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

Deep Learning Texture Upscaler (merge) #45

Open
philyeahz opened this issue Jan 14, 2019 · 3 comments
Open

Deep Learning Texture Upscaler (merge) #45

philyeahz opened this issue Jan 14, 2019 · 3 comments
Assignees
Labels
enhancement New feature or request too lazy

Comments

@philyeahz
Copy link
Collaborator

Fix that branch (put executable in resources?) and merge it with the develop branch.

@philyeahz philyeahz added the enhancement New feature or request label Jan 14, 2019
@derplayer
Copy link
Owner

derplayer commented Jan 14, 2019

That stuff is way too big. (~500mb)
I'll implement it as an adhoc extension with an messagebox that asks you to download extra files to activate the deep learning feature in Tools menu. This feature will have an BETA tag, because it has problems with stuff like transparency. (at least for now)

Also:

  • Implement a CUDA/CPU CLI Parameter
  • Refreeze into executeable
  • Investigate OpenCL usecase
  • Publish python source code in separate repository (pre-freeze)

@derplayer derplayer added this to the Release 1.3 (Modding Tools) milestone Jan 14, 2019
@derplayer
Copy link
Owner

Workaround for transparency channel:

Input (argb)
rgb -> model
a -> grayscale -> model

Output (argb)
grayscale -> a
rgb + a -> output

@derplayer
Copy link
Owner

Moved prototype stuff into separate Helper class and merged into dev branch.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request too lazy
Projects
None yet
Development

No branches or pull requests

2 participants