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 encountered some tricky problems #22

Closed
psw13583112 opened this issue Sep 8, 2021 · 4 comments
Closed

I encountered some tricky problems #22

psw13583112 opened this issue Sep 8, 2021 · 4 comments

Comments

@psw13583112
Copy link

Can this model run a single picture? When I ran a picture, there was some misalignment. The model used was MLP trained by PoseAug, and I found that the result was not very satisfactory.
20210908-104340
20210908-170632
20210908-170643

@Garfield-kh
Copy link
Collaborator

Hi, thank you for the interest!
I think the problem might be 2D pose normalization. The 2D pose here has absolute value > 1 (head, feet), which is not usual in training data.
Can you try scale down the 2D pose by 0.5?

@psw13583112
Copy link
Author

@Garfield-kh Thanks a lot for your prompt reply, I tried to reduce it by 0.5 times, the effect is indeed much better, but the results obtained by predicting the same picture every time are not the same.

@Garfield-kh
Copy link
Collaborator

Did you fix the random seed and also model.eval() for the dropout layer?

@psw13583112
Copy link
Author

@Garfield-kh Thank you, I will pay attention to these details

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