卷积神经网络闲扯-------也许并没有LUAN用的LRN

alexnet当中提出，不过VGGNet当中被视为是没啥LUAN用的~

闲来无事也学习下（感性理解下）：

tensorflow函数：

tf.nn.lrn(input,depth_radius=None,bias=None,alpha=None,beta=None,name=None)

The 4-D input tensor is treated as a 3-D array of 1-D vectors (along the last dimension), and each vector is normalized independently. Within a given vector, each component is divided by the weighted, squared sum of inputs within depth_radius. In detail, 
sqr_