Views
No views yet
| Method | Car @ 0.50 | Ped @ 0.25 | Cyc @ 0.25 | mAP_3D |
|---|---|---|---|---|
| This checkpoint (best seed, s3) | 41.58 | 44.78 | 71.31 | 52.56 |
| 3-seed mean | 41.02 | 43.15 | 70.12 | 51.43 ± 0.99 |
| RadarPillars (paper) | 41.10 | 38.60 | 72.60 | 50.70 |
1git clone https://github.com/fthbng77/RadarPillar
2cd RadarPillar
3python setup.py develop
4
5# download this checkpoint
6huggingface-cli download fthbng77/radarpillars-vod radarpillar_vod_best_map52.56.pth --local-dir weights
7
8# evaluate
9python tools/test.py \
10 --cfg_file tools/cfgs/vod_models/vod_radarpillar_rot.yaml \
11 --ckpt weights/radarpillar_vod_best_map52.56.pth1@inproceedings{radarpillars2024,
2 title = {RadarPillars: Efficient Object Detection from 4D Radar Point Clouds},
3 author = {Musiat, Alexander and Reichardt, Laurenz and Schulze, Michael and Wasenm{\"u}ller, Oliver},
4 booktitle = {Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems (IROS)},
5 year = {2024}
6}