New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

performance mismatch with paper on imb_factor=0.05. #2

Open

youjiangxu opened this issue Sep 23, 2020 · 0 comments

youjiangxu commented Sep 23, 2020 •

edited

Loading

hello,

I run the code 3 times with imb_factor=0.05. The results are "53.52 | 53.31 | 52.94", which do not match the reported number: 54.37.

The command I run is:

python meta-weight-net-class-imbalance.py --dataset cifar100 --num_classes 100 --imb_factor 0.05
Is there something wrong with my experiments?

The text was updated successfully, but these errors were encountered:

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment