Issue with dimension in last output of Discriminator structure in CycleGan notebook. about deep-learning-v2-pytorch HOT 3 CLOSED

Is there a reason for these two steps? Why not go for the single step of creating the final layer with a kernel size of 8, padding 0 and actually have it output just one value?

from deep-learning-v2-pytorch.

@christian-steinmeyer On one particular solution by Ram K in the Udacity Q&A platform I managed to locate an answer to why this is done.

He links to this [explanation] (junyanz/pytorch-CycleGAN-and-pix2pix#39) of which my understanding is that this allows the discriminator to more easily identify which specific patch in the image (i.e. which of the 7x7 cells) looks fake/real, which can then be traced back (via the receptive field of CNNs) through the network. In order to calculate the overall Discriminator Loss, this 7x7 output of the Discriminator is then averaged (since they are all indications of whether a given patch is "real" or not, and therefore the average should indicate whether the whole image is "real" (or not).

from deep-learning-v2-pytorch.

Ah, you're right! Thank you for this feedback. To be more specific, we are looking at one value (the mean of those output values) and using that single value to calculate the real and fake loss, later

from deep-learning-v2-pytorch.