weiaicunzai / pytorch-cifar100

Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet, NasNet, Residual Attention Network, SENet, WideResNet)

shouldn't group in_channels inside 1x1 conv

wuyuanhang94 opened this issue 3 years ago · comments

wuyuanhang94 commented 3 years ago

nn.Conv2d(in_channels, C * D, kernel_size=1, groups=C, bias=False), doesn't make sense.

yukiTemp commented 3 years ago

yeah, I was confused by this too, it's inconsistent to the paper.

Quantum_Rich commented 3 years ago

Has this issue been confirmed or fixed?