search

ispc-lab / HRegNet

[ICCV 2021] HRegNet: A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registration
MIT License
90 stars 12 forks source link

"import point_utils_cuda" cant make it #8

Closed Git-oNmE closed 2 years ago

Git-oNmE commented 2 years ago

I was running sh scripts/train_kitti_det.sh,then I got the error message

/home/hlf/miniconda3/envs/HRegNet/lib/python3.9/site-packages/MinkowskiEngine-0.5.4-py3.9-linux-x86_64.egg/MinkowskiEngine/__init__.py:36: UserWarning: The environment variable `OMP_NUM_THREADS` not set. MinkowskiEngine will automatically set `OMP_NUM_THREADS=16`. If you want to set `OMP_NUM_THREADS` manually, please export it on the command line before running a python script. e.g. `export OMP_NUM_THREADS=12; python your_program.py`. It is recommended to set it below 24.
  warnings.warn(
Traceback (most recent call last):
  File "/media/data3/hlf_data/HRegNet0/HRegNet/train_feats.py", line 7, in <module>
    from data.kitti_data import KittiDataset
  File "/media/data3/hlf_data/HRegNet0/HRegNet/data/kitti_data.py", line 11, in <module>
    from models.utils import generate_rand_rotm, generate_rand_trans, apply_transform
  File "/media/data3/hlf_data/HRegNet0/HRegNet/models/utils.py", line 7, in <module>
    import point_utils_cuda
ImportError: /home/hlf/miniconda3/envs/HRegNet/lib/python3.9/site-packages/point_utils-0.0.0-py3.9-linux-x86_64.egg/point_utils_cuda.cpython-39-x86_64-linux-gnu.so: undefined symbol: _ZN3c104cuda20getCurrentCUDAStreamEa

I checked my file list, found no file named "point_utils_cuda.py" indeed. image

How can I deal with this problem? Thank you very much!

FanLu97 commented 2 years ago

Hello, It seems like the version of pytorch or cuda does not match. We only test the code with cuda11.0/11.0 and torch 1.7.0/1.7.1.

Git-oNmE commented 2 years ago

Hello, It seems like the version of pytorch or cuda does not match. We only test the code with cuda11.0/11.0 and torch 1.7.0/1.7.1.

Thank you for your quick reply, firstly. My server's CUDA version is 11.1, which I can't change. And my torch version is 1.7.1. Like it said in the requirement section, maybe torch 1.7.1 with CUDA 11.1 should be ok? image

FanLu97 commented 2 years ago

Yes, cuda 11.1 with torch 1.7.1 should be OK (this is the environment I am using now). I'm sorry I don't know how to solve this problem. I have run the code on multiple platforms and have not encountered your problem.

Git-oNmE commented 2 years ago

Yes, cuda 11.1 with torch 1.7.1 should be OK (this is the environment I am using now). I'm sorry I don't know how to solve this problem. I have run the code on multiple platforms and have not encountered your problem.

I deleted all files and installed again, and this problem disappeared! :)

But now I come into another problem about the dataset, I submitted it in another issue, could you please take a look? Thanks!