[Python] Total params: 0 , on doing model.summary() keras

Discussão em 'Python' iniciado por Stack, Dezembro 19, 2024.

  1. Stack

    Stack Membro Participativo

    model = Sequential()
    model.add(Embedding(283, 100, input_length=56))
    model.add(LSTM(150))
    model.add(LSTM(150))
    model.add(Dense(283, activation='softmax'))

    model.compile(loss='categorical_crossentropy', optimizer='adam',metrics=['accuracy'])

    model.summary()


    Tensorflow Version: 2.16.1,
    Keras Version: 3.3.3 ,
    Device - M3 pro macbook

    I tried to build a LSTM model for text generation using a dummy dataset (had 282 unique words, checked with tokenizer), expected non zero params but the output is 0 params for each layer.

    Continue reading...

Compartilhe esta Página