update readmes, added pix2pix

This commit is contained in:
Aladdin Persson
2021-03-06 12:46:11 +01:00
parent 9ae1ff3db0
commit 792f4bbb9e
2 changed files with 11 additions and 5 deletions

View File

@@ -17,13 +17,15 @@ The dataset can be downloaded from Kaggle: [link](https://www.kaggle.com/vikramt
The dataset can be downloaded from Kaggle: [link](https://www.kaggle.com/ktaebum/anime-sketch-colorization-pair).
### Download pretrained weights
Pretrained weights for Satellite image to Google Map [here](https://github.com/aladdinpersson/Machine-Learning-Collection/releases/download/1.0/Pix2Pix_Weights_Satellite_to_Map.zip)
Pretrained weights for Colorizing Anime [here](https://github.com/aladdinpersson/Machine-Learning-Collection/releases/download/1.0/Pix2Pix_Weights_Colorize_Anime.zip)
Pretrained weights for Satellite image to Google Map [here](https://github.com/aladdinpersson/Machine-Learning-Collection/releases/download/1.0/Pix2Pix_Weights_Satellite_to_Map.zip).
Pretrained weights for Colorizing Anime [here](https://github.com/aladdinpersson/Machine-Learning-Collection/releases/download/1.0/Pix2Pix_Weights_Colorize_Anime.zip).
Extract the zip file and put the pth.tar files in the directory with all the python files. Make sure you put LOAD_MODEL=True in the config.py file.
### Training
Edit the config.py file to match the setup you want to use. Then run train.py
## Pix2Pix paper
### Image-to-Image Translation with Conditional Adversarial Networks by Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A. Efros