One for many LSTMs in Keras

Question

Is it possible to implement one-to-many LSTM in Keras?
If so, can you provide me with a simple example?

Answer 1

This is possible using the RepeatVector layer. For instance:

 model = Sequential() model.add(Dense(10, input_shape=(1)) model.add(RepeatVector(10)) model.add(LSTM(1, return_sequences=True)) 

Then - the input form (1) , and the output - (10, 1) .