how to solve the error when run render_mesh

[Xueting-Bi]

File "/home/bixueting/anaconda3/envs/mdm/lib/python3.7/site-packages/torch/optim/optimizer.py", line 89, in wrapper
return func(*args, **kwargs)
File "/home/bixueting/anaconda3/envs/mdm/lib/python3.7/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/home/bixueting/anaconda3/envs/mdm/lib/python3.7/site-packages/torch/optim/lbfgs.py", line 311, in step
orig_loss = closure()
File "/home/bixueting/anaconda3/envs/mdm/lib/python3.7/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/home/bixueting/code/motion-diffusion-model/visualize/joints2smpl/src/smplify.py", line 233, in closure
search_tree=search_tree, pen_distance=pen_distance, filter_faces=filter_faces)
File "/home/bixueting/code/motion-diffusion-model/visualize/joints2smpl/src/customloss.py", line 157, in body_fitting_loss_3d
angle_prior_loss = (angle_prior_weight ** 2) * angle_prior(body_pose).sum(dim=-1)
File "/home/bixueting/code/motion-diffusion-model/visualize/joints2smpl/src/customloss.py", line 22, in angle_prior
pose[:, [55 - 3, 58 - 3, 12 - 3, 15 - 3]] * torch.tensor([1., -1., -1, -1.], device=pose.device)) ** 2
RuntimeError: CUDA error: device-side assert triggered
(mdm) ➜ motion-diffusion-model git:(main) ✗

[GuyTevet]

Hi @Xueting-Bi , do you run the code as is? How can we reproduce this fail?