HRNET-Posenet: Pose Estimation

HRNet-PoseNet is a pose estimation model based on the HRNet (High-Resolution Network) architecture, specifically designed for human keypoint detection and pose estimation tasks. HRNet-PoseNet maintains high-resolution feature representations throughout the network, while processing features in parallel across multiple resolutions to capture both global and local information of the human body. This design enables high-precision keypoint localization, retaining high-quality pose estimation even in complex scenarios. HRNet-PoseNet performs exceptionally well in various pose estimation tasks and is widely applied in fields like sports analysis, action recognition, virtual reality, and human-computer interaction, providing robust support for real-time and precise pose estimation.

Source model

  • Input shape: 256x192
  • Number of parameters: 28.5M
  • Model size: 108.94M
  • Output shape: 1x17x64x48

Source model repository: HRNET-Posenet

Performance Reference

Please search model by model name in Model Farm

Inference & Model Conversion

Please search model by model name in Model Farm

License

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support