Question on CondensingConv from layers.py

[lizhenstat]

Hi, thanks for your work, I have one question on the function CondensingConv from layers.py https://github.com/ShichenLiu/CondenseNet/blob/master/layers.py#165

self.in_channels = model.conv.in_channels * model.groups // model.condense_factor

The input channel in a given convolutional layer in the paper is floor(R/C) why is it different here?

Thanks in advance

[lizhenstat]

I finally figure out that: model.conv.in_channels // model.condense_factor --> calculate the number of feature map to each group model.conv.in_channels // model.condense_factor * model.groups --> calculate the number of feature map to all the groups