Thanks for your great work! But i meet a problem.
Processing: ./data/images/05_img.jpg
/media/perfectworld/C4F286ACF286A272/project/smplify-x/smplifyx/optimizers/lbfgsls.py:238: UserWarning: This overload of add is deprecated:
add(Number alpha, Tensor other)
Consider using one of the following signatures instead:
add(Tensor other, , Number alpha) (Triggered internally at /pytorch/torch/csrc/utils/python_argparser.cpp:1005.)
p.data.add(step_size, update[offset:offset + numel].view_as(p.data))
Camera initialization done after 0.9836
Camera initialization final loss 2933.3396
Stage 000 done after 0.6935 seconds
Stage 001 done after 0.8133 seconds
Stage 002 done after 0.9066 seconds
Stage: 60%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████ | 3/5 [00:02<00:01, 1.23it/s]
Orientation: 0%| | 0/1 [00:02<?, ?it/s]
Traceback (most recent call last):
File "smplifyx/main.py", line 272, in
main(args)
File "smplifyx/main.py", line 262, in main
args)
File "/media/perfectworld/C4F286ACF286A272/project/smplify-x/smplifyx/fit_single_frame.py", line 444, in fit_single_frame
use_vposer=use_vposer)
File "/media/perfectworld/C4F286ACF286A272/project/smplify-x/smplifyx/fitting.py", line 175, in run_fitting
loss = optimizer.step(closure)
File "/home/perfectworld/anaconda3/envs/smplify-x/lib/python3.7/site-packages/torch/optim/optimizer.py", line 89, in wrapper
return func(args, kwargs)
File "/media/perfectworld/C4F286ACF286A272/project/smplify-x/smplifyx/optimizers/lbfgs_ls.py", line 280, in step
orig_loss = closure()
File "/media/perfectworld/C4F286ACF286A272/project/smplify-x/smplifyx/fitting.py", line 249, in fitting_func
kwargs)
File "/home/perfectworld/anaconda3/envs/smplify-x/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, kwargs)
File "/media/perfectworld/C4F286ACF286A272/project/smplify-x/smplifyx/fitting.py", line 430, in forward
collision_idxs = self.search_tree(triangles)
File "/home/perfectworld/anaconda3/envs/smplify-x/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, *kwargs)
File "/home/perfectworld/anaconda3/envs/smplify-x/lib/python3.7/site-packages/mesh_intersection-0.1.0-py3.7-linux-x86_64.egg/mesh_intersection/bvh_search_tree.py", line 56, in forward
return BVHFunction.apply(triangles)
File "/home/perfectworld/anaconda3/envs/smplify-x/lib/python3.7/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(args, kwargs)
File "/home/perfectworld/anaconda3/envs/smplify-x/lib/python3.7/site-packages/mesh_intersection-0.1.0-py3.7-linux-x86_64.egg/mesh_intersection/bvh_search_tree.py", line 39, in forward
max_collisions=BVHFunction.max_collisions)
RuntimeError: after reduction step 1: cudaErrorInvalidDevice: invalid device ordinal
It seems that the cuda version is mismatch with the program, but RTX3090 only supports CUDA11.x. How can i solve it?
Thanks for your great work! But i meet a problem. Processing: ./data/images/05_img.jpg /media/perfectworld/C4F286ACF286A272/project/smplify-x/smplifyx/optimizers/lbfgsls.py:238: UserWarning: This overload of add is deprecated: add(Number alpha, Tensor other) Consider using one of the following signatures instead: add(Tensor other, , Number alpha) (Triggered internally at /pytorch/torch/csrc/utils/python_argparser.cpp:1005.) p.data.add(step_size, update[offset:offset + numel].view_as(p.data)) Camera initialization done after 0.9836 Camera initialization final loss 2933.3396 Stage 000 done after 0.6935 seconds
main(args)
File "smplifyx/main.py", line 262, in main
args)
File "/media/perfectworld/C4F286ACF286A272/project/smplify-x/smplifyx/fit_single_frame.py", line 444, in fit_single_frame
use_vposer=use_vposer)
File "/media/perfectworld/C4F286ACF286A272/project/smplify-x/smplifyx/fitting.py", line 175, in run_fitting
loss = optimizer.step(closure)
File "/home/perfectworld/anaconda3/envs/smplify-x/lib/python3.7/site-packages/torch/optim/optimizer.py", line 89, in wrapper
return func( args, kwargs)
File "/media/perfectworld/C4F286ACF286A272/project/smplify-x/smplifyx/optimizers/lbfgs_ls.py", line 280, in step
orig_loss = closure()
File "/media/perfectworld/C4F286ACF286A272/project/smplify-x/smplifyx/fitting.py", line 249, in fitting_func
kwargs)
File "/home/perfectworld/anaconda3/envs/smplify-x/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, kwargs)
File "/media/perfectworld/C4F286ACF286A272/project/smplify-x/smplifyx/fitting.py", line 430, in forward
collision_idxs = self.search_tree(triangles)
File "/home/perfectworld/anaconda3/envs/smplify-x/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, *kwargs)
File "/home/perfectworld/anaconda3/envs/smplify-x/lib/python3.7/site-packages/mesh_intersection-0.1.0-py3.7-linux-x86_64.egg/mesh_intersection/bvh_search_tree.py", line 56, in forward
return BVHFunction.apply(triangles)
File "/home/perfectworld/anaconda3/envs/smplify-x/lib/python3.7/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(args, kwargs)
File "/home/perfectworld/anaconda3/envs/smplify-x/lib/python3.7/site-packages/mesh_intersection-0.1.0-py3.7-linux-x86_64.egg/mesh_intersection/bvh_search_tree.py", line 39, in forward
max_collisions=BVHFunction.max_collisions)
RuntimeError: after reduction step 1: cudaErrorInvalidDevice: invalid device ordinal
Stage 001 done after 0.8133 seconds
Stage 002 done after 0.9066 seconds
Stage: 60%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████ | 3/5 [00:02<00:01, 1.23it/s] Orientation: 0%| | 0/1 [00:02<?, ?it/s] Traceback (most recent call last): File "smplifyx/main.py", line 272, in
It seems that the cuda version is mismatch with the program, but RTX3090 only supports CUDA11.x. How can i solve it?