zzpustc / cc-sam Goto Github PK

Can you provide code for open set evaluation? thanks.

I couldn't find any code about open set.

Dear Authors,

I greatly appreciate the outstanding research presented in your paper. If it is not too much trouble, I was wondering if you would be willing to share the code you used for experiments on the large-scale datasets (ImageNet, Inatrulist2018, Places)? Thanks!

Hi! Thanks for sharing your excellent work!

I notice there are different numbers between the main table in the body and the ablation study in the appendix under the same setting(is it?) e.g. CIFAR10-LT(beta: 100) 83.92 in Table 1 VS 82.42 in Table 2 in the Appendix. Did I miss something? Looking forward to your reply!

While running the code with the given command, I encountered the following issues:

1. ModuleNotFoundError: No module named 'datasets.autoaugment', This error occurs when the train_cifar.py file tries to import Cifar10Policy from datasets.autoaugment, however no such file exists.
2. ImportError: cannot import name 'grad_norm' from 'utils.pytorch'. Similarly here, utils/pytorch.py does not contain any function called grad_norm.

Thanks for sharing your code!

I guess your work would be insteresting and explore the important saddle-point issue in long recognition, as a further investigation beyond the prior work "Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data. NeurIPS 2022". I want to know when and where can I find your paper? I can'wait to read it.

Best wishes.