Doc fixes (#1362)

* Doc fixes from #1357 (awaelchli's comments) + changelog.

* Fix indentation.

* Add blank line to fix doc build?

CHANGELOG.md

@@ -21,7 +21,7 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 - Added `summary` method to Profilers. ([#1259](https://github.com/PyTorchLightning/pytorch-lightning/pull/1259))
 - Added informative errors if user defined dataloader has zero length ([#1280](https://github.com/PyTorchLightning/pytorch-lightning/pull/1280))
 - Added testing for python 3.8 ([#915](https://github.com/PyTorchLightning/pytorch-lightning/pull/915)) 
-
+- Added a `training_epoch_end` method which is the mirror of `validation_epoch_end`. ([#1357](https://github.com/PyTorchLightning/pytorch-lightning/pull/1357))
 ### Changed
 
 - Changed `progress_bar_refresh_rate` trainer flag to disable progress bar when set to 0. ([#1108](https://github.com/PyTorchLightning/pytorch-lightning/pull/1108))

pytorch_lightning/core/lightning.py

@@ -245,16 +245,18 @@ def training_epoch_end(
             for train_batch in train_data:
                 out = training_step(train_batch)
                 train_outs.append(out)
-            training_epoch_end(val_outs)
+            training_epoch_end(train_outs)
 
         Args:
             outputs: List of outputs you defined in training_step, or if there are multiple
-            dataloaders, a list containing a list of outputs for each dataloader
+                     dataloaders, a list containing a list of outputs for each dataloader
 
         Return:
-            Dict or OrderedDict (dict): Dict has the following optional keys:
-            progress_bar -> Dict for progress bar display. Must have only tensors
-            log -> Dict of metrics to add to logger. Must have only tensors (no images, etc)
+            Dict or OrderedDict
+            May contain the following optional keys:
+
+                - log (metrics to be added to the logger ; only tensors)
+                - any metric used in a callback (e.g. early stopping).
 
         .. note:: If this method is not overridden, this won't be called.
 
@@ -282,7 +284,7 @@ def training_epoch_end(self, outputs):
 
             With multiple dataloaders, `outputs` will be a list of lists. The outer list contains
             one entry per dataloader, while the inner list contains the individual outputs of
-            each validation step for that dataloader.
+            each training step for that dataloader.
 
             .. code-block:: python
 
@@ -539,12 +541,14 @@ def validation_epoch_end(
 
         Args:
             outputs: List of outputs you defined in validation_step, or if there are multiple
-            dataloaders, a list containing a list of outputs for each dataloader
+                     dataloaders, a list containing a list of outputs for each dataloader
 
         Return:
-            Dict or OrderedDict (dict): Dict has the following optional keys:
-            progress_bar -> Dict for progress bar display. Must have only tensors
-            log -> Dict of metrics to add to logger. Must have only tensors (no images, etc)
+            Dict or OrderedDict
+            May have the following optional keys:
+
+                - progress_bar (dict for progress bar display ; only tensors)
+                - log (dict of metrics to add to logger ; only tensors).
 
         .. note:: If you didn't define a validation_step, this won't be called.
 

pytorch_lightning/trainer/training_loop.py

@@ -826,4 +826,4 @@ def _recursive_detach(in_dict):
             out_dict.update({k: v.detach()})
         else:
             out_dict.update({k: v})
-        return out_dict
+    return out_dict