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

train pose estimation from strach #589

Open
Dantju opened this issue Jan 17, 2020 · 5 comments
Open

train pose estimation from strach #589

Dantju opened this issue Jan 17, 2020 · 5 comments

Comments

@Dantju
Copy link

Dantju commented Jan 17, 2020

@xingyizhou ,have u train PE from strach but not finetune on OD? I did this ,and get a better result,i want to know,why u train PE finetuned on OD?

@Dantju
Copy link
Author

Dantju commented Jan 17, 2020

train pose estimation from scratch, sorry get a spelling error

@xingyizhou
Copy link
Owner

Thanks for raising this up. I have tried and also observed better results. The new results will be updated in the next revision.

@Dantju
Copy link
Author

Dantju commented Jan 19, 2020

@xingyizhou I observed a better result on PE ,but PD get a lit worse,do u have some idear to improve PD?

@Dantju
Copy link
Author

Dantju commented Feb 24, 2020

@xingyizhou I find use multi_pose to train PD by setting PE's loss weight as 0,the result is worse than using ctdet to train PD ,do u have any idea?

@sisrfeng
Copy link

Hi, I train dla_34 and resdcn_18 on UA-DETRAC using ImageNet pretrained backbone but not loading coco-pretrained model.
The AP50 is always 0 for 50+ epoch.
Do you know how to solve it?
Thx!

@xingyizhou I find use multi_pose to train PD by setting PE's loss weight as 0,the result is worse than using ctdet to train PD ,do u have any idea?

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

3 participants