Update models.html

Added links to model information.

Author: brianjo

docs/stable/torchvision/models.html

@@ -928,6 +928,12 @@ <h3>ResNext<a class="headerlink" href="#id13" title="Permalink to this headline"
 </div>
 <div class="section" id="semantic-segmentation">
 <h2>Semantic Segmentation<a class="headerlink" href="#semantic-segmentation" title="Permalink to this headline">¶</a></h2>
+<p>The models subpackage contains definitions for the following model
+architectures for semantic segmentation:</p>
+<ul class="simple">
+<li><p><a class="reference external" href="https://arxiv.org/abs/1411.4038">FCN ResNet101</a></p></li>
+<li><p><a class="reference external" href="https://arxiv.org/abs/1706.05587">DeepLabV3 ResNet101</a></p></li>
+</ul>
 <p>As with image classification models, all pre-trained models expect input images normalized in the same way.
 The images have to be loaded in to a range of <code class="docutils literal notranslate"><span class="pre">[0,</span> <span class="pre">1]</span></code> and then normalized using
 <code class="docutils literal notranslate"><span class="pre">mean</span> <span class="pre">=</span> <span class="pre">[0.485,</span> <span class="pre">0.456,</span> <span class="pre">0.406]</span></code> and <code class="docutils literal notranslate"><span class="pre">std</span> <span class="pre">=</span> <span class="pre">[0.229,</span> <span class="pre">0.224,</span> <span class="pre">0.225]</span></code>.
@@ -1036,6 +1042,12 @@ <h3>DeepLabV3<a class="headerlink" href="#deeplabv3" title="Permalink to this he
 </div>
 <div class="section" id="object-detection-instance-segmentation-and-person-keypoint-detection">
 <h2>Object Detection, Instance Segmentation and Person Keypoint Detection<a class="headerlink" href="#object-detection-instance-segmentation-and-person-keypoint-detection" title="Permalink to this headline">¶</a></h2>
+<p>The models subpackage contains definitions for the following model
+architectures for detection:</p>
+<ul class="simple">
+<li><p><a class="reference external"href="https://arxiv.org/abs/1506.01497">Faster R-CNN ResNet-50 FPN</a></p></li>
+<li><p><a class="reference external"href="https://arxiv.org/abs/1703.06870">Mask R-CNN ResNet-50 FPN</a></p></li>
+</ul>
 <p>The pre-trained models for detection, instance segmentation and
 keypoint detection are initialized with the classification models
 in torchvision.</p>
@@ -1666,4 +1678,4 @@ <h2>Resources</h2>
     })
   </script>
 </body>
-</html>
+</html>