model output is the same shape as input...

[zhangqizky]

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]

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]

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]

是的