Closed qiqiApink closed 1 year ago
rcxyz loss, and all other geo losses, are supported only for the action2motion dataset. For the text2motion dataset, the geometric data is regulated using the data representation instead of explicit losses.
More info here: https://github.com/GuyTevet/motion-diffusion-model/issues/19
So the "pose_rep" which is fixed to "rot6d" https://github.com/GuyTevet/motion-diffusion-model/blob/3294a7fb6a74054074c1f948d271f0641765f4ae/utils/model_util.py#L45 is useless to text2motion setting?
Yup, in this context we only care about data_rep
, and data_rep
is hardcoded for each dataset, you can not change it.
I set the weight lambda_rcxyz>0 to add the reconstruction loss of xyz positions when I run the trainning code of HumanML3D. But I got the following error:
Can you help me?