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 clipsTrain a skeleton action classifier on keypoint sequences
- Kind
- SkillSkill
- Pricing
- Open sourceOpen source
- Platforms
- Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, GooseClaude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- GitHub stars
- 4K4K
- Last commit
- Nov 2026Nov 2026
- License
- Apache-2.0Apache-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 actionsTrain 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.
