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

I trained myself, but I can't achieve the effect of the paper #19

Open
empty2enrich opened this issue May 17, 2022 · 7 comments
Open

I trained myself, but I can't achieve the effect of the paper #19

empty2enrich opened this issue May 17, 2022 · 7 comments

Comments

@empty2enrich
Copy link

Are there any tricks here?

My result:

MAE: 5.0
Pitch: 5.8
Yaw: 4.9
Roll: 4.4

@empty2enrich
Copy link
Author

trained on the 300W-LP dataset., test on the ALFW2000

@thohemp
Copy link
Owner

thohemp commented May 17, 2022

A MAE of 5.0 seems to be a long way off. Check your data, its pre processing and the training configuration.
Rel: #14

@empty2enrich
Copy link
Author

I don't understand very well, I used the source code for training without modification. Why do I need to check the data?

thank you for your reply!

@thohemp
Copy link
Owner

thohemp commented May 29, 2022

I updated the default training settings. This should help you to achieve the reported results more easily (or in my trainings even surpass them). Let me know if you still struggle after using them.

@PINTO0309
Copy link
Contributor

PINTO0309 commented Jul 3, 2022

I used the adjusted training settings, added an image of the masked face and re-trained it and got about the same accuracy as in the paper. Thank you.

I also merged 6DRepNet and WHENet to generate a new model that allows 360° estimation. 👍
https://github.com/PINTO0309/DMHead

Yaw: 3.3193, Pitch: 4.9063, Roll: 3.3687, MAE: 3.8648

@lucasjinreal
Copy link

@PINTO0309 how did u trained light 6d repnet model? Currently it's slow and big

@PINTO0309
Copy link
Contributor

https://github.com/PINTO0309/DMHead/releases

I have not published the .pth files because I spent quite a bit of money on NVIDIA A100 for personal hobby. ONNX is publicly available, so feel free to use it.

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