mirror/DeepCreamPy
1
0
Fork 0
mirror of https://github.com/Deepshift/DeepCreamPy.git synced 2025-01-05 21:55:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
deep pomf 2018-02-26 10:47:10 -05:00
parent 0b008e60df
commit 9fd51edb95
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -74,7 +74,7 @@ You must have a GPU for training since training on a CPU will take weeks.
Your custom dataset should be 128 x 128 images of uncensored vaginas and penises cropped from hentai. The more images, the better: I used 70,000 images for training. Censoring these images yourself is unnecessary.
Put your custom dataset for training in the "data/images" directory and convert images to npy format.
Put your custom dataset for training in the "training_data/images" directory and convert images to npy format.
```
$ cd training_data
@ -99,7 +99,7 @@ Training can be done separately for mosaics with train_mosaic.py, but decensor.p
- Incorporate GAN loss into training
- Update the model to the new version
Contributions are welcome! Special thanks to StartleStars for contributing code for mosaic decensorship.
Contributions are welcome! Special thanks to @StartleStars for contributing code for mosaic decensorship.
# License