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

Doubt about the input of the mask to the local discriminator #7

Open
freaky-perceptron opened this issue May 4, 2020 · 2 comments
Open

Comments

@freaky-perceptron
Copy link

Hi, the method described in the paper is really amazing!
I am implementing your paper.
I have a doubt about how should be patch or mask arrangement as an input to the local discriminator.
In the paper, the figure has a description of the square sized patch/mask. but how would it be cropped in case of a random mask? like the mask can be distributed randomly all over the image pixels

I would like to hear from you soon.
thanks!

@Zheng222
Copy link
Owner

Zheng222 commented May 5, 2020

@bhaveshIITB Hello, for irregular masks, the random regular regions are cropped and sent to the local discriminator.

@Daiqy
Copy link

Daiqy commented Oct 22, 2020

Hi, I'm so sorry I haven't understood. Could you describe specifically how to crop the random regular regions in the target and output image for irregular cases? Thank you!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
3 participants