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

The conversion effect between images is good during training, but it is much worse when predicting with the trained weights #1690

Open
Ivennnnnnn opened this issue Feb 25, 2025 · 0 comments
Open

The conversion effect between images is good during training, but it is much worse when predicting with the trained weights #1690

Ivennnnnnn opened this issue Feb 25, 2025 · 0 comments

Comments

@Ivennnnnnn
Copy link

Why are the images generated during training (in the index) converted well, but when the trained weights are used for inference, the conversion effect of these images is worse than that of the images converted during training? I can't figure it out.
@Ivennnnnnn Ivennnnnnn changed the title The conversion effect between images is good during training, but it is much worse when using the trained weights for reasoning The conversion effect between images is good during training, but it is much worse when predicting with the trained weights Feb 25, 2025
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
@Ivennnnnnn