Home

Awesome

PGGAN-tensorflow

The tensorflow implementation of PROGRESSIVE GROWING OF GANS FOR IMPROVED QUALITY, STABILITY, AND VARIATION.

The generative process of PG-GAN

<p align="center"> <img src="/images/figure.png"> </p>

Differences with the original paper.

Setup

Prerequisites

Getting Started

git clone https://github.com/zhangqianhui/progressive_growing_of_gans_tensorflow.git
cd progressive_growing_of_gans_tensorflow

You can download the CelebA dataset and unzip CelebA into a directory. Noted that this directory don't contain the sub-directory.

python main.py --path=your celeba data-path --celeba=True
python main.py --path=your celeba-hq data-path --celeba=False

Results on celebA dataset

Here is the generated 64x64 results(Left: generated; Right: Real):

<p align="center"> <img src="/images/sample.png"> </p>

Here is the generated 128x128 results(Left: generated; Right: Real):

<p align="center"> <img src="/images/sample_128.png"> </p>

Results on CelebA-HQ dataset

Here is the generated 64x64 results(Left: Real; Right: Generated):

<p align="center"> <img src="/images/hs_sample_64.jpg"> </p>

Here is the generated 128x128 results(Left: Real; Right: Generated):

<p align="center"> <img src="/images/hs_sample_128.jpg"> </p>

Issue

If you find some bugs, Thanks for your issue to propose it.

Reference code

PGGAN Theano

PGGAN Pytorch