Skip to main content

YOLOv8s Pose Small 320x320 INT8

A YOLOv8s pose estimation model optimized for 320x320 resolution, detecting people and their body keypoints.

Supported processors

  • SL2619

YOLOv8s Pose Small 320x320

Model Overview​

A YOLOv8s pose estimation model optimized for 320x320 resolution, detecting people and their body keypoints.

The YOLOv8s Pose 320x320 model is developed and optimized for the Synaptics Astra® SL2610-Series processors Torq NPU.

Model Features​

  • Model Type: Pose Estimation
  • Input Size: 320x320
  • Quantization: INT8

Deployment​

The compiled model file is available for download on Huggingface at Synaptics/yolov8-pose-small-320-int8-torq.

Usage Tutorial​

A usage example is provided at Torq Examples / pose_estimation. Check out the README for instructions.

License​

Both the source model and the compiled model for on-device deployment are licensed under AGPL-3.0.

Learn More​

Related models