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

checkpoints for eval #19

Closed
Zhirui86 opened this issue Mar 1, 2025 · 3 comments
Closed

checkpoints for eval #19

Zhirui86 opened this issue Mar 1, 2025 · 3 comments

Comments

@Zhirui86
Copy link

Zhirui86 commented Mar 1, 2025

Thanks for your previous answer towards training UH-1 model.I'm trying to reproduce the metric you displayed in your paper based on code of T2M-GPT and your Humanoid-x dataset.However,it lacks a certain opt.txt for params configuration and checkpoints for evaluation during training which correspond to the training of T2M-GPT.Could you plz open these sources if it doesn't cause much inconvenience.Thanks in advance.

Image

Image

@Zhirui86
Copy link
Author

Zhirui86 commented Mar 3, 2025

BTW,will you open source all the human_pose for humanoid-x?In the dataset you provided human_pose.zip from three sources (charades,kinetics700,youtube) which is not corresponding to humanoid_keypoints.zip(more sources).

@sihengz02
Copy link
Owner

Hi! For the first issue, I will try to find time and provide the checkpoint download link within this week. Plz stay tuned! For more detail, we follow the evaluation details of this paper. If you want to train your own evaluator based on your own setting, you may need this code.

For the second issue, we can not directly opensource these data due to legal license issues. But we do provide download instructions on how to download these data on your own. Plz refer to our huggingface dataset page: https://huggingface.co/datasets/USC-GVL/Humanoid-X.

Image

@sihengz02
Copy link
Owner

Now you can download these checkpoints at here.

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