Wardy
Collection
Jetson-based on-device AI for home safety: person tracking, identity, pose, fall and hazard detection, plus the hazard-object dataset. • 6 items • Updated • 1
Wardy M-03 pose estimation
This repository pins the RTMPose-T ONNX artifact used by Wardy M-03 for COCO-17 body keypoint estimation.
Artifact
| Runtime version | File |
|---|---|
openmmlab-rtmpose-t-20230504 |
model.onnx |
manifest.json contains the SHA-256 digest verified by the Wardy model manager.
Provenance and license
The model artifact was published by OpenMMLab as part of RTMPose and is redistributed under Apache-2.0. Wardy does not claim original model authorship.
Runtime boundary
Wardy downloads the pinned ONNX artifact, verifies its digest, and runs pose inference locally. Device-specific TensorRT engines are generated on the target Jetson and are not distributed here.
Limitations
Pose accuracy depends on person visibility, scale, lighting, occlusion, and the preceding person detector. Pose output alone does not determine a fall.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support