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

PalateKit

Sign in
Menu

Request a resource

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

0 / 280

A page, a video or an image online.

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.

Pose classification with ST-GCN v1.0.0

Use this resource to train a TAO pose classifier on keypoint sequences

New

  • 467 downloads
  • 121 likes
  • 107 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install skeleton-pose-action-classification

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 decides whether dataset conversion is needed (only for raw input), writes the training and evaluation specs, then runs the cycle through inference. It follows the skeleton keypoint sequence format. You get a valid spec and an exported model.

Mostly picked by

Updated November 2, 2026

Card for the “Pose classification with ST-GCN” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • references/spec_template_dataset_convert.yaml: dataset conversion
  • references/spec_template_train.yaml: training
  • schemas/inference.schema.json: inference schema

Good fit for

  • You recognize actions from skeletons extracted from video
  • You have keypoint sequences and want a classifier

Not for

    Tags

    • pose
    • ST-GCN
    • skeleton
    • classification

    About

    You say

    “Train an ST-GCN on my keypoint sequences to tell walking, sitting and falling apart.”

    Card for the “Pose classification with ST-GCN” 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 a TAO pose classifier on keypoint sequences
    3. Review and adjust the result

    Content preview

    Files

    • BENCHMARK.md7.1 KB
    • config/skillspector-baseline.yaml1 KB
    • evals/evals.json0.9 KB
    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/skill_info.yaml4.6 KB
    • references/spec_template_dataset_convert.yaml0.5 KB
    • references/spec_template_evaluate.yaml1.5 KB
    • references/spec_template_export.yaml1.4 KB
    • references/spec_template_inference.yaml1.5 KB
    • references/spec_template_train.yaml1.3 KB
    • schemas/evaluate.schema.json26 KB
    • schemas/export.schema.json23.8 KB
    • schemas/inference.schema.json26.2 KB
    • schemas/manifest.json6.5 KB
    • schemas/train.schema.json22.2 KB
    • skill-card.md4.6 KB
    • SKILL.md15.3 KB
    • skill.oms.sig7.4 KB

    Origin and licence

    Listed unmodified

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

    Notice

    « tao-train-pose-classification » (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.