WideResNet-pytorch

WideResNet-pytorch copied to clipboard

AvgPool2d different from the original

3

@xternalz I think your avgpool https://github.com/xternalz/WideResNet-pytorch/blob/master/wideresnet.py#L81 and the original avgpool https://github.com/szagoruyko/wide-residual-networks/blob/master/pytorch/resnet.py#L56 use different strides (yours=kernelsize=8, original=1).

sungyoon-lee

In your code, you add dropout after [relu2](https://github.com/xternalz/WideResNet-pytorch/blob/master/wideresnet.py#L28), your process is like `dropout(relu2(bn2(conv1(relu1(bn1(x))))))`. But it this code, he adds dropout after [conv1](https://github.com/meliketoy/wide-resnet.pytorch/blob/master/networks/wide_resnet.py#L27), his process is like `relu2(bn2(dropout(conv1(relu1(bn1(x))))))`. Does it matter?...

gauss-clb