README.md

BSD-GAN

Tensorflow implementation of BSD-GAN

BSD-GAN paper

paper

please cite the paper, if the codes/dataset has been used for your research.

results of BSD-GAN

How to setup

Prerequisites

• Python (2.7 or later)

• numpy

• scipy

• NVIDIA GPU + CUDA 8.0 + CuDNN v5.1

• TensorFlow 1.0 or later

Getting Started

steps

• clone this repo:

git clone https://github.com/duxingren14/BSD-GAN.git

cd BSD-GAN

mkdir data

• download datasets (e.g., car) from google drive and put it in ./data/.

./BSD-GAN/data/car_400x300/*.jpg

• train the model:

python main.py --phase train --dataset_name car_400x300 --input_height 300 --input_width 400 --epoch 45

• test the model:

python main.py --phase train --dataset_name car_400x300 --input_height 300 --input_width 400 --epoch 45 --train False

other datasets

some datasets can be downloaded from the website. Please cite their papers if you use the data.

celebahq: https://github.com/tkarras/progressive_growing_of_gans

lsun: http://lsun.cs.princeton.edu/2017/

Experimental results:

Acknowledgments

Codes are built on the top of DCGAN tensorflow and progressive growing. Thanks for their precedent contributions!