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 meaning of arg “color-levels”? #14

Open
lujiarui-iie opened this issue Jun 14, 2023 · 4 comments
Open

The meaning of arg “color-levels”? #14

lujiarui-iie opened this issue Jun 14, 2023 · 4 comments

Comments

@lujiarui-iie
Copy link

Hello, could you tell me what the meaning of "color-levels" is?

@anordertoreclaim
Copy link
Owner

hey, it's how many discrete levels each value of an image channel can take. For instance, for a black-and-white image (i.e. there is only a single channel) and color-levels equal to 2, the image is binary (each pixel value is equal to either one or two). If color-levels is 255 and image is coloured (i.e. there are 3 channels), you get a usual colored image.

@lujiarui-iie
Copy link
Author

lujiarui-iie commented Jun 19, 2023 via email

@anordertoreclaim
Copy link
Owner

I don't know if my understanding is correct: taking a color image as an example, each channel in each position of the image corresponds to 256 probability values, and the index corresponding to the maximum probability value is taken as the result of image generation (or the prediction result during the training stage).

yea, you are absolutely right here
note that teacher forcing is used during the training

@lujiarui-iie
Copy link
Author

lujiarui-iie commented Jun 24, 2023 via email

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