jiequancui / reslt Goto Github PK

Thanks for proposing such interesting method. I am wondering three branches have diffierent classifiers or same?
Furthermore, do you compare with mulit-experts methods as [1]?
[1] LONG-TAILED RECOGNITION BY ROUTING DIVERSE DISTRIBUTION-AWARE EXPERTS, 2021 ICLR.

When can the source code be displayed?

Thanks for your great work.

I'm confused about the site of the 1x1conv Block. Could you explain why the 1x1conv block before the avgpool during training and behind the avgpool during testing?

Sorry to bother you that

Code is incomplete, train_sampler is not defined in ImageNetTrain， And Can you explain root_path，dataset，data_path to me

Looking forward to your reply

Greetings
Really nice work, but I have a small question.
You mentioned in the code comments that # 1x1 conv can be replaced with more light-weight bn layer, I wonder why they are equivalent? Actually I think conv and bn are totally different.

Thanks for your great work.

I'm confused about the gamma hyperparameter. Could you explain the function of gamma for me? Why do you just set it on the ImageNet-lt and iNaturalist datasets, not Cifar?

Thanks for the open source, but how to use mixup in reslt confuses me.

Hello, I want to study your related papers. When can the relevant code be uploaded?

Am I correct ?