Skip to content

GangZhang842/CPGNet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CPGNet: Cascade Point-Grid Fusion Network for Real-Time LiDAR Semantic Segmentation

Official code for CPGNet

CPGNet: Cascade Point-Grid Fusion Network for Real-Time LiDAR Semantic Segmentation, Xiaoyan Li, Gang Zhang, Hongyu Pan, Zhenhua Wang. Accepted by ICRA2022 (arXiv:2204.09914)

NEWS

[2022-02-01] CPGNet is accepted by ICRA 2022

1 Dependency

CUDA>=10.2
Pytorch>=1.8.0
[email protected]
[email protected]
nuscenes

2 Training Process

2.1 Installation

python3 setup.py install

2.2 Training Script

torchrun --master_port=12098 --nproc_per_node=4 train.py --config config/config_cpgnet_sgd_bili_sample_ohem_fp16.py

3 Evaluate Process

torchrun --master_port=12097 --nproc_per_node=4 evaluate.py --config config/config_cpgnet_sgd_bili_sample_ohem_fp16.py --start_epoch 0 --end_epoch 47

Citations

@inproceedings{li2022cpgnet,
  author={Li, Xiaoyan and Zhang, Gang and Pan, Hongyu and Wang, Zhenhua},
  booktitle={2022 International Conference on Robotics and Automation (ICRA)}, 
  title={CPGNet: Cascade Point-Grid Fusion Network for Real-Time LiDAR Semantic Segmentation}, 
  year={2022},
  volume={},
  number={},
  pages={11117-11123},
  doi={10.1109/ICRA46639.2022.9811767}
}

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published