Opencv 4 DNN, People detection CPU performance with yolo 2 tiny model
I am still working on a tutorial on how to simply run yolo and others model in opencv 4. I try to do as simple as possible. Not like a general sample in Opencv. Differently, simply, and described as much as possible.
Some technical specifications video
Testing opencv 4.0 DNN with yolo tiny 2 model on people detection in a mall. Pure CPU, I7 (4 cores), running by the following command under Windows 10. Performance for the CPU without 2 much optimization effort is 500 ms per image approximately on my configuration. Let me know if there is some problem with the parameters.
testOpecv.exe --config=C:\darknet-master\cfg\yolov2-tiny.cfg
--model=C:\darknet-master\weights\yolov2-tiny.weights
--classes=C:\opencv32\darknet-master\data\coco.names
--width=616 --height=616 --scale=0.00192 --rgb
Sources:
Thank you for a great job