How to input mask value to Convolution1D layer

Question

I need to feed variable length sequences into my model.

My model is Embedding + LSTM + Conv1d + Maxpooling + softmax.

When I set mask_zero =

Answer 1

Conv1D layer does not support masking at this time. Here is an open issue on the keras repo.

Depending on the task you might be able to get away with embedding the mask_value just like the other values in the sequence and apply global pooling (as you're doing now).