Hakkai

Results 7 issues of Hakkai

Hi! Thanks for providing such an awesome codebase. I wonder whether it is in the schedule that the augmentation introduced in the paper "AutoAugment: Learning Augmentation Policies from Data" will...

enhancement
external contribution welcome

It is possible that the 30-nearest neighbors share same labels (only 1 prediction). Therefore, it is impossible to calculate the top-5 acc. Please re-evaluate the scripts. Thank you.

It is possible that the 30-nearest neighbors share same labels (only 1 prediction). Therefore, it is impossible to calculate the top-5 acc. Please re-evaluate the scripts. Thank you.

In the `GANModule`, grad information is explicitly saved and added again, which may require more memory cost. Is it possible to use `grad_req='add'` instead?

Hi! Thanks for providing such a wonderful work. I wonder have you tried a ResNet backbone without ImageNet pretraining? Is it possible that a pre-trained model might become one of...

I fail to figure out a reasonable explanation. Could anyone help me out?