Turn stereo image pairs into depth estimates.
What it does
Trains and evaluates FoundationStereo models to produce disparity maps from stereo image pairs.
When to use it
Use for training, evaluation, export, or inference with a TAO FoundationStereo model.
How to use it
Give it stereo image data and a training, evaluation, export, or inference request; it runs the model workflow and saves results.
What you provide
- Your files
Latest review
What you need · 5
Requires Docker to run the TAO container.
Requires the NVIDIA container toolkit for the GPU-enabled container workflow.
The documented container launch requires access to GPU device 0.
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.