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.

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

negative value for the adv loss #1

Open
KyominHwang opened this issue Dec 12, 2022 · 0 comments
Open

negative value for the adv loss #1

KyominHwang opened this issue Dec 12, 2022 · 0 comments

Comments

@KyominHwang
Copy link

KyominHwang commented Dec 12, 2022 •
edited
Loading

Hi.
First of all, thank you for the nice work to solve the domain shift problem in automatic colorization.
It inspired me a lot that the idea of domain generalization can be applicable to another field.

While I train and test your model on my local PC, I got negative value for the adv loss.
Is this OK for having negative value while training the model?
@KyominHwang KyominHwang changed the title negative loss occurs at adv loss & how to select the final model for the test negative adv loss value & how to select the final model for the test Dec 12, 2022
@KyominHwang KyominHwang changed the title negative adv loss value & how to select the final model for the test negative value for the adv loss& how to select the final model for the test Dec 12, 2022
@KyominHwang KyominHwang changed the title negative value for the adv loss& how to select the final model for the test negative value for the adv loss Dec 13, 2022
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
@KyominHwang