First draft of the documentation for callbacks

docs/mkdocs.yml

@@ -25,6 +25,7 @@ pages:
 - [regularizers.md, Regularizers]
 - [constraints.md, Constraints]
 - [initializations.md, Initializations]
+- [callbacks.md, Callbacks]
 
 - [datasets.md, Datasets]
 

docs/sources/callbacks.md

@@ -0,0 +1,39 @@
+## Base class
+
+```python
+keras.callbacks.Callback()
+```
+- __Properties__:
+    - __params__: dict. Training parameters (eg. verbosity, batch size, number of epochs...).
+    - __model__: `keras.models.Model`. Reference of the model being trained.
+- __Methods__:
+    - __on_train_begin__(): Method called at the beginning of training.
+    - __on_train_end__(): Method called at the end of training.
+    - __on_epoch_begin__(epoch): Method called at the beginning of epoch `epoch`.
+    - __on_epoch_end__(epoch, val_loss, val_acc): Method called at the end of epoch `epoch`, with validation loss `val_loss` and accuracy `val_acc` (if applicable).
+    - __on_batch_begin__(batch): Method called at the beginning of batch `batch`.
+    - __on_batch_end__(batch, indices, loss, accuracy): Method called at the end of batch `batch`, with loss `loss` and accuracy `accuracy` (if applicable).
+
+
+### Example
+
+```python
+from keras.models import Sequential
+from keras.layers.core import Dense, Activation
+from keras.callbacks import History
+
+model = Sequential()
+model.add(Dense(784, 10, init='uniform'))
+model.add(Activation('softmax'))
+
+model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
+
+history = History()
+model.fit(X_train, Y_train, batch_size=128, nb_epoch=20, verbose=0, callbacks=[history])
+
+print history.losses
+# outputs
+'''
+[0.66047596406559383, 0.3547245744908703, ..., 0.25953155204159617, 0.25901699725311789]
+'''
+```

docs/sources/models.md

@@ -13,7 +13,7 @@ model = keras.models.Sequential()
             - __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. 
             - __theano_mode__: A `theano.compile.mode.Mode` ([reference](http://deeplearning.net/software/theano/library/compile/mode.html)) instance controlling specifying compilation options.
-    - __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, callbacks=[]): Train a model for a fixed number of epochs.
         - __Return__: a history dictionary with a record of training loss values at successive epochs, as well as validation loss values (if applicable), accuracy (if applicable), etc.
         - __Arguments__: 
             - __X__: data.
@@ -25,6 +25,7 @@ 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.
+            - __callbacks__: `keras.callbacks.Callback` list. List of callbacks to apply during training. See [callbacks](callbacks.md).
     - __evaluate__(X, y, batch_size=128, show_accuracy=False, verbose=1): Show performance of the model over some validation data.
         - __Return__: The loss score over the data.
         - __Arguments__: Same meaning as fit method above. verbose is used as a binary flag (progress bar or nothing).

test/test_callbacks.py

@@ -115,7 +115,6 @@ class DrawActivations(Callback):
             self.imgs.set_title('Epoch #%d - Batch #%d' % (self.epoch, batch))
 
     def on_train_end(self):
-        # anim = animation.ArtistAnimation(self.fig, self.imgs, interval=10, blit=False, repeat_delay=1000)
         anim = SubplotTimedAnimation(self.fig, self.imgs, grid=(1,5), interval=10, blit=False, repeat_delay=1000)
         # anim.save('test_gif.gif', fps=15, writer='imagemagick')
         plt.show()