mirror/DeepCreamPy
1
0
Fork 0
mirror of https://github.com/Deepshift/DeepCreamPy.git synced 2025-01-26 21:35:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
deep pomf 2018-02-09 21:25:48 -05:00
parent f0c84d38d1
commit e38d316d57
1 changed files with 6 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
README.md
View File

@ -18,9 +18,11 @@ Link coming soon
## I. Decensoring hentai ## I. Decensoring hentai
The decensorship process is fairly involved. A UI will eventually be released to streamline the process.
Crop 128 x 128 size images containing the censored regions from your images and save them as new images. For each 128 x 128 image, color the
## I. Prepare the training data ## II. Prepare the training data
Put the images for training the "data/images" directory and convert images to npy format. Put the images for training the "data/images" directory and convert images to npy format.
@ -29,22 +31,14 @@ $ cd data
$ python to_npy.py $ python to_npy.py
``` ```
The dataset will not be released The dataset will not be released. I do not want to risk trouble for distributing copyrighted pornographic material.
## II. Train the GLCIC model
```
$ cd src
$ python train.py
```
You can download the trained model file: [glcic_model.tar.gz](
https://drive.google.com/open?id=1jvP2czv_gX8Q1l0tUPNWLV8HLacK6n_Q)
# To do # To do
- Add a user interface - Add a user interface
- Incorporate GAN loss into training - Incorporate GAN loss into training
Contributions are welcome!
# License # License
Model is under CC BY-NC 3.0 License Model is under CC BY-NC 3.0 License