Qualcomm® AI HubAI Hub

HRNetPose

Perform accurate human pose estimation.

HRNet performs pose estimation in high‑resolution representations.

Model RepositoryHugging FaceResearch Paper

Technical Details

Model checkpoint:hrnet_posenet_FP32_state_dict
Input resolution:256x192
Number of parameters:28.5M
Model size (float):109 MB
Model size (w8a8):28 MB

Applicable Scenarios

  • Injury prevention training
  • Sports performance analysis
  • Posture recognition

Licenses

Source Model:MIT
Deployable Model:AI-HUB-MODELS-LICENSE

Supported IoT Devices

  • QCS6490 (Proxy)
  • QCS8250 (Proxy)
  • QCS8275 (Proxy)
  • QCS8550 (Proxy)
  • QCS9075 (Proxy)
  • RB3 Gen 2 (Proxy)
  • RB5 (Proxy)

Supported IoT Chipsets

  • Qualcomm® QCS6490 (Proxy)
  • Qualcomm® QCS8250 (Proxy)
  • Qualcomm® QCS8275 (Proxy)
  • Qualcomm® QCS8550 (Proxy)
  • Qualcomm® QCS9075 (Proxy)

Related Models

See all models
View details for the LiteHRNet model.

LiteHRNet

Human pose estimation.

Looking for more? See models created by industry leaders.

Discover Model Makers