Dear Mentor,
I found that in yolo_head() function, the prediction of bounding box on width and height is unscaled from log-scale to linear scale, and box_wh is unscaled relative to anchor boxes.
- box_wh = K.exp(feats[…, 2:4])
- box_wh = box_wh * anchors_tensor
Does it mean the width and height of a bounding box is scaled with respect to width and height of an anchor box , and applying log scaling?
log(width of bounding box / width of anchor box)
log(height of bounding box / height of anchor box)
Then, the log-scaled width and height are annotated in the truth label in the training set?
Thank you.