polyrnn-pp-pytorch
polyrnn-pp-pytorch copied to clipboard
Upgrading to Pytorch 1.3/Python3
Hi, I'm trying to update the code to use python 3 and pytorch 1.3.
When running inference, I'm getting a different output than python 2 and pytorch 0.4.
Do you know what needs to change? SkipResnet output matches when I set Upsample(align_corners=False) PolyGGNN has a different output
How about your performance with torch1.3?