1. 安装

1.1 前提条件

• gcc 5 (c++11或更新版本)
• python >= 3.6
• cuda >= 10.1
• pytorch >= 1.6

# spconv
spconv_cu11{X}（根据你的cuda版本设置X）

# waymo_open_dataset
## python 3.6
waymo-open-dataset-tf-2-1-0==1.2.0

## python 3.7, 3.8
waymo-open-dataset-tf-2-4-0==1.3.1

1.2 从源代码构建

git clone https://github.com/poodarchu/EFG.git
cd EFG
pip install -v -e .
# 设置日志路径以保存模型检查点、训练日志等
echo "export EFG_CACHE_DIR=/path/to/your/logs/dir" >> ~/.bashrc

2. 数据

2.1 数据准备 - Waymo

# 下载waymo数据集v1.2.0（或v1.3.2等）
gsutil -m cp -r \
  "gs://waymo_open_dataset_v_1_2_0_individual_files/testing" \
  "gs://waymo_open_dataset_v_1_2_0_individual_files/training" \
  "gs://waymo_open_dataset_v_1_2_0_individual_files/validation" \
  .

# 从tfrecord提取帧到pkl
CUDA_VISIBLE_DEVICES=-1 python cli/data_preparation/waymo/waymo_converter.py --record_path "/path/to/waymo/training/*.tfrecord" --root_path "/path/to/waymo/train/"
CUDA_VISIBLE_DEVICES=-1 python cli/data_preparation/waymo/waymo_converter.py --record_path "/path/to/waymo/validation/*.tfrecord" --root_path "/path/to/waymo/val/"

# 创建数据集的软链接
cd /path/to/EFG/datasets; ln -s /path/to/waymo/dataset/root waymo; cd ..
# 从提取的帧创建数据摘要和gt数据库
python cli/data_preparation/waymo/create_data.py --root-path datasets/waymo --split train --nsweeps 1
python cli/data_preparation/waymo/create_data.py --root-path datasets/waymo --split val --nsweeps 1

2.2 数据准备 - nuScenes

# nuScenes

dataset/nuscenes
├── can_bus
├── lidarseg
├── maps
├── occupancy
│   ├── annotations.json
│   └── gts
├── panoptic
├── samples
├── sweeps
├── v1.0-mini
├── v1.0-test
└── v1.0-trainval

# 创建数据集的软链接
cd /path/to/EFG/datasets; ln -s /path/to/nuscenes/dataset/root nuscenes; cd ..
# 假设这里我们使用nuScenes/samples图像，将gts和annotations.json放在nuScenes/occupancy下
python cli/data_preparation/nuscenes/create_data.py --root-path datasets/nuscenes --version v1.0-trainval --nsweeps 11 --occ --seg

3. 开始使用

3.1 训练与评估

# cd playground/path/to/experiment/directory

efg_run --num-gpus x  # 默认为1
efg_run --num-gpus x task [train | val | test]
efg_run --num-gpus x --resume
efg_run --num-gpus x dataloader.num_workers 0  # 动态更改config.yaml中的选项

模型将在训练结束时自动评估。或者，

efg_run --num-gpus x task val

4. 模型库

所有模型均在8 x NVIDIA A100 GPU上训练和评估。

Waymo开放数据集 - 3D目标检测（验证集 - mAPH/L2）

nuScenes - 3D目标检测（验证集）

5. 寻求贡献

EFG目前处于相对初步的阶段，我们还有很多工作要做。如果您有兴趣贡献，可以发送邮件至poodarchu@gmail.com。

6. 引用

@article{chen2023trajectoryformer,
  title={TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses},
  author={Chen, Xuesong and Shi, Shaoshuai and Zhang, Chao and Zhu, Benjin and Wang, Qiang and Cheung, Ka Chun and See, Simon and Li, Hongsheng},
  journal={arXiv preprint arXiv:2306.05888},
  year={2023}
}

@inproceedings{zhu2023conquer,
  title={Conquer: Query contrast voxel-detr for 3d object detection},
  author={Zhu, Benjin and Wang, Zhe and Shi, Shaoshuai and Xu, Hang and Hong, Lanqing and Li, Hongsheng},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={9296--9305},
  year={2023}
}

@misc{zhu2023efg,
    title={EFG: An Efficient, Flexible, and General deep learning framework that retains minimal},
    author={EFG Contributors},
    howpublished = {\url{https://github.com/poodarchu/efg}},
    year={2023}
}