Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Bad substitution when running dist_test.sh #15

Open
Joechencc opened this issue May 12, 2023 · 5 comments
Open

Bad substitution when running dist_test.sh #15

Joechencc opened this issue May 12, 2023 · 5 comments

Comments

@Joechencc
Copy link

Thanks for your error report and we appreciate it a lot.

Checklist

  1. I have searched related issues but cannot get the expected help.
  2. The bug has not been fixed in the latest version.

Describe the bug
A clear and concise description of what the bug is.

Reproduction

  1. What command or script did you run?
sh ./tools/dist_test.sh ./configs/MSMDFusion_nusc_voxel_LC.py $ckpt_path$ 8 --eval bbox
A placeholder for the command.
  1. Did you make any modifications on the code or config? Did you understand what you have modified?
    No change to the code
  2. What dataset did you use?
    Nuscense dataset

Environment

  1. Please run python mmdet3d/utils/collect_env.py to collect necessary environment infomation and paste it here.
    ImportError: cannot import name 'get_git_hash' from 'mmcv.utils' (/home/cc7287/mambaforge/envs/open-mmlab/lib/python3.7/site-packages/mmcv/utils/init.py)
  2. You may add addition that may be helpful for locating the problem, such as
    • How you installed PyTorch [e.g., pip, conda, source]
    • Other environment variables that may be related (such as $PATH, $LD_LIBRARY_PATH, $PYTHONPATH, etc.)
      conda create -n open-mmlab python=3.7 -y
      conda activate open-mmlab

install latest pytorch prebuilt with the default prebuilt CUDA version (usually the latest)

conda install -c pytorch pytorch torchvision -y

install mmcv

pip install mmcv-full

install mmdetection

pip install git+https://github.com/open-mmlab/mmdetection.git

install mmdetection3d

git clone https://github.com/open-mmlab/mmdetection3d.git
cd mmdetection3d
pip install -v -e .

Error traceback
If applicable, paste the error trackback here.

A placeholder for trackback.

Bug fix
If you have already identified the reason, you can provide the information here. If you are willing to create a PR to fix it, please also leave a comment here and that would be much appreciated!

@SxJyJay
Copy link
Owner

SxJyJay commented May 12, 2023

I don't get the exact error you encountered. Can you briefly describe your problem?😊

@Joechencc
Copy link
Author

Joechencc commented May 12, 2023

Hi, I am unable to find the correct version to use for mmdet3D, mmdet, and mmcv. Which CUDA version is installed on your computer? It seems like CUDA>=11.0 does not work

@SxJyJay
Copy link
Owner

SxJyJay commented May 13, 2023

I use CUDA 11.1. Please make sure the CUDA that you used to build or install mmdet3D, mmdet, and mmcv has the same version as the one used during the runtime.

@Joechencc
Copy link
Author

I got the environment working. I wonder if I just need the bounding box location for nuscense dataset. What dataset and what command do I need? For example, should I use the standard nuscense dataset or your precomputed dataset? What is the command to run?

@SxJyJay
Copy link
Owner

SxJyJay commented May 16, 2023

You can follow the instructions here to prepare the data. Nuscenes dataset provides the basic sensor data and their annotations. Our precomputed data only include virtual points as stated in the paper.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants