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

Results for R18-Rd100? #6

Open
TzxzT opened this issue Jan 10, 2021 · 0 comments
Open

Results for R18-Rd100? #6

TzxzT opened this issue Jan 10, 2021 · 0 comments

Comments

@TzxzT
Copy link

TzxzT commented Jan 10, 2021

Hello:
Thanks for your open-source implementation! I run your code without modification and find the results on 14 classes are same,except on the class "transistor" (R18-Rd100):
image ROCAUC: 0.887
pixel ROCAUC: 0.959
vs : (yours)
image ROCAUC: 0.925
pixel ROCAUC: 0.968
I'm confused because i don't find randomness and all other classes's results are same. Do you have any idea about this?
btw, the per-pixel level ROCAUC seems to be calculated on all images once. How about evalute on single picture and average the AUC? Which is more reasonable?

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

1 participant