Why channel drop?

[apple2373]

I was checking other repository (before checking this one), and then found a strange channel drop trick.
huggingface/pytorch-pretrained-BigGAN#9

I can see you also use it here:

BigGAN-PyTorch/BigGANdeep.py

Lines 54 to 56 in ba3d057

	# Drop channels in x if necessary
	if self.in_channels != self.out_channels:
	x = x[:, :self.out_channels]

Could you explain why do you do this? I think it's strange to train with lager channels more than necessary and drop at inference time. Does this trick somehow help for training?

[ajbrock]

The channel drops in G's blocks are part of the BigGAN-deep architecture, as described in the paper. The channel drop at the output layer you see in Thom's TFHub port (from 128->3) is an implementation detail for taking advantage of TPU accelerators.