ChenFengYe / motion-latent-diffusion

[CVPR 2023] Executing your Commands via Motion Diffusion in Latent Space, a fast and high-quality motion diffusion model
https://chenxin.tech/mld/
MIT License
584 stars 53 forks source link

Can you provide instructions for other datasets such as UESTC and HumanAct12? #39

Open Xuguowei-hub opened 1 year ago

Xuguowei-hub commented 1 year ago

Thank you very much for open-sourcing the code. Here, I would like to inquire if it would be possible to provide more information about the Action to Motion task, such as training and evaluation on datasets like UESTC and HumanAct12. If feasible, it would be greatly appreciated if the missing pre-trained models could also be shared. Thank you very much!

ChenFengYe commented 1 year ago

Hi, thanks for your attention! You can download the pred-trained model of HumanAct12., and please refer to the config below for action-to-motion training. https://github.com/ChenFengYe/motion-latent-diffusion/blob/c28a06435077800fde4d76ef93eb2a4016a5120c/README.md?plain=1#L20 We will provide more information soon.

Xuguowei-hub commented 1 year ago

Thank you very much for your reply. Your reply has been of great help to me. However, I don't seem to have seen the pre-trained model on the UESTC dataset. Can you provide this pre-trained model and its corresponding config file?