Dropout_U and Dropout_W is not defined in LSTM model

Question

I am facing this error

NameError: name 'Dropout_U' is not defined

by creating an LSTM model

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())

Can you help me overcome this problem?

Answer 1

The syntax used is outdated, Dropout_U has been changed to recurrent_dropout . Dropout_W is simply Dropout .

If you replace Dropout_U with recurrent_dropout and make it part of your LSTM layer it should work. Simply change the Dropout_W layer to 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())