bearpaw / pytorch-classification

Classification with PyTorch.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

PreResNet-110 on Cifar100, Top1 error rate is 26.47 rather than 23.65.

WeixiangXu opened this issue · comments

commented

I trained PreResNet-110 on Cifar100 as training recipes. And I get top1 error rate: 26.47%.

Same here, cannot reach 23.65. But I can only get 28. Could you give me some hints about the dropped accuracy?

Same here, I get top1 error rate ~ 28%

@BeierZhu Now I can confirm it should be 28%.
Please see this issue #36 (comment).

The reason is that some people use the easier version which is indeed PreResNet 164 with Bottleneck (higher accuracy) while the current version is PreResNet110 with BasicBlock.