Turn image points and boxes into precise masks.
What it does
Trains, evaluates, and runs segmentation models that turn point or box annotations into image masks.
When to use it
Use when training, evaluating, or running inference for a TAO MAL model.
How to use it
Give it images and annotations; it runs MAL training, evaluation, or inference and saves results locally.
What you provide
- Your files
What you need · 5
Requires Docker to launch the TAO container; the documented launch does not require host Python or the TAO SDK.
Requires NVIDIA Container Toolkit alongside Docker.
Requires at least one GPU. The documented memory requirement is 24GB or more per GPU for the ViT-MAE backbone at crop size 512; two GPUs are recommended.
Requires running tao-setup first when the session was not initialized by the TAO skill bank plugin, for host preflight, credentials, and cross-skill discovery.
Access · 0
No additional actions listed.