bug in prune-weights-ResNet18.py?

[dalistarh]

Hi,

I was looking into the ResNet18 pytorch code, and noticed the following sequence:

	if layer_name == 'fc':
		layer_type = 'F'
	else:
		layer_type = 'R'

	if layer_type == 'C':
                [...]

Unless I'm wrong, this means that none of the layers will be treated as Conv for this code.
Is this behaviour intended?

Thanks,
Dan

[csyhhu]

Hi @dalistarh ,

Yes, all conv layer is treated as res layer (without bias). For ResNet18 only contain one conv layer and the rest are res, FC. It is a simplicity when I write the code.