Percetual Loss

[nicksunyang]

for midx, mod in enumerate(self.vgg):
es = mod(es)

for i,mod in enumerate(vgg):
... if i == 3:
... print(mod)
...
ReLU(inplace=True)

I can't understand this，why?

[griegler]

Are you refering to this part of the code? What do you not understand?

[nicksunyang]

Yeah，I suppose mod only represents one layer, eg. i= 3 mod is ReLU.

[griegler]

Yes, you can verify via print(torchvision.models.vgg19().features).