ValueError: Input 0 is incompatible with layer lstm_55: expected ndim=3, found ndim=2

Question

I use 2 LSTM multilayer stack with dense layer it's showing me an error.
Here is my code :

model.add(LSTM(5, batch_input_shape=(batch_size, X.shape[1], X.shape[2]), stateful=True))
model.add(Dropout(0.2))
model.add(LSTM(5,return_sequences=False))
model.add(Dropout(0.2))
model.add(Dense(units=1))
model.add(Activation('relu'))

batch_input_shape=(1,1,4)

It's showing me following error:

ValueError: Input 0 is incompatible with layer lstm_57: expected ndim=3, found ndim=2

Answer 1

Your second LSTM admits input of shape [batch_size, time_steps, features]. The first LSTM yields outputs of shape [batch_size, output_units], since the parameter return_sequences defaults to False.

You need to explicitly set return_sequences = True in your first LSTM to render the two recurrent layers compatible.