From 672fb597cad0d40b7de9abc4f4c4e0ad22a3947d Mon Sep 17 00:00:00 2001 From: deeppomf Date: Sun, 11 Feb 2018 23:29:10 -0500 Subject: [PATCH] Revert. Add some warnings --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 4dedae1..ac20ef9 100644 --- a/README.md +++ b/README.md @@ -3,7 +3,7 @@ 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.** +# **THIS PROJECT IS STILL IN DEVELOPMENT. DO NOT BE DISAPPOINTED IF THE RESULTS AREN'T AS GOOD AS YOU EXPECT.** ![Censored, decensored](/readme_images/collage.png) @@ -36,12 +36,12 @@ Embarrassingly, because the neural network was trained to decensor horizontally - matplotlib (only for running test.py) # Model -The pretrained model can be downloaded from **Model temporarily removed.**. +The pretrained model can be downloaded from https://drive.google.com/open?id=1mWHYSj0LDSbJQQxjR4hUMykQkVve2U3Q. Unzip the contents into the /models/ folder. # Usage - +o ## I. Decensoring hentai ![Guide](/readme_images/guide.png)