <span class="n">_CompiledModule</span>
+
+            <span class="n">allowed_archs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">_CompiledModule</span><span class="p">)</span>
+
+        <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">arch</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">(</span><span class="n">allowed_archs</span><span class="p">)):</span>
             <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;unknown architecture: </span><span class="si">{</span><span class="nb">type</span><span class="p">(</span><span class="n">arch</span><span class="p">)</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
         <span class="n">_model</span> <span class="o">=</span> <span class="n">arch</span>
 

latest/_modules/doctr/models/detection/zoo.html

@@ -354,7 +354,14 @@ <h1>Source code for doctr.models.detection.zoo</h1><div class="highlight"><pre>
         <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">_model</span><span class="p">,</span> <span class="n">detection</span><span class="o">.</span><span class="n">FAST</span><span class="p">):</span>
             <span class="n">_model</span> <span class="o">=</span> <span class="n">reparameterize</span><span class="p">(</span><span class="n">_model</span><span class="p">)</span>
     <span class="k">else</span><span class="p">:</span>
-        <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">arch</span><span class="p">,</span> <span class="p">(</span><span class="n">detection</span><span class="o">.</span><span class="n">DBNet</span><span class="p">,</span> <span class="n">detection</span><span class="o">.</span><span class="n">LinkNet</span><span class="p">,</span> <span class="n">detection</span><span class="o">.</span><span class="n">FAST</span><span class="p">)):</span>
+        <span class="n">allowed_archs</span> <span class="o">=</span> <span class="p">[</span><span class="n">detection</span><span class="o">.</span><span class="n">DBNet</span><span class="p">,</span> <span class="n">detection</span><span class="o">.</span><span class="n">LinkNet</span><span class="p">,</span> <span class="n">detection</span><span class="o">.</span><span class="n">FAST</span><span class="p">]</span>
+        <span class="k">if</span> <span class="n">is_torch_available</span><span class="p">():</span>
+            <span class="c1"># Adding the type for torch compiled models to the allowed architectures</span>
+            <span class="kn">from</span> <span class="nn">doctr.models.utils</span> <span class="kn">import</span> <span class="n">_CompiledModule</span>
+
+            <span class="n">allowed_archs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">_CompiledModule</span><span class="p">)</span>
+
+        <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">arch</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">(</span><span class="n">allowed_archs</span><span class="p">)):</span>
             <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;unknown architecture: </span><span class="si">{</span><span class="nb">type</span><span class="p">(</span><span class="n">arch</span><span class="p">)</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
 
         <span class="n">_model</span> <span class="o">=</span> <span class="n">arch</span>

latest/_modules/doctr/models/recognition/zoo.html

@@ -303,7 +303,7 @@ <h1>Source code for doctr.models.recognition.zoo</h1><div class="highlight"><pre
 
 <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Any</span>
 
-<span class="kn">from</span> <span class="nn">doctr.file_utils</span> <span class="kn">import</span> <span class="n">is_tf_available</span>
+<span class="kn">from</span> <span class="nn">doctr.file_utils</span> <span class="kn">import</span> <span class="n">is_tf_available</span><span class="p">,</span> <span class="n">is_torch_available</span>
 <span class="kn">from</span> <span class="nn">doctr.models.preprocessor</span> <span class="kn">import</span> <span class="n">PreProcessor</span>
 
 <span class="kn">from</span> <span class="nn">..</span> <span class="kn">import</span> <span class="n">recognition</span>
@@ -333,9 +333,14 @@ <h1>Source code for doctr.models.recognition.zoo</h1><div class="highlight"><pre
             <span class="n">pretrained</span><span class="o">=</span><span class="n">pretrained</span><span class="p">,</span> <span class="n">pretrained_backbone</span><span class="o">=</span><span class="n">kwargs</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;pretrained_backbone&quot;</span><span class="p">,</span> <span class="kc">True</span><span class="p">)</span>
         <span class="p">)</span>
     <span class="k">else</span><span class="p">:</span>
-        <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span>
-            <span class="n">arch</span><span class="p">,</span> <span class="p">(</span><span class="n">recognition</span><span class="o">.</span><span class="n">CRNN</span><span class="p">,</span> <span class="n">recognition</span><span class="o">.</span><span class="n">SAR</span><span class="p">,</span> <span class="n">recognition</span><span class="o">.</span><span class="n">MASTER</span><span class="p">,</span> <span class="n">recognition</span><span class="o">.</span><span class="n">ViTSTR</span><span class="p">,</span> <span class="n">recognition</span><span class="o">.</span><span class="n">PARSeq</span><span class="p">)</span>
-        <span class="p">):</span>
+        <span class="n">allowed_archs</span> <span class="o">=</span> <span class="p">[</span><span class="n">recognition</span><span class="o">.</span><span class="n">CRNN</span><span class="p">,</span> <span class="n">recognition</span><span class="o">.</span><span class="n">SAR</span><span class="p">,</span> <span class="n">recognition</span><span class="o">.</span><span class="n">MASTER</span><span class="p">,</span> <span class="n">recognition</span><span class="o">.</span><span class="n">ViTSTR</span><span class="p">,</span> <span class="n">recognition</span><span class="o">.</span><span class="n">PARSeq</span><span class="p">]</span>
+        <span class="k">if</span> <span class="n">is_torch_available</span><span class="p">():</span>
+            <span class="c1"># Adding the type for torch compiled models to the allowed architectures</span>
+            <span class="kn">from</span> <span class="nn">doctr.models.utils</span> <span class="kn">import</span> <span class="n">_CompiledModule</span>
+
+            <span class="n">allowed_archs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">_CompiledModule</span><span class="p">)</span>
+
+        <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">arch</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">(</span><span class="n">allowed_archs</span><span class="p">)):</span>
             <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;unknown architecture: </span><span class="si">{</span><span class="nb">type</span><span class="p">(</span><span class="n">arch</span><span class="p">)</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
         <span class="n">_model</span> <span class="o">=</span> <span class="n">arch</span>
 

latest/_sources/using_doctr/using_model_export.rst.txt

@@ -31,7 +31,11 @@ Advantages:
         .. code:: python3
 
             import torch
-            predictor = ocr_predictor(reco_arch="crnn_mobilenet_v3_small", det_arch="linknet_resnet34", pretrained=True).cuda().half()
+            predictor = ocr_predictor(
+                reco_arch="crnn_mobilenet_v3_small",
+                det_arch="linknet_resnet34",
+                pretrained=True
+            ).cuda().half()
             res = predictor(doc)
 
     .. tab:: TensorFlow
@@ -41,8 +45,63 @@ Advantages:
             import tensorflow as tf
             from tensorflow.keras import mixed_precision
             mixed_precision.set_global_policy('mixed_float16')
-            predictor = ocr_predictor(reco_arch="crnn_mobilenet_v3_small", det_arch="linknet_resnet34", pretrained=True)
-
+            predictor = ocr_predictor(
+                reco_arch="crnn_mobilenet_v3_small",
+                det_arch="linknet_resnet34",
+                pretrained=True
+            )
+
+
+Compiling your models (PyTorch only)
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+**NOTE:**
+
+- This feature is only available if you use PyTorch as backend.
+- The recognition architecture `master` is not supported for model compilation yet.
+- We provide only official support for the default (`inductor`) backend, but you can try other backends, configurations depending on your hardware and requirements as well.
+
+Compiling your PyTorch models with `torch.compile` optimizes the model by converting it to a graph representation and applying backends that can improve performance.
+This process can make inference faster and reduce memory overhead during execution.
+
+Further information can be found in the `PyTorch documentation <https://pytorch.org/tutorials/intermediate/torch_compile_tutorial.html>`_.
+
+.. code::
+
+    import torch
+    from doctr.models import (
+        ocr_predictor,
+        vitstr_small,
+        fast_base,
+        mobilenet_v3_small_crop_orientation,
+        mobilenet_v3_small_page_orientation,
+        crop_orientation_predictor,
+        page_orientation_predictor
+    )
+
+    # Compile the models
+    detection_model = torch.compile(
+        fast_base(pretrained=True).eval()
+    )
+    recognition_model = torch.compile(
+        vitstr_small(pretrained=True).eval()
+    )
+    crop_orientation_model = torch.compile(
+        mobilenet_v3_small_crop_orientation(pretrained=True).eval()
+    )
+    page_orientation_model = torch.compile(
+        mobilenet_v3_small_page_orientation(pretrained=True).eval()
+    )
+
+    predictor = models.ocr_predictor(
+        detection_model, recognition_model, assume_straight_pages=False
+    )
+    # NOTE: Only required for non-straight pages (`assume_straight_pages=False`) and non-disabled orientation classification
+    # Set the orientation predictors
+    predictor.crop_orientation_predictor = crop_orientation_predictor(crop_orientation_model)
+    predictor.page_orientation_predictor = page_orientation_predictor(page_orientation_model)
+
+    compiled_out = predictor(doc)
 
 Export to ONNX
 ^^^^^^^^^^^^^^
@@ -64,7 +123,11 @@ It defines a common format for representing models, including the network struct
             input_shape = (3, 32, 128)
             model = vitstr_small(pretrained=True, exportable=True)
             dummy_input = torch.rand((batch_size, input_shape), dtype=torch.float32)
-            model_path = export_model_to_onnx(model, model_name="vitstr.onnx, dummy_input=dummy_input)
+            model_path = export_model_to_onnx(
+                model,
+                model_name="vitstr.onnx",
+                dummy_input=dummy_input
+            )
 
     .. tab:: TensorFlow
 
@@ -78,7 +141,11 @@ It defines a common format for representing models, including the network struct
             input_shape = (32, 128, 3)
             model = vitstr_small(pretrained=True, exportable=True)
             dummy_input = [tf.TensorSpec([batch_size, input_shape], tf.float32, name="input")]
-            model_path, output = export_model_to_onnx(model, model_name="vitstr.onnx", dummy_input=dummy_input)
+            model_path, output = export_model_to_onnx(
+                model,
+                model_name="vitstr.onnx",
+                dummy_input=dummy_input
+            )
 
 
 Using your ONNX exported model

latest/_sources/using_doctr/using_models.rst.txt

@@ -298,7 +298,7 @@ For instance, this snippet instantiates an end-to-end ocr_predictor working with
 
 .. code:: python3
 
-    from doctr.model import ocr_predictor
+    from doctr.models import ocr_predictor
     model = ocr_predictor('linknet_resnet18', pretrained=True, assume_straight_pages=False, preserve_aspect_ratio=True)
 
 
@@ -309,7 +309,7 @@ Additionally, you can change the batch size of the underlying detection and reco
 
 .. code:: python3
 
-    from doctr.model import ocr_predictor
+    from doctr.models import ocr_predictor
     model = ocr_predictor(pretrained=True, det_bs=4, reco_bs=1024)
 
 To modify the output structure you can pass the following arguments to the predictor which will be handled by the underlying `DocumentBuilder`:
@@ -322,7 +322,7 @@ For example to disable the automatic grouping of lines into blocks:
 
 .. code:: python3
 
-    from doctr.model import ocr_predictor
+    from doctr.models import ocr_predictor
     model = ocr_predictor(pretrained=True, resolve_blocks=False)
 
 
@@ -477,7 +477,7 @@ This will only have an effect with `assume_straight_pages=False` and/or `straigh
 
 .. code:: python3
 
-    from doctr.model import ocr_predictor
+    from doctr.models import ocr_predictor
     model = ocr_predictor(pretrained=True, assume_straight_pages=False, disable_page_orientation=True)
 
 
@@ -489,15 +489,15 @@ This will only have an effect with `assume_straight_pages=False` and/or `straigh
 
 .. code:: python3
 
-    from doctr.model import ocr_predictor
+    from doctr.models import ocr_predictor
     model = ocr_predictor(pretrained=True, assume_straight_pages=False, disable_crop_orientation=True)
 
 
 * Add a hook to the `ocr_predictor` to manipulate the location predictions before the crops are passed to the recognition model.
 
 .. code:: python3
 
-    from doctr.model import ocr_predictor
+    from doctr.models import ocr_predictor
 
     class CustomHook:
         def __call__(self, loc_preds):