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

Question about the shape of poses. #13

Open
Talegqz opened this issue Mar 11, 2022 · 2 comments
Open

Question about the shape of poses. #13

Talegqz opened this issue Mar 11, 2022 · 2 comments

Comments

@Talegqz
Copy link

Talegqz commented Mar 11, 2022

I find the the length of out_poses_trimodal and out_poses is not equal to clip_poses_resampled, so I can not do comparision.
Could you please tell me how to fix it?

@Talegqz
Copy link
Author

Talegqz commented Mar 12, 2022

And the length of out_poses is still not equal to the length of audio.

@UttaranB127
Copy link
Owner

The pose length and audio length are very different because of the different sampling rates. But if you render them out in a video, they should look appropriate. Also, the resampled poses are resampled at a certain frame rate and are not supposed to match the out poses. You might want to compare with the target poses.

Note: you might notice that the out poses length is often longer than the target poses length. This is because for the last clip subdivision, out poses are predicted for the entire clip length (34 frames) while the target poses often end before the entire clip length. For comparison, you can therefore take the first N frames of the out poses, where N is the number of frames in the target poses.

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