Pytorch RuntimeError
Sangmin-Bak opened this issue · comments
Thank you for your research, I have a question because the following issue arose.
When I run "run.py", I get a RuntimeError like below. I would like to know how to solve this.
Traceback (most recent call last):
File "/home/psm/anaconda3/envs/nice-slam/lib/python3.7/multiprocessing/process.py", line 297, in _bootstrap
self.run()
File "/home/psm/anaconda3/envs/nice-slam/lib/python3.7/multiprocessing/process.py", line 99, in run
self._target(*self._args, **self._kwargs)
File "/home/psm/workspace/nice-slam/src/NICE_SLAM.py", line 276, in mapping
self.mapper.run()
File "/home/psm/workspace/nice-slam/src/Mapper.py", line 606, in run
gt_c2w, self.keyframe_dict, self.keyframe_list, cur_c2w=cur_c2w)
File "/home/psm/workspace/nice-slam/src/Mapper.py", line 518, in optimize_map
val[mask] = val_grad.clone().detach()
RuntimeError: out_ptr == out_accessor[thread_count_nonzero[tid + 1]].data()INTERNAL ASSERT FAILED at "/opt/conda/conda-bld/pytorch_1634272168290/work/aten/src/ATen/native/TensorAdvancedIndexing.cpp":1723, please report a bug to PyTorch.
Hi, please make sure you are using the exact conda environment.yaml and ubuntu desktop. If all versions match, there should not be a problem.