I'm building a model with multiple sequential models that I need to merge before training the dataset. It seems keras.engine.topology.Merge isn't supported on Keras 2.0 anymore. I tried keras.layers.Add and keras.layers.Concatenate and it doesn't work as well.
Here's my code:
model = Sequential()
model1 = Sequential()
model1.add(Embedding(len(word_index) + 1, 300, weights = [embedding_matrix], input_length = 40, trainable = False))
model1.add(TimeDistributed(Dense(300, activation = 'relu')))
model1.add(Lambda(lambda x: K.sum(x, axis = 1), output_shape = (300, )))
model2 = Sequential()
###Same as model1###
model3 = Sequential()
model3.add(Embedding(len(word_index) + 1, 300, weights = [embedding_matrix], input_length = 40, trainable = False))
model3.add(Convolution1D(nb_filter = nb_filter, filter_length = filter_length, border_mode = 'valid', activation = 'relu', subsample_length = 1))
model3.add(GlobalMaxPooling1D())
model3.add(Dropout(0.2))
model3.add(Dense(300))
model3.add(Dropout(0.2))
model3.add(BatchNormalization())
model4 = Sequential()
###Same as model3###
model5 = Sequential()
model5.add(Embedding(len(word_index) + 1, 300, input_length = 40, dropout = 0.2))
model5.add(LSTM(300, dropout_W = 0.2, dropout_U = 0.2))
model6 = Sequential()
###Same as model5###
merged_model = Sequential()
merged_model.add(Merge([model1, model2, model3, model4, model5, model6], mode = 'concat'))
merged_model.add(BatchNormalization())
merged_model.add(Dense(300))
merged_model.add(PReLU())
merged_model.add(Dropout(0.2))
merged_model.add(Dense(1))
merged_model.add(BatchNormalization())
merged_model.add(Activation('sigmoid'))
merged_model.compile(loss = 'binary_crossentropy', optimizer = 'adam', metrics = ['accuracy'])
checkpoint = ModelCheckpoint('weights.h5', monitor = 'val_acc', save_best_only = True, verbose = 2)
merged_model.fit([x1, x2, x1, x2, x1, x2], y = y, batch_size = 384, nb_epoch = 200, verbose = 1, validation_split = 0.1, shuffle = True, callbacks = [checkpoint])
Error:
name 'Merge' is not defined
Using keras.layers.Add and keras.layers.Concatenate says cannot do it with sequential models.
What's the workaround for it?
If I were you, I would use Keras functional API in this case, at least for making the final model (i.e. merged_model). It gives you much more flexibility and let you easily define complex models:
from keras.models import Model
from keras.layers import concatenate
merged_layers = concatenate([model1.output, model2.output, model3.output,
model4.output, model5.output, model6.output])
x = BatchNormalization()(merged_layers)
x = Dense(300)(x)
x = PReLU()(x)
x = Dropout(0.2)(x)
x = Dense(1)(x)
x = BatchNormalization()(x)
out = Activation('sigmoid')(x)
merged_model = Model([model1.input, model2.input, model3.input,
model4.input, model5.input, model6.input], [out])
merged_model.compile(loss = 'binary_crossentropy', optimizer = 'adam', metrics = ['accuracy'])
You can also do the same thing for other models you have defined. As I mentioned, functional API gives you more control over the structure of the model, so it is recommended to be used in case of creating complex models like this.