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

confused with the code and ability of the weight_learner fuction in reweighting.py #16

Open

pending1face opened this issue Jan 20, 2024 · 1 comment

pending1face commented Jan 20, 2024

I print the softmax_weight like below:

and the result is here

Does this mean that it did not have the ability to reweight the loss of each sample？

Also，I print the loss in weight calculating process like below:

The results show that this part does not seem to learn well:

universe27king commented May 14, 2024

I also found that the weights of each samples appear almost identical, do you know why is this now? thank you.

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