tensorflow-wavenet icon indicating copy to clipboard operation
tensorflow-wavenet copied to clipboard

Published 20 hours ago • verified publisher icon ibab

Why did we slice the output at every dilation layer?

Open ghost opened this issue 6 years ago • 0 comments

https://github.com/ibab/tensorflow-wavenet/blob/3c973c038c8c2c20fef0039f111cb04139ff594b/wavenet/model.py#L309

I would like to know why do we have this slice operation over the skip connection!!!

Any help is much appreciated!!

ghost avatar Aug 30 '18 20:08 ghost