Step 0. Install pytorch(v1.9.0).
Step 1. Install MMDetection3D(v1.0.0rc4).
Step 2. Install requirements.
pip install -r requirements.txtStep 3. Install BEVDepth(gpu required).
python setup.py developStep 0. Download nuScenes official dataset.
Step 1. Symlink the dataset root to ./data/.
ln -s [nuscenes root] ./data/
The directory will be as follows.
BEVDepth
├── data
│ ├── nuScenes
│ │ ├── maps
│ │ ├── samples
│ │ ├── sweeps
│ │ ├── v1.0-test
| | ├── v1.0-trainval
Step 2. Prepare infos.
python scripts/gen_info.py
Train.
python [EXP_PATH] --amp_backend native -b 8 --gpus 8
Eval.
python [EXP_PATH] --ckpt_path [CKPT_PATH] -e -b 8 --gpus 8
Please cite our work if you find it useful.
@article{liu2022multi,
title={Multi-latent Space Alignments for Unsupervised Domain Adaptation in Multi-view 3D Object Detection},
author={Liu, Jiaming and Zhang, Rongyu and Chi, Xiaowei and Li, Xiaoqi and Lu, Ming and Guo, Yandong and Zhang, Shanghang},
journal={arXiv preprint arXiv:2211.17126},
year={2022}
}