update docs

docs/source/index.rst

@@ -1,6 +1,12 @@
 Introduction
 =========================================
 
+
+.. raw:: html
+
+    <p><font color="red">*NOT FOR MEDICAL USE*</font></p>
+
+
 A library for chest X-ray datasets and models. Including pre-trained models.
 
 TorchXRayVision is an open source software library for working with chest X-ray datasets and deep learning models. It provides a common interface and common pre-processing chain for a wide set of publicly available chest X-ray datasets. In addition, a number of classification and representation learning models with different architectures, trained on different data combinations, are available through the library to serve as baselines or feature extractors.
@@ -10,6 +16,15 @@ TorchXRayVision is an open source software library for working with chest X-ray
 
 Twitter: `@torchxrayvision <https://twitter.com/torchxrayvision>`_
 
+
+.. raw:: html
+
+    <div style="position: relative; padding-bottom: 56.25%; height: 0; overflow: hidden; max-width: 100%; height: auto;">
+        <iframe src="https://www.youtube.com/embed/lvXc3O2n56w" frameborder="0" allowfullscreen style="position: absolute; top: 0; left: 0; width: 100%; height: 100%;"></iframe>
+    </div>
+
+
+
 .. _installation:
 
 Installation

docs/source/models.rst

@@ -2,8 +2,11 @@
 Models
 ======
 
-Core Classifiers
-++++++++++++++++
+Model benchmarks for classifiers are `here <https://github.com/mlmed/torchxrayvision/blob/master/BENCHMARKS.md>`_
+
+
+Model Interface
++++++++++++++++
 
 .. automodule:: torchxrayvision.models
 
@@ -12,28 +15,32 @@ Core Classifiers
 
         .. automethod:: forward
 
+
+XRV Pathology Classifiers
++++++++++++++++++++++++++
+
     .. autoclass:: DenseNet(weights=SPECIFY, op_threshs=None, apply_sigmoid=False)
         :members:
 
     .. autoclass:: ResNet(weights=SPECIFY, op_threshs=None, apply_sigmoid=False)
         :members:
 
-Core Autoencoders
-+++++++++++++++++
+XRV ResNet Autoencoder
+++++++++++++++++++++++
 
 .. automodule:: torchxrayvision.autoencoders
 
     .. autoclass:: ResNetAE(weights=SPECIFY)
 
 
-CheXpert Pathologies
-++++++++++++++++++++
+CheXpert Pathology Classifier
++++++++++++++++++++++++++++++
 
 .. automodule:: torchxrayvision.baseline_models.chexpert
    :members:
 
-JF Healthcare Pathologies
-+++++++++++++++++++++++++
+JF Healthcare Pathology Classifier
+++++++++++++++++++++++++++++++++++
 
 .. automodule:: torchxrayvision.baseline_models.jfhealthcare
    :members:
@@ -57,7 +64,7 @@ Riken Age Model
    :members:
 
 Xinario View Model
-+++++++++++++++
+++++++++++++++++++
 
 .. automodule:: torchxrayvision.baseline_models.xinario
-   :members:
+   :members:

torchxrayvision/autoencoders.py

@@ -222,6 +222,8 @@ def ResNetAE(weights=None):
     """A ResNet based autoencoder.
 
     Possible weights for this class include:
+    
+    - "101-elastic" trained on PadChest, NIH, CheXpert, and MIMIC. From the paper https://arxiv.org/abs/2102.09475
 
     .. code-block:: python