Reason for multiplication and addition after generating outputs

aitorzip / PyTorch-CycleGAN

A clean and readable Pytorch implementation of CycleGAN

https://arxiv.org/abs/1703.10593

GNU General Public License v3.0

1.19k stars 283 forks source link

Reason for multiplication and addition after generating outputs #16

Closed patrick-han closed 5 years ago

patrick-han commented 5 years ago

What is the reason for adding 1 and multiplying by 0.5 here when generating our "fake" outputs. Is this to reverse the effects of transforms.Normalize()?

Mahlagha commented 5 years ago

Right, it is equivalent to multiplying by sigma, and then adding the mean.