Zhongdao / Towards-Realtime-MOT

Joint Detection and Embedding for fast multi-object tracking
MIT License
2.4k stars 539 forks source link

sample integration #213

Open partus opened 3 years ago

partus commented 3 years ago

This script illustrates how to run inference with this model in real time on a video stream. The video stream is read using OpenCV.

I think it would be a good example for somebody who would like to integrate the model in his inference stack.