Skip to content
This repository has been archived by the owner on Jun 13, 2024. It is now read-only.

Why the scores is higher than that in the paper when I used your code and model? #159

Open
touhou-ayaya opened this issue Feb 19, 2021 · 3 comments
Open

Why the scores is higher than that in the paper when I used your code and model? #159

touhou-ayaya opened this issue Feb 19, 2021 · 3 comments

Comments

@touhou-ayaya
Copy link

Why the scores is higher than that in the paper when I used your code and model? And how do I test the model on COCO test-dev dataset? (Sorry for my terrible English)
@Whj-cv
Copy link

Whj-cv commented Oct 4, 2021

你有自己在mpii上训练过吗，我训练过的结果低于所给出的结果

@touhou-ayaya
Copy link
Author

你有自己在mpii上训练过吗，我训练过的结果低于所给出的结果

没有，只在COCO上测试过

@yuan243212790
Copy link

关flip test

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@yuan243212790 @touhou-ayaya @Whj-cv