Train models to match people across cameras.
What it does
Trains, evaluates, and exports person-matching models and runs inference to match people across camera views.
When to use it
Use for training, evaluation, export, or inference with a TAO person re-identification model.
How to use it
Give it datasets and model checkpoints as needed for the requested action; it saves model results and output files on your computer.
What you provide
- Your files
What you need · 5
Requires Docker for the container-based workflow; no TAO SDK or Python installation is needed on the host.
Requires the NVIDIA Container Toolkit alongside Docker.
Requires at least one GPU with 16GB or more VRAM per GPU; two GPUs are recommended.
Must run 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.