Train models to find depth in a single photo.
What it does
Trains, evaluates, and exports monocular depth models that predict depth from single RGB images.
When to use it
Use when training, evaluating, exporting, or running inference for a TAO monocular depth model.
How to use it
Give it image data and a model-training, evaluation, inference, or export request; it runs the configured action and saves model artifacts or results.
What you provide
- Your files
What you need · 5
Requires Docker to run the TAO container.
Requires NVIDIA Container Toolkit for the container-based workflow.
Requires at least one GPU with 24GB or more VRAM per GPU; two GPUs are recommended.
Must run first for standalone use when the session was not initialized by the TAO skill bank plugin; handles host preflight, credentials, and cross-skill discovery.
Access · 0
No additional actions listed.