Jarvis
Jarvis
And I found that if there are some overlapping points(not completely overlapping), the intersection area is wrong.
Thanks for your quick reply! I will try this loss to train my network. By the way, I implemented a differential IoU loss in python before. Although it is accurate,...
The enclosing area in this repo is not convex hull area, therefore the results are different from standard package such as Shapely. I think you could use https://github.com/JarvisUSTC/Differential-Rotated-IoU-Loss for calculating...
我设成1时为什么第一次结束不停。。。
yes, I just find diff-iou from other's github repo.