Train 3D object detectors on LiDAR scans.
What it does
Trains and manages PointPillars models that detect 3D objects in LiDAR point clouds.
When to use it
Use when training, evaluating, exporting, pruning, retraining, or running inference for a TAO PointPillars model.
How to use it
Give it LiDAR training data; it runs PointPillars training and saves model results to a results folder.
What you provide
- Your files
Uses
Good to know
- a credential is hard-coded: key
What you need · 5
Requires Docker for the container-based workflow.
Requires NVIDIA Container Toolkit alongside Docker.
Requires at least one GPU with 16GB or more VRAM per GPU; recommends four GPUs and names V100 or A100.
Requires running tao-setup first for host preflight, credentials, and cross-skill discovery when the session was not initialized by the TAO skill bank plugin.
Access · 0
No additional actions listed.