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

The ability of the model to learn about color information #104

Open
SDD2021-car opened this issue Oct 25, 2024 · 0 comments
Open

The ability of the model to learn about color information #104

SDD2021-car opened this issue Oct 25, 2024 · 0 comments

Comments

@SDD2021-car
Copy link

Hello, I appreciate you provided your code and instruction for implementing colorization task based on your paper. I have a few questions about model that I'd like to ask. I have tried palette in my work for image translaiton and almost all hyperparameters are the same as yours. The results showed that the model roughly learned the texture information of the original image but almost no color information from the original image was learned. When I set the linear end to be smaller, the results can be the seen almost clearly but their colors are incorrect. When I set the linear end to be larger,the excessive color bias makes the image unclear. I would like to ask what might have caused this? Thank you very much.

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

1 participant