I have some trouble running the code. I hope you can help me.Producer process has been terminated before all shared CUDA tensors released. See Note [Sharing CUDA tensors]
zerolfq opened this issue · comments
******* initializing first_frame: 0
initializing the first frame ...
mapping process started!
insert keyframe
******* tracking process started! *******
tracking frame: 52%|█████████████▉ | 51/99 [00:32<00:34, 1.38it/s]insert keyframe
********** current num kfs: 2 **********
tracking frame: 100%|███████████████████████████| 99/99 [01:07<00:00, 1.47it/s]
========== stop_mapping set ==========
******* tracking process died *******
[W CudaIPCTypes.cpp:15] Producer process has been terminated before all shared CUDA tensors released. See Note [Sharing CUDA tensors]
********** post-processing 0 steps **********
******* extracting final mesh *******
/home/xyz/anaconda3/envs/Vox/lib/python3.9/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/conda/conda-bld/pytorch_1634272204863/work/aten/src/ATen/native/TensorShape.cpp:2157.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
********** get color from network **********
/home/xyz/Github/Vox-Fusion/src/utils/mesh_util.py:110: UserWarning: floordiv is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
voxel_pos = points // self.voxel_size
tensor(1457)
******* mapping process died *******
[W CudaIPCTypes.cpp:15] Producer process has been terminated before all shared CUDA tensors released. See Note [Sharing CUDA tensors]
/home/xyz/anaconda3/envs/Vox/lib/python3.9/multiprocessing/resource_tracker.py:216: UserWarning: resource_tracker: There appear to be 3 leaked semaphore objects to clean up at shutdown
warnings.warn('resource_tracker: There appear to be %d '
Hi, this warning only appears after the program ends and does not affect the result. You can find the final mesh in your log folder.
I got the same warning, but there was no output in any folder :(