pyun-ram / FL3D

The code is implemented to show focal loss improvement based on 3D-FCN and VoxelNet for “Focal Loss in 3D Object Detection”.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

README

This repository is for "Focal Loss in 3D Object Detection". If you use this code for academic purpose, we would appreciate if you cite our paper:

@article{yun2018fl3d,
  title={Focal Loss in 3D Object Detection},
  author={Peng Yun, Lei Tai, Yuan Wang, and Ming Liu},
  journal={arXiv preprint arXiv:1809.06065},
  year={2018}
}

Organization

It contains two parts: 3D-FCN and VoxelNet as claimed in our paper. For detailed information of these two parts, please refer the sub-README in each dir.

Data & Weights

The splited data & weights are available in Data&Weights

Docker

The docker images for 3D-FCN and VoxelNet are also available.

docker pull pyun/voxelnet:baseline
docker pull pyun/3d-fcn:tf1.7
# Then launch a container with nvidia-docker 1.0

Acknowledgments

About

The code is implemented to show focal loss improvement based on 3D-FCN and VoxelNet for “Focal Loss in 3D Object Detection”.

License:GNU General Public License v3.0


Languages

Language:Python 62.2%Language:C++ 37.6%Language:Shell 0.2%