Claude MarketplacesSubmit
nvidia avatar

Tao Train Foundation Stereo

nvidia/skillsOfficial

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.

skills.sh installs
1.6K
GitHub stars
3.9K
last updated
Aug 21, 2026
View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Depth Net Stereo

Standalone install? If this session was not initialized by the TAO skill bank plugin, run the tao-setup skill first (host preflight, credentials, cross-skill discovery).

Stereo depth estimation using FoundationStereo architecture. Predicts disparity maps from stereo image pairs for 3D reconstruction.

Uses pretrained Depth Anything v2 and EdgeNeXt encoders. Set model.stereo_backbone.depth_anything_v2_pretrained_path and model.stereo_backbone.edgenext_pretrained_path.

The mono and stereo skills both invoke the unified TAO depth_net CLI inside the container; the mono/stereo family is selected via model.model_type (e.g., FoundationStereo).

PyT actions packaged by this model skill: train, evaluate, inference, export, and quantize. The PyT depth_net entrypoint does not accept a gen_trt_engine action in the current TAO image; build TensorRT engines only through the deploy workflow.

For TAO Deploy TensorRT actions (gen_trt_engine, TensorRT evaluate, and TensorRT inference), read references/tao-deploy-foundation-stereo.md first. The deploy spec template lives in this skill's references/spec_template_deploy.yaml.

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Details

Repository
github.com/nvidia/skills
First seen
Jul 14, 2026

More from nvidia/skills

All 236

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs