几篇文章保存下:
1.https://blog.csdn.net/guleileo/article/details/80581858
(转于https://blog.csdn.net/App_12062011/article/details/77554288)
2.https://blog.csdn.net/qq_28123095/article/details/80052308
https://zhuanlan.zhihu.com/p/25236464
3.https://www.cnblogs.com/fariver/p/7446921.html
4.https://blog.csdn.net/jesse_mx/article/details/53925356
5.超级好的使用教程;https://github.com/AlexeyAB/darknet#how-to-train-to-detect-your-custom-objects
6.https://www.jianshu.com/p/c1a009385f59
7.https://blog.csdn.net/u014380165/article/details/80202337
论文中提到YOLOv3在AP50和小目标上表现都不错,但AP75表现就比较乏力。说明随着IoU的升高,YOLOv3预测的bbox不能很好的与GT相重叠。
9.https://github.com/ayooshkathuria/pytorch-yolo-v3
以及从该github上扩展出来的
检测:https://blog.paperspace.com/how-to-implement-a-yolo-object-detector-in-pytorch/