ONNX-Mobile-Human-Pose-3D icon indicating copy to clipboard operation
ONNX-Mobile-Human-Pose-3D copied to clipboard

Published 20 hours ago • verified publisher icon ibaiGorordo

Inference problem

Open SienChen1997 opened this issue 3 years ago • 2 comments

Hi,thanks for the great work. I follow your Readme and download the required models including Mobile Human Pose and YOLOv5s, and below is the inference result and which is not as accurate as i expect. The input image size is 512*512, and i have no idea to choose the proper detection model(different resolution),so i just tried it all,which not improved the result.Could you point out what the problem is?

output

SienChen1997 avatar Oct 12 '21 12:10 SienChen1997

I am sorry for the delay. I have not forgotten, but I am planning to release an inference script for a more accurate model soon that might fix your issue. I have been getting distracted with other projects, but I want to get it working by the end of this week.

ibaiGorordo avatar Oct 25 '21 01:10 ibaiGorordo

@SienChen1997 @ibaiGorordo I am trying model on live / image data, and keypoints quality is like above only. Any suggestion how i can better results.

chandelarvind avatar Jan 29 '22 18:01 chandelarvind