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

Face Detector #135

Closed
yug125lk opened this issue Sep 9, 2024 · 1 comment
Closed

Face Detector #135

yug125lk opened this issue Sep 9, 2024 · 1 comment

Comments

@yug125lk
Copy link

yug125lk commented Sep 9, 2024

Thank you for this great work.
I'm just a bit confused—are the results with or without face detection?
When I trained MobileNet with the original dataset, it reached 97.98%. However, when I used the dataset with face detection preprocessing, it only reached 97.45%.

@leondgarse
Copy link
Owner

Sorry for the late reply.

  • For training process, the dataset is assumed already handled by face detection. Thus the result is without face detection.
  • So the 97.98% is printed during traing, and 97.45% is your own testing process result? As the result is rather close, maybe just some difference in image processing like Reproduce the results #110, or flip process?

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

2 participants