multi-sa-bev
Science Score: 54.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
✓Academic publication links
Links to: arxiv.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (10.3%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: WAN-M
- License: apache-2.0
- Language: Python
- Default Branch: master
- Size: 52.8 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 1
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
SA-BEV
[ICCV2023] SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection
News
- 2023.07.14 SA-BEV is accepted by ICCV 2023. The paper is available here.
Main Results
| Config | mAP | NDS | Baidu | Google | | --------------------------------------------------------------- | :----: | :----: | :-----: | :---: | | SA-BEV-R50 | 35.5 | 46.7 | link | link | | SA-BEV-R50-MSCT | 37.0 | 48.8 | link | link | | SA-BEV-R50-MSCT-CBGS| 38.7 | 51.2 | link | link |
Get Started
1. Please follow these steps to install SA-BEV.
a. Create a conda virtual environment and activate it.
shell
conda create -n sabev python=3.8 -y
conda activate sabev
b. Install PyTorch and torchvision following the official instructions.
shell
pip install torch==1.10.0+cu111 torchvision==0.11.0+cu111 torchaudio==0.10.0 -f https://download.pytorch.org/whl/torch_stable.html
c. Install SA-BEV as mmdet3d.
shell
pip install mmcv-full==1.5.3
pip install mmdet==2.27.0
pip install mmsegmentation==0.25.0
pip install -e .
2. Prepare nuScenes dataset as introduced in nuscenes_det.md and create the pkl for SA-BEV by running:
shell
python tools/create_data_bevdet.py
3. Download nuScenes-lidarseg from nuScenes official site and put it under data/nuscenes/. Create depth and semantic labels from point cloud by running:
shell
python tools/generate_point_label.py
4. Train and evalutate model following:
shell
bash tools/dist_train.sh configs/sabev/sabev-r50.py 8 --no-validate
bash tools/dist_test.sh configs/sabev/sabev-r50.py work_dirs/sabev-r50/epoch_24_ema.pth 8 --eval bbox
Acknowledgement
This project is not possible without multiple great open-sourced code bases. We list some notable examples below.
Bibtex
If SA-BEV is helpful for your research, please consider citing the following BibTeX entry.
@article{zhang2023sabev,
title={SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection},
author={Jinqing, Zhang and Yanan, Zhang and Qingjie, Liu and Yunhong, Wang},
journal={arXiv preprint arXiv:2307.11477},
year={2023},
}
Owner
- Login: WAN-M
- Kind: user
- Repositories: 1
- Profile: https://github.com/WAN-M
Citation (CITATION.cff)
cff-version: 1.2.0 message: "If you use this software, please cite it as below." authors: - name: "MMDetection3D Contributors" title: "OpenMMLab's Next-generation Platform for General 3D Object Detection" date-released: 2020-07-23 url: "https://github.com/open-mmlab/mmdetection3d" license: Apache-2.0
GitHub Events
Total
Last Year
Dependencies
- actions/checkout v2 composite
- actions/setup-python v2 composite
- codecov/codecov-action v1.0.10 composite
- codecov/codecov-action v2 composite
- actions/checkout v2 composite
- actions/setup-python v2 composite
- actions/checkout v2 composite
- actions/setup-python v1 composite
- actions/checkout v2 composite
- actions/setup-python v2 composite
- nvcr.io/nvidia/tensorrt 22.07-py3 build
- pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
- docutils ==0.16.0
- m2r *
- mistune ==0.8.4
- myst-parser *
- sphinx ==4.0.2
- sphinx-copybutton *
- sphinx_markdown_tables *
- mmcv-full >=1.4.8,<=1.6.0
- mmdet >=2.24.0,<=3.0.0
- mmsegmentation >=0.20.0,<=1.0.0
- open3d *
- spconv *
- waymo-open-dataset-tf-2-1-0 ==1.2.0
- mmcv >=1.4.8
- mmdet >=2.24.0
- mmsegmentation >=0.20.1
- torch *
- torchvision *
- lyft_dataset_sdk *
- networkx >=2.2,<2.3
- numba ==0.53.0
- numpy *
- nuscenes-devkit *
- plyfile *
- scikit-image *
- setuptools ==58.0.4
- tensorboard ==2.9.1
- trimesh >=2.35.39,<2.35.40
- asynctest * test
- codecov * test
- flake8 * test
- interrogate * test
- isort * test
- kwarray * test
- pytest * test
- pytest-cov * test
- pytest-runner * test
- ubelt * test
- xdoctest >=0.10.0 test
- yapf * test