Fine tuned with "Stateful LSTMs, Stacked"

[erturkkadir]

If you try "Stateful LSTMs, Stacked" with following parameters, you may get quick (may be better) solution in terms of frequency and phase (not amplitude),

batch_size = 1

model = Sequential() model.add(LSTM(128, batch_input_shape=(batch_size, look_back, 1), stateful=True, return_sequences=True)) model.add(Dropout(0.2)) model.add(LSTM(256, stateful=True)) model.add(Dense(1))

model.compile(loss='mse', optimizer='adadelta') for i in range(5): model.fit(trainX, trainY, epochs=1, batch_size=batch_size, verbose=2, shuffle=False) model.reset_states()

[sachinruk]

Did you mean to put more nodes (256) in the upper layer or was that a typo. And thanks will try it out.

[erturkkadir]

I did since I noticed that the more unit in second stack gets better in this case