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

the best result #6

Open
yuyyuu opened this issue Apr 21, 2022 · 3 comments
Open

the best result #6

yuyyuu opened this issue Apr 21, 2022 · 3 comments

Comments

@yuyyuu
Copy link

yuyyuu commented Apr 21, 2022

Hello,
Thank for your great work. I have a question. When I replicated the work, I got a better result than 3.92 on MPIIFaceGaze. However, when I tested your pre-training results, I got a 4.17. I want to konw is 3.92 the best result ?Are all the results performed on 448 *448 pictures?

@AimersS
Copy link

AimersS commented May 3, 2022

Hello, Thank for your great work. I have a question. When I replicated the work, I got a better result than 3.92 on MPIIFaceGaze. However, when I tested your pre-training results, I got a 4.17. I want to konw is 3.92 the best result ?Are all the results performed on 448 *448 pictures?

Hello,When I trained his model, there were many bugs, and based on some values that were not defined, after modification, I got the wrong Mae: 0.041. How do you reproduce it? Can you analyze your code with me? My email: a847990008@icloud.com Thank you very much.

@AndrewDing616
Copy link

Hello, when I replicated the work as the parameters the writer provided, I got 4.9°, where the error is big. I don't know why. So, could I have a communication with you?
My email: 726804161@shu.edu.cn
Tks!

@godkaieethu
Copy link

same question, bro. i get much smaller error on MpiiGaze

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

4 participants