merge

Author: fchollet

docs/mkdocs.yml

@@ -30,6 +30,7 @@ pages:
   - Advanced Activations Layers: layers/advanced_activations.md
   - Normalization Layers: layers/normalization.md
   - Embedding Layers: layers/embeddings.md
+  - Noise layers: layers/noise.md
   - Containers: layers/containers.md
 - Preprocessing:
   - Sequence Preprocessing: preprocessing/sequence.md

docs/sources/layers/noise.md

@@ -36,4 +36,3 @@ The Gaussian noise is only used at training time.
 
     - __p__: float, drop probability as with Dropout.
 
----

examples/mnist_irnn.py

@@ -12,7 +12,7 @@
 from keras.utils import np_utils
 
 '''
-    This is a reproduction of the IRNN experiment 
+    This is a reproduction of the IRNN experiment
     with pixel-by-pixel sequential MNIST in
     "A Simple Way to Initialize Recurrent Networks of Rectified Linear Units "
     by Quoc V. Le, Navdeep Jaitly, Geoffrey E. Hinton
@@ -23,8 +23,8 @@
     Optimizer is replaced with RMSprop which yields more stable and steady
     improvement.
 
-    0.80 train/test accuracy and 0.55 train/test loss after 70 epochs
-    (it's still underfitting at that point, though).
+    Reaches 0.93 train/test accuracy after 900 epochs (which roughly corresponds
+    to 1687500 steps in the original paper.)
 '''
 
 batch_size = 32
@@ -64,7 +64,7 @@
 rmsprop = RMSprop(lr=learning_rate)
 model.compile(loss='categorical_crossentropy', optimizer=rmsprop)
 
-model.fit(X_train, Y_train, batch_size=16, nb_epoch=nb_epochs,
+model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epochs,
           show_accuracy=True, verbose=1, validation_data=(X_test, Y_test))
 
 scores = model.evaluate(X_test, Y_test, show_accuracy=True, verbose=0)
@@ -79,9 +79,9 @@
 rmsprop = RMSprop(lr=learning_rate)
 model.compile(loss='categorical_crossentropy', optimizer=rmsprop)
 
-model.fit(X_train, Y_train, batch_size=16, nb_epoch=nb_epochs,
+model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epochs,
           show_accuracy=True, verbose=1, validation_data=(X_test, Y_test))
 
 scores = model.evaluate(X_test, Y_test, show_accuracy=True, verbose=0)
 print('LSTM test score:', scores[0])
-print('LSTM test accuracy:', scores[1])
+print('LSTM test accuracy:', scores[1])