jamessmith123456

big brother, i met the same problem. How you solve it? Just adjust the learning rate ? My loss_box and loss_cls both are 0.00000....

啊，这个是因为数据集制作错误了；图片的那个ground-truth box坐标，有的超出了图片边界，比如为-1；或者是右下角的点的横坐标小于等于左上角的横坐标(按道理应该是大于才对)；我记得有个地方是可以改源码的，就可以避免这个错误，你查一下； Emmm，dataset is wrong. Especially the cordiniate of ground-truth box. For example: x2 must larger than x1.(something like that...).  if x2==x1, then width = (x2-x1)=0;  a/(x2-x1)=NaN!!! ------------------ 原始邮件 ------------------ 发件人: "CRmost"

感觉990张确实有点少... ------------------ 原始邮件 ------------------ 发件人: "CRmost"

> Hello, I am also studying this project. If you don't recommend it, please contact me, thank you. > > [[email protected]](mailto:[email protected]) Have you find the solution ? Please share...Thanks...

i got it too..Segmentation fault(core dumped). Have you solve it?