Cylinder3D
The source code of our work "Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation.
Installation
Requirements
- PyTorch >= 1.2
- yaml
- Cython
- torch-scatter
- nuScenes-devkit (optional for nuScenes)
- spconv
Data Preparation
SemanticKITTI
./
├──
├── ...
└── path_to_data_shown_in_config/
├──sequences
├── 00/
│ ├── velodyne/
| | ├── 000000.bin
| | ├── 000001.bin
| | └── ...
│ └── labels/
| ├── 000000.label
| ├── 000001.label
| └── ...
├── 08/ # for validation
├── 11/ # 11-21 for testing
└── 21/
└── ...
nuScenes
./
├──
├── ...
└── path_to_data_shown_in_config/
├──v1.0-trainval
├──v1.0-test
├──samples
├──sweeps
├──maps
Training
- modify the config/semantickitti.yaml with your custom settings. We provide a sample yaml for SemanticKITTI.
- train the network by running "sh train.sh".
Pretrained Models
-- We provide a pretrained model for SemanticKITTI LINK1 or LINK2 (access code: xqmi)
TODO List
- [ ] Release pretrained model for nuScenes.
- [ ] Support more models, including PolarNet, RandLA, SequeezeV3 and etc.
- [ ] Support more datasets, including A2D2 and etc.
- [ ] Integrate LiDAR Panoptic Segmentation into the codebase.