When I try to train the model on amass data, the following error occurs: an error is reported on line 323 of the /HOVER/third_party/human2humanoid/phc/phc/utils/motion_lib_h1.py file. After testing, it was found that some self.dvs = torch.cat([m.dof_vels for m in motions], dim=0).float().to(self._device) have fewer dimensions, for example, most m.dof_vels have a shape of [x, 19], but some m.dof_vels have a shape of [19]. Why does this error occur and how can it be avoided?
File "/home/lenovo/Code/HOVER/third_party/human2humanoid/phc/phc/utils/motion_lib_h1.py", line 327, in load_motions self.dvs = torch.cat([m.dof_vels for m in motions], dim=0).float().to(self._device) RuntimeError: Tensors must have same number of dimensions: got 1 and 2
When I try to train the model on amass data, the following error occurs: an error is reported on line 323 of the
/HOVER/third_party/human2humanoid/phc/phc/utils/motion_lib_h1.pyfile. After testing, it was found that someself.dvs = torch.cat([m.dof_vels for m in motions], dim=0).float().to(self._device)have fewer dimensions, for example, mostm.dof_velshave a shape of [x, 19], but somem.dof_velshave a shape of [19]. Why does this error occur and how can it be avoided?File "/home/lenovo/Code/HOVER/third_party/human2humanoid/phc/phc/utils/motion_lib_h1.py", line 327, in load_motions self.dvs = torch.cat([m.dof_vels for m in motions], dim=0).float().to(self._device) RuntimeError: Tensors must have same number of dimensions: got 1 and 2