domains / families / science / tao-train-pointpillars
tao-train-pointpillars
separate
PointPillars for 3D object detection from LiDAR point clouds. Encodes point clouds into a pseudo-image via a
When to use
- training PointPillars
- evaluating PointPillars
- exporting PointPillars
- pruning PointPillars
- retraining PointPillars
- running inference for PointPillars
- LiDAR 3D detection
- point-cloud object detection
When not to use
- TensorRT engine generation via parent-model gen_trt_engine action
Skill page
Source
| Repository | Path |
|---|
| NVIDIA/skills | skills/tao-train-pointpillars/SKILL.md |