search

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

I want to detect small & big objects using YOLOV4-CSP , what changes should i need to do ?? #7627

Open akashAD98 opened 3 years ago

akashAD98 commented 3 years ago

In repository @AlexeyAB mentioned for detecting small & large objects use this https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/yolov4-custom.cfg custom.cfg file

but i think we can't do the same changes in YOLOV4-CSP.cfg right ??

I want to detect small & big objects using YOLOV4-CSP.cfg what are the changes I need to do in , activation functions, loss function, also which data augmentation technique will work better for detecting small+big objects ??

ekesdf commented 3 years ago

**for training for both small and large objects use modified models:

Full-model: 5 yolo layers: https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/yolov3_5l.cfg Tiny-model: 3 yolo layers: https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/yolov4-tiny_3l.cfg YOLOv4: 3 yolo layers: https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/yolov4-custom.cfg**

read the Readme.md under the point improving object detction