Individual skill
tao-train-foundation-stereo
Stereo depth estimation using FoundationStereo. Predicts disparity maps from stereo image pairs for 3D reconstruction. Use when training, evaluating, exporting, or running inference for a TAO FoundationStereo model. Trigger phrases include "train stereo depth", "FoundationStereo", "stereo disparity estimation", "3D reconstruction from stereo".
skills/tao-train-foundation-stereo/SKILL.md
Source commit fce3cca4170be75e82c64920654d56ee2811b005
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 9, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 3,907
- Repository last updated
- Nov 6, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- agentic-ai Repository topic
- ai-agents Repository topic
- claude-code Repository topic
- codex Repository topic
- coding-agents Repository topic
- cuda Repository topic
- developer-tools Repository topic
- llm Repository topic
- omniverse Repository topic
- stereo Declared skill tag
- depth Declared skill tag
- estimation Declared skill tag
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
BENCHMARK.mddoc · 7,206 bytesSKILL.mdcore · 12,988 bytesSKILL.mdcore · 12,988 bytesSKILL.mdcore · 12,988 bytesSKILL.mdcore · 12,988 bytesconfig/skillspector-baseline.yamlasset · 1,010 bytesevals/evals.jsonasset · 819 bytesreferences/checkpoint-inference-mappings-foundation-stereo.mddoc · 3,974 bytesreferences/parameters-foundation-stereo.mddoc · 5,755 bytesreferences/skill_info.yamlasset · 5,659 bytesreferences/spec-overrides-foundation-stereo.mddoc · 4,170 bytesreferences/spec_template_deploy.yamlasset · 2,029 bytesreferences/spec_template_evaluate.yamlasset · 5,676 bytesreferences/spec_template_export.yamlasset · 5,745 bytesreferences/spec_template_gen_trt_engine.yamlasset · 5,764 bytesreferences/spec_template_inference.yamlasset · 5,698 bytesreferences/spec_template_quantize.yamlasset · 5,511 bytesreferences/spec_template_train.yamlasset · 5,511 bytesreferences/tao-deploy-foundation-stereo.mddoc · 11,989 bytesreferences/tao-deploy-foundation-stereo.skill_info.yamlasset · 3,265 bytesreferences/troubleshooting-foundation-stereo.mddoc · 2,463 bytesschemas/evaluate.schema.jsonasset · 106,996 bytesschemas/export.schema.jsonasset · 107,660 bytesschemas/gen_trt_engine.schema.jsonasset · 109,561 bytesschemas/inference.schema.jsonasset · 107,441 bytesschemas/manifest.jsonasset · 30,587 bytesschemas/quantize.schema.jsonasset · 103,806 bytesschemas/train.schema.jsonasset · 103,800 bytesskill-card.mddoc · 4,511 bytesskill.oms.sigasset · 10,169 bytes
Read excerpt
# 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`.
