Monday, April 27, 2020

YOLOv3 Inference Server for Intel Movidius


In a previous post, I went over the steps to get the "Intel Neural Compute Stick 2" working on a Raspberry Pi. It handles the conversion of the Darknet YOLOv3 model, trained on a COCO dataset, to OpenVINO IR format.





As a demonstration of that, I made a small Pyhton Flask web service that is suitable to run on the Raspberry Pi. Using a basic web UI you can PUSH images to it to do object detection and classification. 

While processing some validation images from the COCO dataset, the observed inference speed is about 400ms, do add another 150 ms to post-process the results. This makes about 550 ms for the full object detection, which sounds pretty acceptable to me. Given it runs on a Raspberry Pi4 and I made the postprocessing code to be readable, not to have optimal performance. 

The full source code is available for download on github 
https://github.com/brunokeymolen/movidius-inference-server







1 comment:

  1. But credit cards require no loading or reloading, making it easier to lose observe of cash spent. While gambling firms face related dangers, they’re not identical. Depending on the character of your gamers, video games, and payouts, 바카라 사이트 you may have|you may have|you would possibly have} larger or lower dangers across different danger elements. As a end result, it’s important to evaluate dangers on a case-by-case basis.

    ReplyDelete