Tao Train Foundation Stereo

If you're building 3D reconstruction pipelines from stereo camera pairs, this wraps NVIDIA's TAO FoundationStereo model for training, evaluation, and inference on disparity maps. It's AutoML-enabled by default, which is helpful if you don't want to hand-tune hyperparameters, though you can disable it. The workflow is typical TAO: annotate your stereo pairs, pick the right dataset class (Middlebury, KITTI, ETH3D, or GenericDataset), write a spec yaml, and run. One thing to watch: crop sizes need to match between training and export or you'll have shape mismatches downstream. The convert action generates annotation files if your data isn't already formatted as left-right-disparity triplets. Requires Docker with NVIDIA container toolkit.

Install to Claude Code

npx -y skills add nvidia/skills --skill tao-train-foundation-stereo --agent claude-code