yhhhli/BRECQ

Cannot reproduce the accuracy

Closed this issue · 2 comments

Greetings,

Really appreciate your open source contribution.

However, it seems the accuracy mentioned in the paper cannot be reproduced applying the standard Imagenet. For instance, with the full precision model, I have tested Resnet 18 (70.186%), MobileNetv2(71.618%), which is slightly lower than the results from your paper (71.08, 72.49 respectively).

Have you utilized any preprocessing techniques other than imagenet.build_imagenet_data?

Thanks

Hi, can you validate now?

It seems there is a typo in my build_imagenet_data. Now I change the Resize((256, 256)) to Reszie(256)

Hi, can you validate now?

It seems there is a typo in my build_imagenet_data. Now I change the Resize((256, 256)) to Reszie(256)

This would work, thanks a lot!