在tflearn中添加多个LSTM图层

如何为以下神经网络添加另一个LSTM图层？在tflearn中添加多个LSTM图层

net = tflearn.input_data([None, width, height]) 
net = tflearn.lstm(net, 128) 
net = tflearn.fully_connected(net, classes, activation='softmax') 
net = tflearn.regression(net, optimizer='adam', learning_rate=learning_rate, loss='categorical_crossentropy') 
model = tflearn.DNN(net, tensorboard_verbose=3,tensorboard_dir='log')

来源

2017-07-23 CSdesign css

加上'净= tflearn.lstm（净值，128）之间的' lstm和完全连接的图层 –

net = tflearn.lstm(net, 128, return_seq=True) 
net = tflearn.lstm(net, 256)

不要忘记设置return_seq=True以前的LSTM层上，或者你会得到一个错误

来源

2017-07-28 00:07:30 RiffShark

在tflearn中添加多个LSTM图层

回答

相关问题