[skip ci] Documentation updates

latest/_modules/doctr/models/classification/mobilenet/tensorflow.html

@@ -272,6 +272,7 @@ <h1>Source code for doctr.models.classification.mobilenet.tensorflow</h1><div cl
     <span class="s2">&quot;mobilenet_v3_large&quot;</span><span class="p">,</span>
     <span class="s2">&quot;mobilenet_v3_large_r&quot;</span><span class="p">,</span>
     <span class="s2">&quot;mobilenet_v3_small_crop_orientation&quot;</span><span class="p">,</span>
+    <span class="s2">&quot;mobilenet_v3_small_page_orientation&quot;</span><span class="p">,</span>
 <span class="p">]</span>
 
 
@@ -679,6 +680,29 @@ <h1>Source code for doctr.models.classification.mobilenet.tensorflow</h1><div cl
 <span class="sd">    &quot;&quot;&quot;</span>
     <span class="k">return</span> <span class="n">_mobilenet_v3</span><span class="p">(</span><span class="s2">&quot;mobilenet_v3_small_crop_orientation&quot;</span><span class="p">,</span> <span class="n">pretrained</span><span class="p">,</span> <span class="n">include_top</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div>
 
+
+
+<div class="viewcode-block" id="mobilenet_v3_small_page_orientation">
+<a class="viewcode-back" href="../../../../../modules/models.html#doctr.models.classification.mobilenet_v3_small_page_orientation">[docs]</a>
+<span class="k">def</span> <span class="nf">mobilenet_v3_small_page_orientation</span><span class="p">(</span><span class="n">pretrained</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">MobileNetV3</span><span class="p">:</span>
+<span class="w">    </span><span class="sd">&quot;&quot;&quot;MobileNetV3-Small architecture as described in</span>
+<span class="sd">    `&quot;Searching for MobileNetV3&quot;,</span>
+<span class="sd">    &lt;https://arxiv.org/pdf/1905.02244.pdf&gt;`_.</span>
+<span class="sd">    &gt;&gt;&gt; import tensorflow as tf</span>
+<span class="sd">    &gt;&gt;&gt; from doctr.models import mobilenet_v3_small_page_orientation</span>
+<span class="sd">    &gt;&gt;&gt; model = mobilenet_v3_small_page_orientation(pretrained=False)</span>
+<span class="sd">    &gt;&gt;&gt; input_tensor = tf.random.uniform(shape=[1, 512, 512, 3], maxval=1, dtype=tf.float32)</span>
+<span class="sd">    &gt;&gt;&gt; out = model(input_tensor)</span>
+<span class="sd">    Args:</span>
+<span class="sd">    ----</span>
+<span class="sd">        pretrained: boolean, True if model is pretrained</span>
+<span class="sd">        **kwargs: keyword arguments of the MobileNetV3 architecture</span>
+<span class="sd">    Returns:</span>
+<span class="sd">    -------</span>
+<span class="sd">        a keras.Model</span>
+<span class="sd">    &quot;&quot;&quot;</span>
+    <span class="k">return</span> <span class="n">_mobilenet_v3</span><span class="p">(</span><span class="s2">&quot;mobilenet_v3_small_page_orientation&quot;</span><span class="p">,</span> <span class="n">pretrained</span><span class="p">,</span> <span class="n">include_top</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div>
+
 </pre></div>
         </article>
       </div>

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

@@ -261,7 +261,7 @@ <h1>Source code for doctr.models.classification.zoo</h1><div class="highlight"><
 <span class="kn">from</span> <span class="nn">..preprocessor</span> <span class="kn">import</span> <span class="n">PreProcessor</span>
 <span class="kn">from</span> <span class="nn">.predictor</span> <span class="kn">import</span> <span class="n">OrientationPredictor</span>
 
-<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;crop_orientation_predictor&quot;</span><span class="p">]</span>
+<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;crop_orientation_predictor&quot;</span><span class="p">,</span> <span class="s2">&quot;page_orientation_predictor&quot;</span><span class="p">]</span>
 
 <span class="n">ARCHS</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="p">[</span>
     <span class="s2">&quot;magc_resnet31&quot;</span><span class="p">,</span>
@@ -281,7 +281,7 @@ <h1>Source code for doctr.models.classification.zoo</h1><div class="highlight"><
     <span class="s2">&quot;vit_s&quot;</span><span class="p">,</span>
     <span class="s2">&quot;vit_b&quot;</span><span class="p">,</span>
 <span class="p">]</span>
-<span class="n">ORIENTATION_ARCHS</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;mobilenet_v3_small_crop_orientation&quot;</span><span class="p">]</span>
+<span class="n">ORIENTATION_ARCHS</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;mobilenet_v3_small_crop_orientation&quot;</span><span class="p">,</span> <span class="s2">&quot;mobilenet_v3_small_page_orientation&quot;</span><span class="p">]</span>
 
 
 <span class="k">def</span> <span class="nf">_orientation_predictor</span><span class="p">(</span><span class="n">arch</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">pretrained</span><span class="p">:</span> <span class="nb">bool</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">OrientationPredictor</span><span class="p">:</span>
@@ -292,7 +292,7 @@ <h1>Source code for doctr.models.classification.zoo</h1><div class="highlight"><
     <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="n">kwargs</span><span class="p">[</span><span class="s2">&quot;mean&quot;</span><span class="p">]</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;mean&quot;</span><span class="p">,</span> <span class="n">_model</span><span class="o">.</span><span class="n">cfg</span><span class="p">[</span><span class="s2">&quot;mean&quot;</span><span class="p">])</span>
     <span class="n">kwargs</span><span class="p">[</span><span class="s2">&quot;std&quot;</span><span class="p">]</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;std&quot;</span><span class="p">,</span> <span class="n">_model</span><span class="o">.</span><span class="n">cfg</span><span class="p">[</span><span class="s2">&quot;std&quot;</span><span class="p">])</span>
-    <span class="n">kwargs</span><span class="p">[</span><span class="s2">&quot;batch_size&quot;</span><span class="p">]</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;batch_size&quot;</span><span class="p">,</span> <span class="mi">128</span><span class="p">)</span>
+    <span class="n">kwargs</span><span class="p">[</span><span class="s2">&quot;batch_size&quot;</span><span class="p">]</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;batch_size&quot;</span><span class="p">,</span> <span class="mi">128</span> <span class="k">if</span> <span class="s2">&quot;crop&quot;</span> <span class="ow">in</span> <span class="n">arch</span> <span class="k">else</span> <span class="mi">4</span><span class="p">)</span>
     <span class="n">input_shape</span> <span class="o">=</span> <span class="n">_model</span><span class="o">.</span><span class="n">cfg</span><span class="p">[</span><span class="s2">&quot;input_shape&quot;</span><span class="p">][:</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="k">if</span> <span class="n">is_tf_available</span><span class="p">()</span> <span class="k">else</span> <span class="n">_model</span><span class="o">.</span><span class="n">cfg</span><span class="p">[</span><span class="s2">&quot;input_shape&quot;</span><span class="p">][</span><span class="mi">1</span><span class="p">:]</span>
     <span class="n">predictor</span> <span class="o">=</span> <span class="n">OrientationPredictor</span><span class="p">(</span>
         <span class="n">PreProcessor</span><span class="p">(</span><span class="n">input_shape</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> <span class="n">symmetric_pad</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">),</span> <span class="n">_model</span>
@@ -305,17 +305,44 @@ <h1>Source code for doctr.models.classification.zoo</h1><div class="highlight"><
 <span class="k">def</span> <span class="nf">crop_orientation_predictor</span><span class="p">(</span>
     <span class="n">arch</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;mobilenet_v3_small_crop_orientation&quot;</span><span class="p">,</span> <span class="n">pretrained</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">:</span> <span class="n">Any</span>
 <span class="p">)</span> <span class="o">-&gt;</span> <span class="n">OrientationPredictor</span><span class="p">:</span>
-<span class="w">    </span><span class="sd">&quot;&quot;&quot;Orientation classification architecture.</span>
+<span class="w">    </span><span class="sd">&quot;&quot;&quot;Crop orientation classification architecture.</span>
 
 <span class="sd">    &gt;&gt;&gt; import numpy as np</span>
 <span class="sd">    &gt;&gt;&gt; from doctr.models import crop_orientation_predictor</span>
-<span class="sd">    &gt;&gt;&gt; model = crop_orientation_predictor(arch=&#39;classif_mobilenet_v3_small&#39;, pretrained=True)</span>
-<span class="sd">    &gt;&gt;&gt; input_crop = (255 * np.random.rand(600, 800, 3)).astype(np.uint8)</span>
+<span class="sd">    &gt;&gt;&gt; model = crop_orientation_predictor(arch=&#39;mobilenet_v3_small_crop_orientation&#39;, pretrained=True)</span>
+<span class="sd">    &gt;&gt;&gt; input_crop = (255 * np.random.rand(256, 256, 3)).astype(np.uint8)</span>
 <span class="sd">    &gt;&gt;&gt; out = model([input_crop])</span>
 
 <span class="sd">    Args:</span>
 <span class="sd">    ----</span>
-<span class="sd">        arch: name of the architecture to use (e.g. &#39;mobilenet_v3_small&#39;)</span>
+<span class="sd">        arch: name of the architecture to use (e.g. &#39;mobilenet_v3_small_crop_orientation&#39;)</span>
+<span class="sd">        pretrained: If True, returns a model pre-trained on our recognition crops dataset</span>
+<span class="sd">        **kwargs: keyword arguments to be passed to the OrientationPredictor</span>
+
+<span class="sd">    Returns:</span>
+<span class="sd">    -------</span>
+<span class="sd">        OrientationPredictor</span>
+<span class="sd">    &quot;&quot;&quot;</span>
+    <span class="k">return</span> <span class="n">_orientation_predictor</span><span class="p">(</span><span class="n">arch</span><span class="p">,</span> <span class="n">pretrained</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div>
+
+
+
+<div class="viewcode-block" id="page_orientation_predictor">
+<a class="viewcode-back" href="../../../../modules/models.html#doctr.models.classification.page_orientation_predictor">[docs]</a>
+<span class="k">def</span> <span class="nf">page_orientation_predictor</span><span class="p">(</span>
+    <span class="n">arch</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;mobilenet_v3_small_page_orientation&quot;</span><span class="p">,</span> <span class="n">pretrained</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">:</span> <span class="n">Any</span>
+<span class="p">)</span> <span class="o">-&gt;</span> <span class="n">OrientationPredictor</span><span class="p">:</span>
+<span class="w">    </span><span class="sd">&quot;&quot;&quot;Page orientation classification architecture.</span>
+
+<span class="sd">    &gt;&gt;&gt; import numpy as np</span>
+<span class="sd">    &gt;&gt;&gt; from doctr.models import page_orientation_predictor</span>
+<span class="sd">    &gt;&gt;&gt; model = page_orientation_predictor(arch=&#39;mobilenet_v3_small_page_orientation&#39;, pretrained=True)</span>
+<span class="sd">    &gt;&gt;&gt; input_page = (255 * np.random.rand(512, 512, 3)).astype(np.uint8)</span>
+<span class="sd">    &gt;&gt;&gt; out = model([input_page])</span>
+
+<span class="sd">    Args:</span>
+<span class="sd">    ----</span>
+<span class="sd">        arch: name of the architecture to use (e.g. &#39;mobilenet_v3_small_page_orientation&#39;)</span>
 <span class="sd">        pretrained: If True, returns a model pre-trained on our recognition crops dataset</span>
 <span class="sd">        **kwargs: keyword arguments to be passed to the OrientationPredictor</span>
 

latest/_sources/modules/models.rst.txt

@@ -27,6 +27,8 @@ doctr.models.classification
 
 .. autofunction:: doctr.models.classification.mobilenet_v3_small_crop_orientation
 
+.. autofunction:: doctr.models.classification.mobilenet_v3_small_page_orientation
+
 .. autofunction:: doctr.models.classification.magc_resnet31
 
 .. autofunction:: doctr.models.classification.vit_s
@@ -41,6 +43,8 @@ doctr.models.classification
 
 .. autofunction:: doctr.models.classification.crop_orientation_predictor
 
+.. autofunction:: doctr.models.classification.page_orientation_predictor
+
 
 doctr.models.detection
 ----------------------

latest/genindex.html

@@ -452,6 +452,8 @@ <h2>M</h2>
         <li><a href="modules/models.html#doctr.models.classification.mobilenet_v3_small">mobilenet_v3_small() (in module doctr.models.classification)</a>
 </li>
         <li><a href="modules/models.html#doctr.models.classification.mobilenet_v3_small_crop_orientation">mobilenet_v3_small_crop_orientation() (in module doctr.models.classification)</a>
+</li>
+        <li><a href="modules/models.html#doctr.models.classification.mobilenet_v3_small_page_orientation">mobilenet_v3_small_page_orientation() (in module doctr.models.classification)</a>
 </li>
         <li><a href="modules/models.html#doctr.models.classification.mobilenet_v3_small_r">mobilenet_v3_small_r() (in module doctr.models.classification)</a>
 </li>
@@ -492,6 +494,8 @@ <h2>P</h2>
   <table style="width: 100%" class="indextable genindextable"><tr>
     <td style="width: 33%; vertical-align: top;"><ul>
         <li><a href="modules/io.html#doctr.io.Page">Page (class in doctr.io)</a>
+</li>
+        <li><a href="modules/models.html#doctr.models.classification.page_orientation_predictor">page_orientation_predictor() (in module doctr.models.classification)</a>
 </li>
     </ul></td>
     <td style="width: 33%; vertical-align: top;"><ul>