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 to compute the global color histogram #61

Open
cccusername opened this issue Dec 17, 2018 · 5 comments
Open

how to compute the global color histogram #61

cccusername opened this issue Dec 17, 2018 · 5 comments

Comments

@cccusername
Copy link

hi, @richzhang i am confused about how to compute the global color histogram. Does it come from Global Hints Network? If my hypothesis is right, the input of Global Hints Network is a reference image, right?
I am looking forward to your reply, thanks!

@richzhang
Copy link
Collaborator

An example for extracting the global color histogram is here in function get_global_histogram. It called a network here. The network resizes the image, computes the color bin that each pixel belongs to using this function, and then averages all the pixels in the image to get a distribution.

@cccusername
Copy link
Author

@richzhang The target of the image is colorized with a reference image. So how to color the the background of the image.

@junyanz
Copy link
Owner

junyanz commented Dec 22, 2018

The entire image is colorized based on a reference image, not only the target.

@mattclifford1
Copy link

Would it be possible to get a pytorch version of the global hints network?

@junyanz
Copy link
Owner

junyanz commented Sep 25, 2019

It's currently not available. We have a notebook with Caffe backend.

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

4 participants