Use the NGC CLI to download:
Copied!
Model
Pose classification network to classify poses of people from their skeletons.
Use the NGC CLI to download:
Copied!
| Field | Response |
|---|---|
| Intended Application(s) & Domain(s): | Classifies human body poses. |
| Model Type: | Pose Classification |
| Intended Users: | Developers working in industrial, personal health, and smart spaces applications. |
| Output: | Category Label(s) |
| Describe how the model works: | Classifies poses of people from their skeletons: sitting down, getting up, sitting, standing, walking, jumping |
| Technical Limitations: | PoseClassificationNet does not give good results for very crowded scenes, especially if detecting the pose for small-scale people in the image. PoseClassificationNet may also have difficulty estimating poses of people who are occluded by other objects or persons or in environments where there is no distinction between the person and the background. |
| Verified to have met prescribed NVIDIA standards: | Yes |
| Performance Metrics: | Accuracy, Precision, Recall |
| Potential Known Risks: | Model may fail to classify correct pose. |
| Licensing: | https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/ |