Open akashAD98 opened 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
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 ??