在tflearn中添加多个LSTM层

import tflearn
from tflearn.layers.recurrent import lstm
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.estimator import regression

net = tflearn.input_data(shape=[None, input_size, 1])

net = tflearn.lstm(net, n_units=128, activation='relu', return_seq=True)
net = tflearn.lstm(net, n_units=128, activation='relu', return_seq=True)

net = tflearn.fully_connected(net, n_units=64, activation='relu')
net = tflearn.dropout(net, keep_prob=0.5)
net = tflearn.fully_connected(net, n_units=output_size, activation='softmax')
net = tflearn.regression(net, optimizer='adam', learning_rate=0.001, loss='categorical_crossentropy')

model = tflearn.DNN(net)
model.fit(X_train, y_train, validation_set=(X_val, y_val), batch_size=128, n_epoch=10)