pytorch-gconv-experiments

pytorch-gconv-experiments copied to clipboard

nn.BatchNorm2d cannot process input with 4 dims.

6

When I test the file resnet.py, I encountered the problems. It seems the nn.BatchNorm2d cannot process 5 dims input. ``` def test(): net = ResNet101() y = net(Variable(torch.randn(1,3,32,32))) print(y.size()) ```...

xmengli

Change loss.data[0] to loss.item() to support more recent versions of pytorch

Abe404

Hello Adam, thanks for your pytorch implementation of Group-CNN. It helped me greatly for my research. I just had an issue while using your code to train a different dataset...

gustmd0121

Dear Adam, Thank you so much for your pytorch version of Group CNNs. with your codes, I just wonder that the features maps in a P4M are not equivariant when...

shuchao1212

Sir, I am trying to implement your work. Please help me out in installling groupy with pytorch support. I always end up with : error: No module named 'groupy.gconv' Thank...

NaveenPaluru