Non-causal dilated convolution?

Open Artix18 opened this issue 7 years ago • 1 comments

Hello,

I think your dilated convolution class, as implemented, is not causal because of the 0 padding.

The last comment here proposes a solution that might work better: https://github.com/pytorch/pytorch/issues/1333

May 16 '18 19:05 Artix18

@Artix18 Hi. Thank you for your suggestion. And if you can make a patch, I'll be great. ☺️

May 18 '18 06:05 golbin