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

More detalization. #6

Open
gummybear opened this issue Oct 3, 2018 · 4 comments
Open

More detalization. #6

gummybear opened this issue Oct 3, 2018 · 4 comments

Comments

@gummybear
Copy link

Can you help me, which parameter in the code changes the detail of the resulting image. Suppose that by reducing the productivity.

In pix2pix project.

@zaidalyafeai
Copy link
Owner

It is not trivial to increase the resolutions of the generated images. You would have to train on high res images but the model might be big and you wont be able to run in the browser.

@gummybear
Copy link
Author

It's a pity. )

@gummybear
Copy link
Author

А month later... )

Do you have a big model for pix2pix/scene_model? More than 50 MB. I do not necessarily have high speed work. Hour of work per frame - normal. )

If not, please tell me how to generate this model and on which data set. Thanks in advance.

@zaidalyafeai
Copy link
Owner

No, I don't have a larger model but you can train your own model. Follow the instructions here. To increase the size of the model use ngf = ndf = 64 for instance.

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