DSGN2
DSGN2 copied to clipboard
Missing dependencies
Can you please provide more environment details? I am facing a problem with pcdet build. It would be great if you provide a conda env or a Dockerfile.
Thanks
Error Traceback:
Traceback (most recent call last):
File "tools/train.py", line 13, in <module>
from pcdet.datasets import build_dataloader
File "/home/trainer/dsgn2/pcdet/datasets/__init__.py", line 5, in <module>
from .kitti.lidar_kitti_dataset import LiDARKittiDataset
File "/home/trainer/dsgn2/pcdet/datasets/kitti/lidar_kitti_dataset.py", line 10, in <module>
from pcdet.utils import box_utils, calibration_kitti, common_utils, object3d_kitti
File "/home/trainer/dsgn2/pcdet/utils/box_utils.py", line 7, in <module>
from pcdet.ops.roiaware_pool3d import roiaware_pool3d_utils
File "/home/trainer/dsgn2/pcdet/ops/roiaware_pool3d/roiaware_pool3d_utils.py", line 7, in <module>
from . import roiaware_pool3d_cuda
ImportError: /home/trainer/dsgn2/pcdet/ops/roiaware_pool3d/roiaware_pool3d_cuda.cpython-38-x86_64-linux-gnu.so: undefined symbol: _ZNK2at6Tensor8data_ptrIfEEPT_v
Hi, could you check if the pytorch matches cuda verison? This error often occurs when they are not matched.
@chenyilun95 Please provide a dockerfile.
I am facing lots of issues with spconv and cumm intsallation.
Thanks
Hi, could you check if the pytorch matches cuda verison? This error often occurs when they are not matched. can you tell us pytorch and cuda version
I use cuda 10.2 conda install pytorch torchvision torchaudio cudatoolkit=10.2 -c pytorch
have the issue too
python -m pcdet.datasets.kitti.lidar_kitti_dataset create_kitti_infos
Traceback (most recent call last):
File "/home/azuryl/anaconda3/envs/dsgn_j/lib/python3.8/runpy.py", line 185, in _run_module_as_main
mod_name, mod_spec, code = _get_module_details(mod_name, _Error)
File "/home/azuryl/anaconda3/envs/dsgn_j/lib/python3.8/runpy.py", line 111, in _get_module_details
import(pkg_name)
File "/data/azuryl/DSGN2/pcdet/datasets/init.py", line 5, in
@chenyilun95 Please provide a dockerfile.
I am facing lots of issues with spconv and cumm intsallation.
Thanks
Hi, could you check if the pytorch matches cuda verison? This error often occurs when they are not matched.
please tell us which python version, which cuda version, which pytorch version you used
I use python setup.py develop
to solve this problem. It seems that the environment needs to be installed before step 2
I have ran the experiments with pytorch 1.7.1+cu101 and cu111.
@chenyilun95 Please provide a dockerfile. I am facing lots of issues with spconv and cumm intsallation. Thanks
Hi, could you check if the pytorch matches cuda verison? This error often occurs when they are not matched.
please tell us which python version, which cuda version, which pytorch version you used
datasets
您好,我遇到了同样的问题,请问您问题解决了吗,谢谢