Keras LSTM neural net: TypeError: LSTM() missing 1 required positional argument: 'Y'

Question

I'm trying to train a LSTM neural net using Keras (version 2.2.0) and TensorFlow (version 1.1.0). I know that there are more recent TensorFlow versions but unfortunately I'm having some issues installing them. However, I don't believe that my problem is related to the TensorFlow version.

This is how my Keras code looks like:

[...] from keras.layers import Dense, Dropout, LeakyReLU, LSTM, Activation, Dense, Dropout, Input, Embedding

def LSTM(X,Y):
    inputDimension = len(X[0])
    inputSize = len(X)
    
    # create the model
    model = Sequential()
    model.add(Embedding(input_length=inputDimension,input_dim=inputDimension,output_dim=256))
    model.add(LSTM(100))
    model.add(Dropout(0.2))
    model.add(Dense(1, activation='sigmoid'))
    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
    model.fit(X,Y,epochs=3,batch_size=64)
    return model

Whenever I try to run it, I end up with the following error message:

Traceback (most recent call last):

File "Main.py", line 208, in lstmModel = ann.LSTM(scaledTrainingX,trainingY)
File "ann.py", line 158, in LSTM model.add(LSTM(100))
TypeError: LSTM() missing 1 required positional argument: 'Y'

I found this question on StackOverflow but the solution suggested there doesn't help because I'm not using a generator to train my network.

Any help to get this network to run would be highly appreciated. Thank you very much.

Answer 1

The function LSTM(X,Y) in which you create your model is shadowing the Keras LSTM layer. So when you call:

model.add(LSTM(100))

you're indeed calling the function that you defined. You need to rename this function to something else.