Train detectors that find objects from text.
What it does
Trains and runs text-prompted Grounding DINO detectors, with evaluation, export, and quantization workflows.
When to use it
Use for training, evaluating, exporting, quantizing, or running inference with a TAO Grounding DINO model.
How to use it
Give it datasets and a requested model operation; it produces model artifacts and results in an output folder.
What you provide
- Your files
What you need · 5
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 VRAM per GPU, with reduced batches for 16GB GPUs.
Must run first for host preflight, credentials, and cross-skill discovery unless the session was initialized by the TAO skill bank plugin.
Access · 0
No additional actions listed.