lucidrains/g-mlp-pytorch

Potentially missing the high way pass

Vincent-Li-9701 opened this issue · 1 comments

Hello,

Maybe I missed it, but would you mind pointing out where the high way pass of the gMLP block is in the code? Based on the paper, there is a high way path (addition) between the input and the output. I couldn't find it in the gMLPBlock code.

Thank you