mlpConv:
add some 1*1 conv(ReLU) after the conv, the n can be seen as the number of 1*1 conv(ReLU) in mlpConv
------------------------------
global average pooling without fc layer
the number of feature maps before loss-function(eg. softmaxwithloss) must equal to the category's ( in the classification task). and each feature map after ave pooling feed to the loss func.
----------------------Reference--------------------------
[1] Min Lin, Qiang Chen, Shuicheng Yan. Network In Network