L1，L2以及Smooth L1是深度学习中常见的3种损失函数，这3个损失函数有各自的优缺点和适用场景。
https://blog.csdn.net/vv___/article/details/116396475?spm=1001.2101.3001.6650.1&utm_medium=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7Edefault-1.no_search_link&depth_1-utm_source=distribute.pc_relevant.none-task-blog-2%7Edefault%7ECTRLIST%7Edefault-1.no_search_link