Support training for 5 yolo layers?

[ycxia]

The project https://github.com/AlexeyAB/darknet/blob/master/cfg/yolov3_5l.cfg has supported 5 yolo layers. Does your project support training for 5 yolo layers?

[eric612]

Not yet , but , however , As I see it is compatible with this project , your can try it . Contribution is welcome

The link was invalid , but It's is interesting , what application will use it , a small object detection on birdview ?

[ycxia]

@eric612 you can find yolov3-5l.cfg file of 5 yolo layers in AlexeyAB's github. Additional 2 yolo layers are used to detect small object. the 2 layers anchor boxs: 4,4 5,5 6,6 7,7 8,8 9,9

[vim5818]

@eric612 Can you please mention in which file and how exactly to add the layers. I am new to this. Request your support kindly. Thank you.