PyTorch provides 2 kinds of Softmax class. The one is applying softmax along a certain dimension. The other is do softmax on a spatial matrix sized in B, C, H, W.
But it seems like some problems existing in Softmax2d. : (
转载于:https://www.cnblogs.com/hizhaolei/p/10641459.html
![[AHOI2009]最小割（最大流+tarjan）](http://pic.xiahunao.cn/[AHOI2009]最小割（最大流+tarjan）)
