Kai Zhong

Hi，thank you for your code firstly but I'm confused why you using ShortcutB(1*1 conv) when the size of feature map is halved. Because as far as I know, ShortcutA(insert 0)...

How about ShotcutA ？

1

Hi，thank you for your code firstly but I'm confused why you using ShortcutB(1*1 conv) when the size of feature map is halved. Because as far as I know, ShortcutA(insert 0)...

min/max calculatation and quantize of BN layer

1

I'm curious about why you use chunk during the calculation of min and max, why not just calculate? And can't we quantize weights and bias of BN?

Thank you for your code firstly. I just changed the finish function to print last status of bar into stdout at the end of the progress instead of stderr, which...

Thank you for your code firstly. I have tried to train resnet-20 on cifar10 dataset with pytorch and I used ShortcutA as you did. But I can't get as good...