gMLP
Opened this issue · 1 comments
Miraclerice commented
Why does the gMLP model put v+1, what does it do here?
Registration-CorrMLP/CorrMLP/networks.py
Line 419 in da5ce37
MungoMeng commented
We followed the gMLP implementation used in MAXIM:
https://github.com/vztu/maxim-pytorch/blob/main/maxim_pytorch/maxim_torch.py#L125
I think this might provide a residual connection on u, which might make the training more stable.