8000 Train with insightface aligned data? · Issue #16 · somanchiu/ReSwapper · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Train with insightface aligned data? #16

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
Mr-Nobody-dey opened this issue Jan 24, 2025 · 0 comments
Open

Train with insightface aligned data? #16

Mr-Nobody-dey opened this issue Jan 24, 2025 · 0 comments

Comments

@Mr-Nobody-dey
Copy link
Mr-Nobody-dey commented Jan 24, 2025 •
edited
Loading

If its not too much, can you train with the data aligned using insightface code? the area of face/total area of a 128x128 image is much larger compared to that of ffhq data.
My hypothesis is that, with that data, the model should produce better result.
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
@Mr-Nobody-dey
0