Terminology - AsyDynamics/keras-yolo2 GitHub Wiki
Anchor box
YOLOv2 divides the entire image into 13X13 grid cells, next places 5 anchor boxes at each location and finally predicts corrections on these anchor boxes. YOLOv2 makes 5 predictions corresponding to corrections on location of center (x and y), height and width, and finally the intersection over union (IOU) between predicted bounding boxes and ground truth boxes. A unique feature of YOLOv2 is that all the predictions are have magnitude less than 1, as a result the chance of one type of cost dominating the optimization is less likely. A unique feature of YOLOv2 is that the anchor boxes are designed specifically for the given dataset using K-means clustering. Unlike other anchor boxes (or prior) based methods, like Single Shot Detection, YOLOv2 does not assume the aspect ratios or shapes of the boxes. As a result, the YOLOv2 in general has lower localization loss and has higher intersection over union (IOU) between the target and network prediction.