Output a 3 shape LSTM

Question

I'm trying to understand the basics of the LSTM's and I built this model:

self.model = Sequential()

self.model.add(LSTM(self.config.layers[0],
    input_shape=(None, channel.X_train.shape[2]),
    return_sequences=True))
    self.model.add(Dropout(self.config.dropout))

self.model.add(LSTM(
    self.config.layers[1],
    return_sequences=True))
self.model.add(Dropout(self.config.dropout))

self.model.add(Dense(
self.config.n_predictions))
self.model.add(Activation('linear'))

The input shape is (2000, 200, 10) and I need an output of the same shape. I tried on this way but I got the error:

ValueError: Input 0 is incompatible with layer lstm_2: expected ndim=3, found ndim=2

If I set to False the return_sequence parameter of the second layer it works, but I get an output of shape (X, Y), which is not what I want.

Output a 3 shape LSTM

0 Answers