RTMPose_Body2d: Pose Estimation

RTMPose_Body2d is a real-time 2D human pose estimation model focused on fast and accurate detection of body keypoints such as joints. It uses an efficient neural network architecture designed to minimize computational resources while enabling real-time localization of human keypoints in video streams or images. RTMPose_Body2d is suitable for applications like action recognition, sports analytics, virtual reality, and human-computer interaction. Its lightweight design makes it ideal for deployment on edge devices and mobile platforms where low latency and high responsiveness are essential.

Source model

  • Input shape: 1x3x256x192
  • Number of paramaters: 38 MB
  • Model size: 69 MB
  • Output shape: 1x133x384,1x133x512

Source model repository: RTMPose_Body2d

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