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

always getting video is fake:true and frame score =1 for all videos. #1

Open
KjAeRsTuIsK opened this issue May 5, 2023 · 1 comment

Comments

@KjAeRsTuIsK
Copy link

KjAeRsTuIsK commented May 5, 2023

Hi! you guys have done some great work. While trying to take inference on deepfake videos I have created along with the original videos, the demo model always predicts all videos as fake and gives frame wise score almost always 1.
Are the demo weights provided trained significantly or should I train it on my own ?
Is it possible for you guys to provide pre-trained weights to take inference?

@kkakkkka
Copy link

kkakkkka commented May 6, 2023

I used the weights provided by the author and encountered the same problem. Obviously, this method has a high false positive rate.

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