git clone https://github.com/ZikangZhou/HiVT.git
cd HiVT

conda create -n HiVT python=3.8
conda activate HiVT
conda install pytorch==1.8.0 cudatoolkit=11.1 -c pytorch -c conda-forge
conda install pytorch-geometric==1.7.2 -c rusty1s -c conda-forge
conda install pytorch-lightning==1.5.2 -c conda-forge

/path/to/dataset_root/
├── train/
|   └── data/
|       ├── 1.csv
|       ├── 2.csv
|       ├── ...
└── val/
    └── data/
        ├── 1.csv
        ├── 2.csv
        ├── ...

python train.py --root /path/to/dataset_root/ --embed_dim 64

python train.py --root /path/to/dataset_root/ --embed_dim 128

tensorboard --logdir lightning_logs/

python eval.py --root /path/to/dataset_root/ --batch_size 32 --ckpt_path /path/to/your_checkpoint.ckpt

tensorboard --logdir checkpoints/

@inproceedings{zhou2022hivt,
  title={HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction},
  author={Zhou, Zikang and Ye, Luyao and Wang, Jianping and Wu, Kui and Lu, Kejie},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2022}
}