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?
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?