Keras stateful LSTM

Question

Please consider this simple example.

nb_samples = 100000
X = np.random.randn(nb_samples)
Y = X[1:]
X = X[:-1]
X = X.reshape((len(Y), 1, 1))
Y = Y.reshape((len(Y), 1))

So, we have basically

Y[i] = X[i-1]

and the model is just a delay operator.

I can learn this model using stateless LSTM, but I want to understand and apply stateful LSTM in Keras here.

So, I'm trying to learn this model using state-based LSTM by setting pairs of values (x, y)one by one(batch_size = 1)

model = Sequential()
model.add(LSTM(batch_input_shape=(1, 1, 1),
               output_dim =10,
               activation='tanh', stateful=True
          )
    )
model.add(Dense(output_dim=1, activation='linear'))
model.compile(loss='mse', optimizer='adam')


for epoch in range(50):
    model.fit(X_train,
              Y_train,
              nb_epoch = 1,
              verbose = 2,
              batch_size = 1,
              shuffle = False)
    model.reset_states()

But the model does not recognize anything.

Following Marcin’s suggestion, I changed the training code as follows:

for epoch in range(10000):
    model.reset_states()
    train_loss = 0
    for i in range(Y_train.shape[0]):
        train_loss += model.train_on_batch(X_train[i:i+1],
                         Y_train[i:i+1],
                         )
    print '# epoch', epoch, '  loss ', train_loss/float(Y_train.shape[0])

but I still see an average loss of about 1, which is the standard deviation of my randomly generated data, so the model does not seem to be studying.

Do I have something wrong?

Answer 1

, reset - - - - , - . :

for epoch in range(50):
    model.train_on_batch(X_train,
              Y_train)
    model.reset_states()

A train_on_batch reset , .