Skip to content
Tensorflow implementation of BranchGAN
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
README.md
app1.png
car.png
face256.png
face512.png
lsun.png
main.py
model.py
ops.py
teaser.png
utils.py

README.md

BranchGAN

Tensorflow implementation of BranchGAN

BranchGAN demo

BranchGAN paper

paper

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

results of BranchGAN

Scale-aware fusion

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/BranchGAN.git

cd BranchGAN

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

./BranchGAN/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:

celeba_hq256 celeba_hq512 car_400x300 lsun church_outdoor

Acknowledgments

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

You can’t perform that action at this time.