| --- | |
| library_name: mmpose | |
|  | |
| RTMPose introduces a real-time, top-down human pose estimation framework that jointly optimizes model architecture and training strategy to achieve high accuracy under strict latency constraints. | |
| Original paper: [RTMPose: Real-Time Multi-Person Pose Estimation Based on MMPose](https://arxiv.org/abs/2303.07399) | |
| # RTMPose-M | |
| This model uses the RTMPose-M variant, which strikes a balance between accuracy and inference speed through efficient backbone design and optimized keypoint heads. It is well suited for real-time pose estimation in applications such as human–computer interaction, sports analytics, video surveillance, and edge AI systems. | |
| Model Configuration: | |
| - Reference implementation: [Official MMPose RTMPose models](https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose) | |
| - Original Weight: [rtmpose-m_simcc-aic-coco_pt-aic-coco_420e-256x192](https://download.openmmlab.com/mmpose/v1/projects/rtmposev1/rtmpose-m_simcc-aic-coco_pt-aic-coco_420e-256x192-63eb25f7_20230126.pth) | |
| - Resolution: 3x256x192 | |
| - Support Cooper version: | |
| - Cooper SDK: [2.5.2] | |
| - Cooper Foundry: [2.2] | |
| | Model | Device | Model Link | | |
| | :-----: | :-----: | :-----: | | |
| | RTMPose-m | N1-655 | [Model_Link](https://huggingface.co/Ambarella/RTMPose/blob/main/n1-655_rtmpose_m.bin) | | |
| | RTMPose-m | CV72 | [Model_Link](https://huggingface.co/Ambarella/RTMPose/blob/main/cv72_rtmpose_m.bin) | | |
| | RTMPose-m | CV75 | [Model_Link](https://huggingface.co/Ambarella/RTMPose/blob/main/cv75_rtmpose_m.bin) | |