Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

model output is the same shape as input... #12

Open
zhangqizky opened this issue Sep 4, 2020 · 3 comments
Open

model output is the same shape as input... #12

zhangqizky opened this issue Sep 4, 2020 · 3 comments

Comments

@zhangqizky
Copy link

Hi, thanks for releasing the repo.
I want to use it to train a image enhance network ,My input are those low quality images,and output are high-quality ones, but they are the same size.
How do I modify the network so it can adjustify my work?Because, I see your net is always downscale ,and when I change the scale factor in opt yml to 1, it return a null net ....

@pkuxmq
Copy link
Owner

pkuxmq commented Sep 8, 2020

Hi, you should modify the invertible architecture in 'models/modules/Inv_arch.py'. And you may consider padding images with the latent variable to represent the lost information.

@zhangqizky
Copy link
Author

Hi, you should modify the invertible architecture in 'models/modules/Inv_arch.py'. And you may consider padding images with the latent variable to represent the lost information.

你好呀,谢谢你的回复。我后面去仔细看了你们的论文,感觉你们的论文的意思是 一套降采样-上采样流程,或者一套压缩编码解码流程对吧?也就是图像的降采样和上采样都是一起做的,如果没有按照你们的INN去降采样(h(y)去建模z得到z'),也就不可能用你们的Inverse INN去上采样恢复原始图像(从z‘从恢复出原始高频信息),请问我这样理解对吗?所以对于我这种只有已经损失信息的低画质图像,用你们的网络结构的后半部分,是无法得到原始的高清图像的吧?

@pkuxmq
Copy link
Owner

pkuxmq commented Sep 8, 2020

是的

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants