原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
The IoU loss becomes 1 when the two bounding boxes do not overlap, which means that there will be no gradient information when running backpropagation. Now we can put together the classification and the localization loss to compute the overall loss: (50.17) where the indicator function 𝟙(yi = 0) sets to zero the location loss for the bounding boxes that do not overlap with any
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c050b.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8