Remove class_mode, add support for acc in Graph

chardmeier · Mar 12, 2016 · 0c1af09 · 0c1af09
1 parent 70431a5
commit 0c1af09
Show file tree

Hide file tree

Showing 6 changed files with 211 additions and 50 deletions.
diff --git a/docs/templates/examples.md b/docs/templates/examples.md
@@ -70,11 +70,8 @@ model.add(Dense(64, activation='relu'))
 model.add(Dropout(0.5))
 model.add(Dense(1, activation='sigmoid'))
 
-# "class_mode" defaults to "categorical". For correctly displaying accuracy
-# in a binary classification problem, it should be set to "binary".
 model.compile(loss='binary_crossentropy',
-              optimizer='rmsprop',
-              class_mode='binary')
+              optimizer='rmsprop')
 ```
 
 ------------------

diff --git a/examples/imdb_bidirectional_lstm.py b/examples/imdb_bidirectional_lstm.py
@@ -55,7 +55,7 @@
 print('Train...')
 model.fit({'input': X_train, 'output': y_train},
           batch_size=batch_size,
-          nb_epoch=4)
+          nb_epoch=4, show_accuracy=True)
 acc = accuracy(y_test,
                np.round(np.array(model.predict({'input': X_test},
                                                batch_size=batch_size)['output'])))

diff --git a/examples/imdb_cnn.py b/examples/imdb_cnn.py
@@ -71,8 +71,7 @@
 model.add(Activation('sigmoid'))
 
 model.compile(loss='binary_crossentropy',
-              optimizer='rmsprop',
-              class_mode='binary')
+              optimizer='rmsprop')
 model.fit(X_train, y_train, batch_size=batch_size,
           nb_epoch=nb_epoch, show_accuracy=True,
           validation_data=(X_test, y_test))
diff --git a/examples/imdb_lstm.py b/examples/imdb_lstm.py
@@ -38,7 +38,7 @@
 print(len(X_train), 'train sequences')
 print(len(X_test), 'test sequences')
 
-print("Pad sequences (samples x time)")
+print('Pad sequences (samples x time)')
 X_train = sequence.pad_sequences(X_train, maxlen=maxlen)
 X_test = sequence.pad_sequences(X_test, maxlen=maxlen)
 print('X_train shape:', X_train.shape)
@@ -54,10 +54,9 @@
 
 # try using different optimizers and different optimizer configs
 model.compile(loss='binary_crossentropy',
-              optimizer='adam',
-              class_mode="binary")
+              optimizer='adam')
 
-print("Train...")
+print('Train...')
 model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=15,
           validation_data=(X_test, y_test), show_accuracy=True)
 score, acc = model.evaluate(X_test, y_test,