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
Source Model: APACHE-2.0
Deployable Model: APLUX-MODEL-FARM-LICENSE