WangFeng
WangFeng
> we can wait for pytoch1.11(stable) to test this pr, if you use the newest NGC image, maybe the pr work. my dev environment : cuda11.5 pytorch1.11 ,nvcr.io/nvidia/pytorch:21.12-py3 from NGC...
In practical applications,I think autoanchors are a huge defect, which will not be able to detect a lot of actual data
> Hey there! 👋 Thanks for sharing your thoughts about the autoanchors feature in YOLOv8. We're always striving to improve, and feedback like yours is crucial. > > Autoanchors were...
> Data augmentation technology cannot meet our needs. I believe it would be better to determine the size of anchor boxes with every class , rather than for every annotated...
I have also encountered such a problem,yolov80bb seems insensitive to angles。
> > > I have also encountered such a problem,yolov80bb seems insensitive to angles。 > > > @Wangfeng2394 > > > Especially for square rotational objects, right? In my case,...
> @Wangfeng2394 Hi, I have encountered the same issue in this situation. Have you found a solution to this problem? thx qq id or wechat id？
> @glenn-jocher Thanks for your reply, but in the loss function, I observed that it contained box_loss, cls_loss and dfl_loss, no rot. Although it's impolite to say this, I think...
hi，Do you know what are you saying？ what‘s loss function in yolov8 obb？“probiou loss” right？The probiou loss including boxloss and angle loss, so where is **individual** rotation_loss？？？