How to resize the random noise input of SinGAN? #449
Answered
by
pjh4993
DonghweeYoon
asked this question in
How-to
-
|
Hi, Like the paper "Positional Encoding as Spatial Inductive Bias in GANs", I want to synthesize images larger than the input(G.T) image. Thank you. |
Beta Was this translation helpful? Give feedback.
Answered by
pjh4993
Dec 23, 2021
Replies: 1 comment
-
|
To resize synthesize images, you need to change size of initial noise and per layer noise You can check SinGANMSGeneratorPE's https://github.com/open-mmlab/mmgeneration/blob/master/mmgen/models/architectures/singan/positional_encoding.py to resize noise |
Beta Was this translation helpful? Give feedback.
0 replies
Answer selected by
zengyh1900
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
To resize synthesize images, you need to change size of initial noise and per layer noise
You can check SinGANMSGeneratorPE's https://github.com/open-mmlab/mmgeneration/blob/master/mmgen/models/architectures/singan/positional_encoding.py to resize noise