close

 

  1. Download yolov4.weights file 245 MB: yolov4.weights (Google-drive mirror yolov4.weights )
  2. yolov4-tiny.cfg - 40.2% mAP@0.5 - 371(1080Ti) FPS / 330(RTX2070) FPS - 6.9 BFlops - 23.1 MB: yolov4-tiny.weights
  3. Download Darknet zip-archive with the latest commit and uncompress it: master.zip

Go to darknet-master->build->Release

Copy darknet.exe and paste it in the folder of darknet-master\build\darknet\x64

Create a new file "darknet_yolo_v4.cmd" from another file called "darknet_yolo_v3.cmd" 

Modify the contents in darknet_yolo_v4.cmd as follows:

darknet.exe detector test cfg/coco.data cfg/yolov4.cfg weights/yolov4.weights -i 0 -thresh 0.25 dog.jpg -ext_output

One thing should done before you start the cmd file is that you should download pretrained weight files and put them in wights folder 

darknet.exe detector test cfg/coco.data cfg/yolov4-tiny.cfg weights/yolov4-tiny.weights

 

 

arrow
arrow
    全站熱搜

    me1237guy 發表在 痞客邦 留言(0) 人氣()