search

aitorzip / PyTorch-CycleGAN

A clean and readable Pytorch implementation of CycleGAN
https://arxiv.org/abs/1703.10593
GNU General Public License v3.0
1.22k stars 283 forks source link

Is the comment for Down sampling and Up sampling switched in the Generator Class? #2

Open inkplay opened 6 years ago

inkplay commented 6 years ago

In = 64 out = in*2 <-- so its 128 We will loop this twice and reassign "out" to "in" so..

in = out <-- in = 128 `out=in * 2'< -- out = 256 The output is consistently getting bigger and bigger why is this labeled #DownSampling?

patrick-han commented 5 years ago

I'm also curious about this, although I think this is how its implemented in the original CycleGAN as well

zhangluustb commented 5 years ago

in and out means channels' numer,not the image size