CODEWITHSUNDEEP
pythontensorflowkeras
Montana Burr
Montana Burr

Reputation: 287

How do I properly use a Keras Add layer?

I'm trying to merge two LSTM layers together, to no success.

answers_questions_lstm = LSTM(256,input_shape=(8,4,))
answers_contexts_lstm = LSTM(256,input_shape=(10,6,))
answers_combined_lstm = Add()([answers_questions_lstm,answers_contexts_lstm])
answers_hidden_1 = Dense(124)(answers_combined_lstm)
answers_output = Dense(outputTrain.shape[1])
answers_network_1.summary()

This gives me "A merge layer should be called on a list of inputs." Why?

Upvotes: 0

Views: 148

Answers (1)

adamconkey
adamconkey

Reputation: 4745

Since you are using the Keras Functional API, you should start with some Input layers. Then call your LSTM layers on the Inputs to get tensor outputs that can then be passed to the Add layer:

answers_questions_input = Input(shape=(8,4))
answers_contexts_input = Input(shape=(10,6))
answers_questions_lstm = LSTM(256)(answers_questions_input)
answers_contexts_lstm = LSTM(256)(answers_contexts_input)
answers_combined_lstm = Add()([answers_questions_lstm, answers_contexts_lstm])
answers_hidden_1 = Dense(124)(answers_combined_lstm)
answers_output = Dense(outputTrain.shape[1])
answers_network_1 = Model(inputs=[answers_questions_input, answers_contexts_input], outputs=answers_output)
answers_network_1.summary()

Upvotes: 3

Related Questions