8000 Issue in Choosing the Best Model · Issue #31 · VITA-Group/Self-PU · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Issue in Choosing the Best Model #31

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
Open
naji-s opened this issue Mar 5, 2025 · 0 comments
Open

Issue in Choosing the Best Model #31

naji-s opened this issue Mar 5, 2025 · 0 comments

Comments

@naji-s
Copy link
naji-s commented Mar 5, 2025 •
edited
Loading

Hi,

I have a fundamental confusion about your code. Based on your accuracy function definition, it seems like you choose the best model based on access to the true labels of the data (by choosing the model that has the lowest true error which should be unavailable while training)

Self-PU/train_2s2t_mix.py

Line 270 in a0e332a

'state_dict': models[all_accuracy.index(max(all_accuracy))].state_dict(),

Am I misunderstanding something? T is the true label, and Y is the noisy one in your code, right?

Thank you in advance.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@naji-s
0