Train Deformable DETR to find objects in images.
What it does
Trains, evaluates, quantizes, and exports Deformable DETR object detectors, with inference and TensorRT engine generation workflows.
When to use it
Use for training, evaluating, exporting, quantizing, or running inference with a TAO Deformable-DETR model.
How to use it
Give it object-detection data and a requested model operation; it runs the workflow and saves its results.
What you provide
- Your files
Uses
Good to know
- a credential is hard-coded: encryption_key
What you need · 5
Requires Docker to run the model containers.
Requires NVIDIA Container Toolkit alongside Docker.
Requires at least one GPU with 16GB or more VRAM per GPU; four GPUs are recommended.
Must run first for standalone sessions not initialized by the TAO skill bank plugin, handling host preflight, credentials, and cross-skill discovery.
Access · 0
No additional actions listed.