Add documentation for save and load functions.

docs/sources/models.md

@@ -6,13 +6,13 @@ Linear stack of layers.
 model = keras.models.Sequential()
 ```
 - __Methods__:
-    - __add(layer)__: Add a layer to the model.
-    - __compile(optimizer, loss, class_mode="categorical")__: 
+    - __add__(layer): Add a layer to the model.
+    - __compile__(optimizer, loss, class_mode="categorical"): 
         - __Arguments__: 
             - __optimizer__: str (name of optimizer) or optimizer object. See [optimizers](optimizers.md).
             - __loss__: str (name of objective function) or objective function. See [objectives](objectives.md).
             - __class_mode__: one of "categorical", "binary". This is only used for computing classification accuracy or using the predict_classes method. 
-    - __fit(X, y, batch_size=128, nb_epoch=100, verbose=1, validation_split=0., validation_data=None, shuffle=True, show_accuracy=False)__: Train a model for a fixed number of epochs.
+    - __fit__(X, y, batch_size=128, nb_epoch=100, verbose=1, validation_split=0., validation_data=None, shuffle=True, show_accuracy=False): Train a model for a fixed number of epochs.
         - __Arguments__: 
             - __X__: data.
             - __y__: labels.
@@ -23,15 +23,16 @@ model = keras.models.Sequential()
             - __validation_data__: tuple (X, y) to be used as held-out validation data. Will override validation_split.
             - __shuffle__: boolean. Whether to shuffle the samples at each epoch.
             - __show_accuracy__: boolean. Whether to display class accuracy in the logs to stdout at each epoch.
-    - __evaluate(X, y, batch_size=128, show_accuracy=False, verbose=1)__: Show performance of the model over some validation data.
+    - __evaluate__(X, y, batch_size=128, show_accuracy=False, verbose=1): Show performance of the model over some validation data.
         - __Arguments__: Same meaning as fit method above. verbose is used as a binary flag (progress bar or nothing).
-    - __predict_proba(X, batch_size=128, verbose=1)__: Return an array of predictions for some test data.
+    - __predict_proba__(X, batch_size=128, verbose=1): Return an array of predictions for some test data.
         - __Arguments__: Same meaning as fit method above.
-    - __predict_classes(X, batch_size=128, verbose=1)__: Return an array of class predictions for some test data.
+    - __predict_classes__(X, batch_size=128, verbose=1): Return an array of class predictions for some test data.
         - __Arguments__: Same meaning as fit method above. verbose is used as a binary flag (progress bar or nothing).
-    - __train__(X, y, accuracy=False)__: Single gradient update on one batch. if accuracy==False, return tuple (loss_on_batch, accuracy_on_batch). Else, return loss_on_batch.
-    - __test__(X, y, accuracy=False)__: Single performance evaluation on one batch. if accuracy==False, return tuple (loss_on_batch, accuracy_on_batch). Else, return loss_on_batch.
-
+    - __train__(X, y, accuracy=False): Single gradient update on one batch. if accuracy==False, return tuple (loss_on_batch, accuracy_on_batch). Else, return loss_on_batch.
+    - __test__(X, y, accuracy=False): Single performance evaluation on one batch. if accuracy==False, return tuple (loss_on_batch, accuracy_on_batch). Else, return loss_on_batch.
+    - __save_weights__(fname): Store the weights of all layers to a HDF5 file. 
+    - __load_weights__(fname): Sets the weights of a model, based to weights stored by __save__weights__. You can only __load__weights__ on a savefile from a model with an identical architecture. __save__weights__ can be called either before or after the __compile__ step.
 
 __Examples__: