AlexeyAB / darknet

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )
http://pjreddie.com/darknet/
Other
21.65k stars 7.96k forks source link

calculate precision and recall for different con_thresh #6180

Open 123liluky opened 4 years ago

123liluky commented 4 years ago

Hi, I have few questions: 1、I want to calculate precision and recall with different con_thresh. Then, I can determine the value of con_thresh for actual use. Which command can I use?
2、How can I set the value of nms_thresh when testing a video using command below: ./darknet detector demo cfg/coco.data cfg/yolov4.cfg yolov4.weights test.mp4 -out_filename res.avi -thresh 0.5 3、I want to have smaller yolov4-tiny model. I have change all filters in convolutional layers into a half. What else can I do? Looking forward to your suggestions, Thank you.

lsd1994 commented 4 years ago

darknet.exe detector map xx.data xx.cfg xx.weights -thresh con_thresh

oubaid2 commented 3 years ago

i tried your command and no results or plots did appear on my colab.notebook