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

How can I get ISP model for your degrade model? #41

Open
yichuangzhang opened this issue Sep 12, 2022 · 4 comments
Open

How can I get ISP model for your degrade model? #41

yichuangzhang opened this issue Sep 12, 2022 · 4 comments

Comments

@yichuangzhang
Copy link

No description provided.

@sunyclj
Copy link

sunyclj commented Oct 19, 2022

@yichuangzhang I have the same problem.Please,have you found the corresponding code?

@jarricd
Copy link

jarricd commented Oct 20, 2022

Read the paper. They cite a model in the paper.
https://github.com/timothybrooks/unprocessing - that's the repository for the reverse ISP model. You'll have to train in on your own.

@en1ero
Copy link

en1ero commented Oct 6, 2023

I don't think it is a trainable ISP model what you are looking for. I assume they just organized a series of image processing/unprocessing steps found in unprocessing into PyTorch classes (instead of Tensorflow). These classes inherit from nn.Module in PyTorch and are grouped within a isp_model class, allowing/forcing them to use the forward() method inside the degradation workflow.

So i guess this just enables PyTorch's functionalities for image processing.

@EugeneCh1a
Copy link

@cszn ,I have same problem in isp model

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

5 participants