embedding_layer = Embedding(len(word_index) + 1,
EMBEDDING_DIM,
weights=[embedding_matrix],
mask_zero=False,
input_length=MAX_SEQUENCE_LENGTH,
trainable=False)
print('Traing and validation set number of positive and negative reviews')
print(y_train.sum(axis=0))
print(y_val.sum(axis=0))
sequence_input = Input(shape=(MAX_SEQUENCE_LENGTH, ), dtype='int32')
embedded_sequences = embedding_layer(sequence_input)
dense_1 = Dense(100, activation='tanh')(embedded_sequences)
max_pooling = GlobalMaxPooling1D()(dense_1)
dense_2 = Dense(2, activation='softmax')(max_pooling)
model = Model(sequence_input, dense_2)
rsmprop = model.RMSprop(lr=0.001, rho=0.9, epsilon=1e-06)
model.compile(loss='categorical_crossentropy',
optimizer='rsmprop',
metrics=['acc'])
model.summary()
model.fit(x_train,
y_train,
validation_data=(x_val, y_val),
nb_epoch=10,
batch_size=50)
