Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Training a stereo depth model v1.0.0

Use this resource to train and run a TAO FoundationStereo stereo disparity model

New

  • 579 downloads
  • 169 likes
  • 230 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install stereo-depth-disparity-training

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent guides annotation preparation, pairing of model_type and dataset_name, the YAML spec, and the training, evaluation and export runs. It reminds you which pretrained weights to set, such as the Depth Anything v2 and EdgeNeXt encoder paths. You get a checked run for 3D reconstruction.

Mostly picked by

Updated November 2, 2026

Card for the “Training a stereo depth model” skill

Details

Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • references/spec-overrides-foundation-stereo.md: spec overrides
  • references/parameters-foundation-stereo.md: model parameters
  • references/checkpoint-inference-mappings-foundation-stereo.md: checkpoint mappings for inference

Good fit for

  • You have rectified stereo pairs and need disparity estimates
  • You rebuild a 3D scene from stereo cameras

Not for

    Tags

    • stereo
    • disparity
    • 3D reconstruction
    • TAO

    About

    You say

    “Train a FoundationStereo model on my rectified stereo pairs and check it on the evaluation set.”

    Card for the “Training a stereo depth model” skill

    Skill published by nvidia under the Apache-2.0 license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to train and run a TAO FoundationStereo stereo disparity model
    3. Review and adjust the result

    Content preview

    Files

    • BENCHMARK.md7.2 KB
    • config/skillspector-baseline.yaml1 KB
    • evals/evals.json0.8 KB
    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/checkpoint-inference-mappings-foundation-stereo.md3.9 KB
    • references/parameters-foundation-stereo.md5.7 KB
    • references/skill_info.yaml5.7 KB
    • references/spec_template_deploy.yaml2 KB
    • references/spec_template_evaluate.yaml5.8 KB
    • references/spec_template_export.yaml5.9 KB
    • references/spec_template_gen_trt_engine.yaml5.9 KB
    • references/spec_template_inference.yaml5.9 KB
    • references/spec_template_quantize.yaml5.7 KB
    • references/spec_template_train.yaml5.7 KB
    • references/spec-overrides-foundation-stereo.md4.2 KB
    • references/tao-deploy-foundation-stereo.md11.9 KB
    • references/tao-deploy-foundation-stereo.skill_info.yaml3.3 KB
    • references/troubleshooting-foundation-stereo.md2.4 KB
    • schemas/evaluate.schema.json107.6 KB
    • schemas/export.schema.json108.3 KB
    • schemas/gen_trt_engine.schema.json110.2 KB
    • schemas/inference.schema.json108.1 KB
    • schemas/manifest.json30.6 KB
    • schemas/quantize.schema.json104.4 KB
    • schemas/train.schema.json104.4 KB
    • skill-card.md4.5 KB
    • SKILL.md12.9 KB
    • skill.oms.sig9.9 KB

    Origin and licence

    Listed unmodified

    Author
    nvidia
    Source
    github.com/nvidia/skills/tree/ca116d60beafe1b4459f0ab790b7b450912c56b0/skills/tao-train-foundation-stereo
    Licence
    Apache-2.0

    Notice

    « tao-train-foundation-stereo » (nvidia, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.