Tensorflow implementation for learning an image-to-image translation without input-output pairs. The method is proposed by Jun-Yan Zhu in Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkssee. For example:

• tensorflow r1.0 or higher version
• numpy 1.11.0
• scipy 0.17.0
• pillow 3.3.0

• Install tensorflow from https://github.com/tensorflow/tensorflow
• Clone this repo:

git clone https://github.com/xhujoy/CycleGAN-tensorflow
cd CycleGAN-tensorflow

• Download a dataset (e.g. zebra and horse images from ImageNet):

bash ./download_dataset.sh horse2zebra

• Train a model:

python main.py --dataset_dir=horse2zebra

• Use tensorboard to visualize the training details:

tensorboard --logdir=./logs

• Finally, test the model:

python main.py --dataset_dir=horse2zebra --phase=test --which_direction=AtoB

To train a model,

python main.py --dataset_dir=/path/to/data/ 

Models are saved to ./checkpoints/ (can be changed by passing --checkpoint_dir=your_dir).

To test the model,

python main.py --dataset_dir=/path/to/data/ --phase=test --which_direction=AtoB/BtoA

Download the datasets using the following script:

bash ./download_dataset.sh dataset_name

• facades: 400 images from the CMP Facades dataset.
• cityscapes: 2975 images from the Cityscapes training set.
• maps: 1096 training images scraped from Google Maps.
• horse2zebra: 939 horse images and 1177 zebra images downloaded from ImageNet using keywords wild horse and zebra
• apple2orange: 996 apple images and 1020 orange images downloaded from ImageNet using keywords apple and navel orange.
• summer2winter_yosemite: 1273 summer Yosemite images and 854 winter Yosemite images were downloaded using Flickr API. See more details in our paper.
• monet2photo, vangogh2photo, ukiyoe2photo, cezanne2photo: The art images were downloaded from Wikiart. The real photos are downloaded from Flickr using combination of tags landscape and landscapephotography. The training set size of each class is Monet:1074, Cezanne:584, Van Gogh:401, Ukiyo-e:1433, Photographs:6853.
• iphone2dslr_flower: both classe of images were downlaoded from Flickr. The training set size of each class is iPhone:1813, DSLR:3316. See more details in our paper.

• The torch implementation of CycleGAN, https://github.com/junyanz/CycleGAN
• The tensorflow implementation of pix2pix, https://github.com/yenchenlin/pix2pix-tensorflow