Dear research community?

How are the anchor sizes defined in the cfg files of YOLOv3 and YOLOv4 object detectors? For example from the Yolov4 cfg file

anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401

During training time do these value get overridden somehow? to the best of my knowledge, the main CNN code simply read these numbers and used them for Non Max suppression.

Any insight to the details of defining the anchors would be greatly appreciated.

With best,

Azmyin

More Azmyin Md Kamal's questions See All
Similar questions and discussions