add u-net to docs. Also add example notebook for training hovernet wh…

…ich was missing

docs/source/index.rst

@@ -54,6 +54,7 @@ Dana-Farber Cancer Institute.
  examples/link_stain_normalization
  examples/link_nucleus_detection
  examples/link_preprocessing_pipeline
+ examples/link_train_hovernet
 
 .. toctree::
  :maxdepth: 2

docs/source/models.rst

@@ -3,20 +3,28 @@ Models
 
 ``PathML`` comes with several model architectures ready to use out of the box.
 
-.. table::
- :widths: 20, 20, 60
+.. list-table:: Models included in PathML
+ :widths: 15, 70, 15
+ :header-rows: 1
 
- ===================================== ============ =============
- Model Reference Description
- ===================================== ============ =============
- U-net (in progress) [Unet]_ A model for segmentation in biomedical images
- :class:`~pathml.ml.hovernet.HoVerNet` [HoVerNet]_ A model for nucleus segmentation and classification in H&E images
- ===================================== ============ =============
+ * - Model
+ - Description
+ - Reference
+ * - :class:`~pathml.ml.unet.UNet`
+ - A standard general-purpose model designed for segmentation in biomedical images.
+ Architecture consists of an 4 encoder blocks followed by 4 decoder blocks.
+ Skip connections propagate information from each layer of the encoder to the corresponding layer in
+ the decoder.
+ - [Unet]_
+ * - :class:`~pathml.ml.hovernet.HoVerNet`
+ - A model for simultaneous nucleus segmentation and classification in H&E images.
+ Architecture consists of a single encoder with three separate decoder branches: one to perform binary
+ classification of nuclear pixels (NP), one to compute horizontal and vertical nucleus maps (HV), and one which
+ is used in the classification setting to perform classification of nuclear pixels (NC).
+ - [HoVerNet]_
 
 You can also use models from `torchvision.models <https://pytorch.org/docs/stable/torchvision/models.html>`_, or create your own!
 
-In many cases, model parameters (weights) for pretrained networks may be available for use through the Model Repository.
-
 References
 ----------