Accelerated by another 5% using FP16/32 Batch-norm for Tensor Cores.

AlexeyAB

2018-04-16 9bae70b22549b68f5cdeece8b6c3b3de00c22714

1
2
3
#rm test_dnn_out.avi
 
./darknet detector demo ./cfg/coco.data ./cfg/yolov3.cfg ./yolov3.weightss rtsp://admin:admin12345@192.168.0.228:554 -i 0 -thresh 0.25