What's the meaning of w and h in your loss function?
Opened this issue · 1 comments
XiaXuehai commented
When you calculate loss, the code about tw
and th
like this:
# Width and height
tw[b, best_n, gj, gi] = math.log(gw/anchors[best_n][0] + 1e-16)
th[b, best_n, gj, gi] = math.log(gh/anchors[best_n][1] + 1e-16)
I don't understand why you use log
,and in the paper, the loss function about w and h is
Can you explain it ? THX.
XiaXuehai commented
I have known it.