LSTM 模型中未定义 Dropout_U 和 Dropout_W

Question

我正面临这个错误

NameError: name 'Dropout_U' is not defined

通过创建 LSTM 模型

embed_dim = 128
lstm_out = 200
batch_size = 32

model = Sequential()
model.add(Embedding(2500, embed_dim,input_length = X.shape[1]))
model.add(Dropout(0.2))
model.add(LSTM(lstm_out))
model.add(Dropout_U(0.2))
model.add(Dropout_W(0.2))
model.add(Dense(2,activation='sigmoid'))
model.compile(loss = 'categorical_crossentropy', optimizer='adam',metrics = ['accuracy'])
print(model.summary())

你能帮我克服这个问题吗？

Answer 1

使用的语法已经过时， Dropout_U已更改为recurrent_dropout 。 Dropout_W就是Dropout 。

如果您要更换Dropout_U与recurrent_dropout ，使你LSTM层的一部分它应该工作。 只需将Dropout_W层更改为Dropout 。

embed_dim = 128
lstm_out = 200
batch_size = 32

model = Sequential()
model.add(Embedding(2500, embed_dim,input_length = X.shape[1]))
model.add(Dropout(0.2))
model.add(LSTM(lstm_out, recurrent_dropout=0.2))
model.add(Dropout(0.2))
model.add(Dense(2,activation='sigmoid'))
model.compile(loss = 'categorical_crossentropy', optimizer='adam',metrics = ['accuracy'])
print(model.summary())