I have one question on cifar/mixnet.py
Line 73- Line 79, the convolution operation order is BN --> conv(1,1) --> relu
Usually in conv (resnet version 2), the order is bn-relu-conv (the same as other convolutional layer in the code)
However, in transition layer, why is there a difference?
Thanks in advance
I have one question on cifar/mixnet.py
Line 73- Line 79, the convolution operation order is BN --> conv(1,1) --> relu
Usually in conv (resnet version 2), the order is bn-relu-conv (the same as other convolutional layer in the code)
However, in transition layer, why is there a difference?
Thanks in advance