Put notice in readme

This commit is contained in:
deeppomf 2018-02-11 16:41:07 -05:00
parent 4635f6b41c
commit 05b5a54b9d

View File

@ -3,6 +3,8 @@
This project applies an implementation of [Globally and Locally Consistent Image Completion](http://hi.cs.waseda.ac.jp/%7Eiizuka/projects/completion/data/completion_sig2017.pdf) to the problem of hentai decensorship. Using a deep fully convolutional neural network, DeepMindBreak can replace censored artwork in hentai with plausible reconstructions. The user needs to only specify the censored regions. This project applies an implementation of [Globally and Locally Consistent Image Completion](http://hi.cs.waseda.ac.jp/%7Eiizuka/projects/completion/data/completion_sig2017.pdf) to the problem of hentai decensorship. Using a deep fully convolutional neural network, DeepMindBreak can replace censored artwork in hentai with plausible reconstructions. The user needs to only specify the censored regions.
**THIS REPO IS NOT YET IN A USABLE STATE. PLEASE WAIT FOR THIS NOTICE TO BE REMOVED BEFORE DOWNLOADING/FORKING.**
![Censored, decensored](/readme_images/collage.png) ![Censored, decensored](/readme_images/collage.png)
# Limitations # Limitations
@ -23,6 +25,8 @@ It does NOT work with:
In particular, if a vagina or penis is completely censored out, inpainting will be ineffective. In particular, if a vagina or penis is completely censored out, inpainting will be ineffective.
Embarrassingly, because the neural network was trained to decensor horizontally and vertically oriented rectangles, it has trouble with angled rectangles. This will be fixed soon.
# Dependencies # Dependencies
- Python 2 - Python 2