hongsukchoi/TCMR_RELEASE

error

liuhaorandezhanghao opened this issue · 4 comments

liuhaorandezhanghao commented

Running TCMR on each person tracklet...
0%| | 0/1 [00:01<?, ?it/s]
Traceback (most recent call last):
File "demo_gzh.py", line 383, in
main(args)
File "demo_gzh.py", line 188, in main
output = model(batch)[0][-1]
File "/home/vtuber/venv/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/vtuber/project/TCMR_RELEASE-master/lib/models/tcmr.py", line 146, in forward
smpl_output = self.regressor(feature, is_train=is_train, J_regressor=J_regressor)
File "/home/vtuber/venv/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/vtuber/project/TCMR_RELEASE-master/lib/models/spin.py", line 269, in forward
pose2rot=False,
File "/home/vtuber/venv/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/vtuber/project/TCMR_RELEASE-master/lib/models/smpl.py", line 83, in forward
full_pose=smpl_output.full_pose)
TypeError: init() got an unexpected keyword argument 'body_pose'

hongsukchoi commented

Hi, it seems you are running your modified codes.
Would you provide your full codes?

Mirandl commented

Hi, I got a similar error but there's a little different

Running TCMR on each person tracklet...
0%| | 0/5 [00:04<?, ?it/s]
Traceback (most recent call last):
File "/root/data/TCMR/demo.py", line 375, in
main(args)
File "/root/data/TCMR/demo.py", line 186, in main
output = model(batch)[0][-1]
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/root/data/TCMR/lib/models/tcmr.py", line 146, in forward
smpl_output = self.regressor(feature, is_train=is_train, J_regressor=J_regressor)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/root/data/TCMR/lib/models/spin.py", line 269, in forward
pose2rot=False,
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/root/data/TCMR/lib/models/smpl.py", line 74, in forward
smpl_output = super(SMPL, self).forward(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/smplx/body_models.py", line 376, in forward
self.lbs_weights, pose2rot=pose2rot, dtype=self.dtype)
File "/usr/local/lib/python3.6/dist-packages/smplx/lbs.py", line 205, in lbs
J_transformed, A = batch_rigid_transform(rot_mats, J, parents, dtype=dtype)
File "/usr/local/lib/python3.6/dist-packages/smplx/lbs.py", line 347, in batch_rigid_transform
rel_joints.view(-1, 3, 1)).view(-1, joints.shape[1], 4, 4)
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.

Process finished with exit code 1

could you help me figure out what's wrong with it? (btw I didn't change your code)

liuhaorandezhanghao commented
hongsukchoi commented

You can change the library code with sudo privilege, if the library code is the problem