domains / families / data / tao-train-action-recognition
tao-train-action-recognition
separate
Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for
When to use
- train action recognition
- video action classification
- RGB + optical flow action model
- TAO ActionRecognition
- evaluate action recognition
- export action recognition
- inference action recognition
When not to use
- deploy flows
- non-action recognition tasks
Skill page
Source
| Repository | Path |
|---|
| NVIDIA/skills | skills/tao-train-action-recognition/SKILL.md |