CIFAR-100 SuperClasses division used in this repo is different from the standard one

[ASDen]

Hello,

The CIFAR100 super-class used here are quite different from the standard division described here This can be easily seen by comparing to other implementations that follow the standard division, e.g. here or here As you can see there is shifting between the fine-grained classes inside each super-class

I think this makes results presented here not comparable to other results on the literature and would need to be re-done

[sangwoomo]

Hi @ASDen,

Thank you for noticing that. I think there was some bug at converting coarse labels. We didn't notice since only some coarse labels suffer the issue, and the reproduced results seemed okay.

We will update the results as soon as possible.

[gdwang08]

A very nice work! I am wondering if you have updated the results using the standard division of CIFAR100 super-class.