ResidualGAN
Tensorflow implementation of Learning Residual Images for Face Attribute Manipulation
Prerequisites
- Python 3.6
- Tensorflow 1.6
Results for Facial Attribute Transfer on CelebA
The images are generated by ResidualGAN trained on the CelebA dataset.
Usage
1. Clone the repository
$ git clone https://github.com/ioanachelu/ResidualGAN.git
$ cd ResidualGAN/
../data
. It should have the following substructure:
2. Download the dataset into .data
celebA
list_attr_celebs.txt
3. Train ResidualGAN with CelebA
$ python train.py --train=True --logdir=./logdir --config=default --dataset_path=../data
4. Resume ResidualGAN training with CelebA
$ python train.py --train=True --resume=True --load_from=./logdir/0-std_gan --config=std_gan --dataset_path=../data