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 CPU without 2 much optimization effort is 500 ms per image approximately on my configuration. https://funvision.blogspot.com
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
https://funvision.blogspot.com
https://opencv.org/
https://pjreddie.com/darknet/yolo/