Skip to content
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.

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

Need For Kind Help in Paper's Replication #46

Open
Christophe-Jia opened this issue Sep 23, 2022 · 3 comments
Open

Need For Kind Help in Paper's Replication #46

Christophe-Jia opened this issue Sep 23, 2022 · 3 comments

Comments

@Christophe-Jia
Copy link

Hi li,
I got a poor performance in both cifar-10/100 when the noise ratio is high than 80%, which mainly indicating 80% 90% in Table 1. All goes well with the hyperparameters in low noise condition. Could you kindly give me some suggestions for this problem I encountered ?
More precisely, my results as follows:
c10 0.8 best:75.7 last:73.5
c10 0.9 best:44.0 last:41.2
c100 0.8 best:52.7 last:50.9
c100 0.9 best:22.6 last:21.4

@Christophe-Jia
Copy link
Author

With respect to the setting metioned in AppendixB Table 7,but still..../

@jiawyGithub
Copy link

The hyperparameters is important.
my results as follows:
c10 0.9 best:78.14 last:77.39
τ is set as 0.6. λu is set as 50.

@Christophe-Jia
Copy link
Author

Thanks a lot for provideing hyperparameters setting!
ANY recommended setting for 0.8 ?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants