I have tested some platforms and have also been involved in packaging Docker images. Now, some popular models can be directly pulled and deployed with one click via Docker. I have created a table listing the models that are currently available for direct deployment – you can refer to it below, or directly .visit the platform：
If running a pose estimation project only requires running it on the device:To directly obtain the project, you can click here to go to the platform.
If running a pose estimation project only requires running it on the device:
Code:
sudo docker run --rm \ --name cm5-hailo-yolov8m-pose \ --privileged \ --net=host \ -e PYTHONUNBUFFERED=1 \ --device /dev/hailo0:/dev/hailo0 \ -v /usr/lib/libhailort.so.4.23.0:/usr/lib/libhailort.so.4.23.0:ro \ -v /usr/lib/libhailort.so:/usr/lib/libhailort.so:ro \ ghcr.io/seeed-projects/recomputer-r20-cv/yolov8_pose:latest \ python web_detection.py --model_path model/yolov8m_pose.hef --video_path video/test.mp4Statistics: Posted by doubleleft — Thu Aug 13, 2026 3:12 am — Replies 0 — Views 35
![[QLD, NSW, VIC] Samsung 65](http://files.ozbargain.com.au/n/31/978831l.jpg?h=8d64f0c6)
/pic7955059.jpg)
