Closed JunjieChen-2020 closed 3 years ago
I guess you are trying to train with the wrong python interpreter. I strongly recommend you to use anaconda to set up the environment.
File "/home/cjj/testcnn/disprcnn/disprcnn/disprcnn/layers/init.py", line 9, in
File "/home/cjj/testcnn/disprcnn/disprcnn/disprcnn/layers/nms.py", line 3, in
ImportError File "/home/cjj/testcnn/disprcnn/disprcnn/disprcnn/layers/nms.py", line 3, in
File "/home/cjj/testcnn/disprcnn/disprcnn/disprcnn/layers/init.py", line 9, in
i used the anaconda emvironment from environment.yaml
You have to re-run "sh build_and_install.sh" if you install a different version of pytorch.
i re -run 'sh build_and_install,sh',still report error as follow:
Traceback (most recent call last):
File "/root/miniconda3/envs/disprcnn/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/root/miniconda3/envs/disprcnn/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/root/miniconda3/envs/disprcnn/lib/python3.7/site-packages/torch/distributed/launch.py", line 246, in
I re-run environment.yaml,and sh build_and_install.the console report the error info as follow: RuntimeError: The NVIDIA driver on your system is too old (found version 9000). Please update your GPU driver by downloading and installing a new version from the URL: http://www.nvidia.com/Download/index.aspx Alternatively, go to: https://pytorch.org to install a PyTorch version that has been compiled with your version of the CUDA driver.
i can not find the file pointnet2_cuda :'import pointnet2_cuda as pointnet2'.
Run the commands in "build_and_install.sh" line by line, and check which of them report errors. Update your GPU driver as suggested.
Closed since no updates for a long time. Re-open it if you have any questions.
i finished run build_and_install. produced a file '_C.cpython-37m-x86_64-linux-gnu.so' but start sh scripts/train_msrcnn.sh make mistakes. Is it a path problem?
File "/home/cjj/testcnn/disprcnn/disprcnn/tools/disprcnn/layers/init.py", line 9, in
File "/home/cjj/testcnn/disprcnn/disprcnn/tools/disprcnn/layers/nms.py", line 3, in
File "/home/cjj/testcnn/disprcnn/disprcnn/tools/disprcnn/data/datasets/kitti_roi_dataset.py", line 9, in
from .nms import nms
File "/home/cjj/testcnn/disprcnn/disprcnn/tools/disprcnn/layers/nms.py", line 3, in
from .nms import nms
File "/home/cjj/testcnn/disprcnn/disprcnn/tools/disprcnn/layers/nms.py", line 3, in
from disprcnn.structures.disparity import DisparityMap
from disprcnn import _C
File "/home/cjj/testcnn/disprcnn/disprcnn/tools/disprcnn/structures/disparity.py", line 9, in
from disprcnn import _C
ImportError: cannot import name '_C'
ImportError: cannot import name '_C'
from disprcnn import _C
ImportError: cannot import name '_C'
from disprcnn.layers import interpolate
File "/home/cjj/testcnn/disprcnn/disprcnn/tools/disprcnn/layers/init.py", line 9, in
from .nms import nms
File "/home/cjj/testcnn/disprcnn/disprcnn/tools/disprcnn/layers/nms.py", line 3, in
from disprcnn import _C
ImportError: cannot import name '_C'
Traceback (most recent call last):
File "/usr/lib64/python3.6/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/usr/lib64/python3.6/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/usr/local/lib64/python3.6/site-packages/torch/distributed/launch.py", line 235, in
main()
File "/usr/local/lib64/python3.6/site-packages/torch/distributed/launch.py", line 231, in main
cmd=process.args)
subprocess.CalledProcessError: Command '['/usr/bin/python3', '-u', 'tools/train_net.py', '--local_rank=0', '--config-file', 'configs/kitti/pob/mask.yaml']' returned non-zero exit status 1.