Train models that outline objects from text prompts.
What it does
Trains, evaluates, and prepares text-guided instance-segmentation models for inference and deployment.
When to use it
Use for training, evaluation, export, quantization, or inference with a TAO Mask-Grounding-DINO model.
How to use it
Give it segmentation datasets; it runs model training and saves the results in a results directory.
What you provide
- Your files
Uses
TT
Latest review
What you need · 6
Requires Docker for the container-based workflow.
Requires NVIDIA Container Toolkit alongside Docker.
Requires at least one GPU; recommends four GPUs and 24GB or more GPU memory per GPU, preferably A100.
Must run first for a standalone installation when the session was not initialized by the TAO skill bank plugin.
Access · 0
No additional actions listed.