sent-conv-torch icon indicating copy to clipboard operation
sent-conv-torch copied to clipboard

How to deal with padding (0 vector) without maskZero in ConvolutionLayer?

Open allanj opened this issue 7 years ago • 0 comments

I find there is no maskZero for the temporalConvolutionLayer. In this case, if we meet a window of all embeddings are paddings, which means 0 vectors., I think the convolution layer will always give us the bias.

But wouldn't the output be 0? Or we don't need maskZero in Convolution Layer?

allanj avatar Oct 25 '17 17:10 allanj