About the network inflation factors
hex0102 opened this issue · comments
As I find out in the code, layers in VGG network, ResNet have an inflation factor.
Could someone please help clarify this?
Why need to inflate the network? Is there a reference to address this question?
I also checked the tensorflow repo for the BNN network, there's no inflation factor.
you don't have to inflate the network but it improves accuracy. WRPN paper: https://arxiv.org/abs/1709.01134
@itayhubara Thank you very much for your quick reply and help. The reference is really useful.
I'm checking out this paper.
@itayhubara It seems like that for VGG_CIFAR10, the attained accuracy for the inflated network doesn't improve very much (limited to 1%). Are there any reasons to explain this?
VGG_CIFAR10 is a very large network to begin with...