Skip to content

Tao train action recognition vs Tao train pose classification

Tao train action recognition is an open-source agent skill for computer vision. Tao train pose classification is an open-source agent skill for computer vision.

  • Tao train action recognition is best for train an action recognition model on labelled video clips.
  • Tao train pose classification is best for train a skeleton action classifier on keypoint sequences.
What it is
Tao train action recognition is an open-source agent skill for computer vision.
Tao train pose classification is an open-source agent skill for computer vision.
Best for
Train an action recognition model on labelled video clips
Train a skeleton action classifier on keypoint sequences
Kind
Skill
Skill
Pricing
Open source
Open source
Platforms
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
GitHub stars
4K
4K
Last commit
Nov 2026
Nov 2026
License
Apache-2.0
Apache-2.0
Open source
Good for
Train an action recognition model on labelled video clips; Evaluate a trained action model on a held-out test set; Run inference on new clips to classify actions
Train a skeleton action classifier on keypoint sequences; Evaluate a trained pose classification checkpoint on validation data; Run inference on new keypoint sequences and save the results

What Tao train action recognition does

  • Docker-based launch

    Runs train, evaluate, inference and export through the TAO toolkit container with mounted data, specs and results folders.

  • Input type selection

    Covers RGB, optical flow and joint multi-stream inputs and the frame-length settings for each.

  • Dataset and spec setup

    Maps required data sources and label maps for each action and warns about tar archive paths.

  • Checkpoint handling

    Explains selecting concrete epoch checkpoints for evaluation, inference, export and resume training.

  • Evaluation metrics

    Lists training monitoring metrics and evaluation accuracy measures used to compare runs.

  • AutoML routing

    Describes when training is routed through an AutoML workflow and when direct training is used.

What Tao train pose classification does

  • Docker-based CLI actions

    Runs dataset conversion, training, evaluation, inference and export through a containerized pose classification CLI.

  • Dataset conversion step

    Converts raw DeepStream BodyPose JSON into the train and validation files, and is skipped for preconverted data.

  • Checkpoint handling

    Selects specific saved checkpoints for evaluation, export, inference or resuming training.

  • Spec override templates

    Provides example spec overrides for dataset paths, class labels, graph layout and training epochs.

  • ONNX export

    Exports a trained model to an ONNX file at a path set in the spec.

  • Single-GPU training guidance

    Describes single-node, single-GPU training setup and the expected hardware.

Tao train action recognition vs Tao train pose classification: questions

Is Tao train action recognition or Tao train pose classification cheaper?

Both are open source. Compare current plans on each official site.

What is the difference between Tao train action recognition and Tao train pose classification?

Tao train action recognition is an open-source agent skill for computer vision. Tao train pose classification is an open-source agent skill for computer vision.

Keep comparing