search

Lab-of-AI-and-Robotics / GS_ICP_SLAM

[ECCV 2024] RGBD GS-ICP SLAM
MIT License
280 stars 29 forks source link

Some strange errors #12

Open YZWYD opened 4 months ago

YZWYD commented 4 months ago

First of all, I would like to thank the open source community for such excellent work! When I tried to replicate this work on Jetson AGX Orin, I encountered some errors. (gsicpslam) nvidia@ubuntu:~/project/GS_ICP_SLAM-main$ bash tum_unlimit.sh run rgbd_dataset_freiburg1_desk Traceback (most recent call last): File "gs_icp_slam_unlimit.py", line 240, in gs_icp_slam.run() File "gs_icp_slam_unlimit.py", line 119, in run p.start() File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/process.py", line 121, in start self._popen = self._Popen(self) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/context.py", line 224, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/context.py", line 283, in _Popen return Popen(process_obj) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/popen_spawn_posix.py", line 32, in init super().init(process_obj) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/popen_fork.py", line 19, in init self._launch(process_obj) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/popen_spawn_posix.py", line 47, in _launch reduction.dump(process_obj, fp) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/reduction.py", line 60, in dump ForkingPickler(file, protocol).dump(obj) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/site-packages/torch/multiprocessing/reductions.py", line 270, in reduce_tensor event_sync_required) = storage._sharecuda() File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/site-packages/torch/storage.py", line 1034, in _sharecuda return self._untyped_storage._sharecuda(*args, **kwargs) RuntimeError: CUDA error: operation not supported Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

run rgbd_dataset_freiburg2_xyz Traceback (most recent call last): File "gs_icp_slam_unlimit.py", line 240, in gs_icp_slam.run() File "gs_icp_slam_unlimit.py", line 119, in run p.start() File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/process.py", line 121, in start self._popen = self._Popen(self) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/context.py", line 224, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/context.py", line 283, in _Popen return Popen(process_obj) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/popen_spawn_posix.py", line 32, in init super().init(process_obj) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/popen_fork.py", line 19, in init self._launch(process_obj) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/popen_spawn_posix.py", line 47, in _launch reduction.dump(process_obj, fp) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/reduction.py", line 60, in dump ForkingPickler(file, protocol).dump(obj) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/site-packages/torch/multiprocessing/reductions.py", line 270, in reduce_tensor event_sync_required) = storage._sharecuda() File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/site-packages/torch/storage.py", line 1034, in _sharecuda return self._untyped_storage._sharecuda(*args, **kwargs) RuntimeError: CUDA error: operation not supported Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

run rgbd_dataset_freiburg3_long_office_household Traceback (most recent call last): File "gs_icp_slam_unlimit.py", line 240, in gs_icp_slam.run() File "gs_icp_slam_unlimit.py", line 119, in run p.start() File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/process.py", line 121, in start self._popen = self._Popen(self) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/context.py", line 224, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/context.py", line 283, in _Popen return Popen(process_obj) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/popen_spawn_posix.py", line 32, in init super().init(process_obj) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/popen_fork.py", line 19, in init self._launch(process_obj) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/popen_spawn_posix.py", line 47, in _launch reduction.dump(process_obj, fp) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/multiprocessing/reduction.py", line 60, in dump ForkingPickler(file, protocol).dump(obj) File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/site-packages/torch/multiprocessing/reductions.py", line 270, in reduce_tensor event_sync_required) = storage._sharecuda() File "/home/nvidia/anaconda3/envs/gsicpslam/lib/python3.8/site-packages/torch/storage.py", line 1034, in _sharecuda return self._untyped_storage._sharecuda(*args, **kwargs) RuntimeError: CUDA error: operation not supported Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

Launch-on-Titania commented 1 month ago

I meet this problem too. And I fixed by reinstalling fast_gicp, when u install fast_gicp,