Which characteristic for which structure - cfg files

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

Which characteristic for which structure - cfg files #3976

Open YKritet opened 4 years ago

YKritet commented 4 years ago

Hi Alexey,

I decided to keep the ratio aspect for my text images using the -letter_box flag and I wanted to ask about the differences in performance (not the mAP necessarily, more like the specific characteristics) between 4 cfg files :

   - yolov3_5l.cfg 
   - yolov3-spp.cfg
   - yolov3.cfg
   - darknet53.cfg

Thank you very much

AlexeyAB commented 4 years ago

@YKritet Hi,

yolov3_5l.cfg - optimized for small and big objects
yolov3-spp.cfg - increased +3 mAP mainly for medium and large objects
yolov3.cfg - default Yolov3 model
darknet53.cfg - is a Classifier backbone which is used for all of these Detectors: yolov3_5l.cfg , yolov3-spp.cfg, yolov3.cfg

H-YunHui commented 4 years ago

@AlexeyAB as you say above that, the yolov3_5l.cfg - optimized for small and big objects, the yolov3-spp.cfg - mainly for medium and large objects. I think whether the big objects, medium objects and small objects all improved that join SPP in yolov3_5l.cfg ? have you try it?