Awesome

celeba-hq-modified

Changes I made (compared to original repo, see fork origin):

• Added multithreading support for substantial speedup.
• Save images using original filename (instead of index).

A modified approach to generate CelebA-HQ Dataset

The CelebA-HQ is a dataset introduced in Progressive Growing of GANs for Improved Quality (progressive_growing_of_gans), containing 30,000 high quality images from CelebA.

The images are originally stored as HDF5 format (.h5), which are not suitable for common data loaders. Therefore, I modified the h5tool.py to generate and save CelebA-HQ images in JPEG format (.jpg).

Usage

1. Clone the original repository

git clone https://github.com/tkarras/progressive_growing_of_gans/tree/original-theano-version

2. Clone this repository

git clone https://github.com/willylulu/celeb-hq-modified

3. Replace h5tool.py in the original repo with the one in this repo

cp celeb-hq-modified/h5tool.py progressive_growing_of_gans/h5tool

4. Create target directory in the original repository

cd progressive_growing_of_gans
mkdir celeba-hq
cd celeba-hq
mkdir celeba-64
mkdir celeba-128
mkdir celeba-256
mkdir celeba-512
mkdir celeba-1024

5. Go back to home path

cd

6. Create a directory B and download CelebA non-aligned version and put them in directory A

7. Create a directory A and download CelebA-HQ zip file and put them in directory B

8. Download annotation files and put them in directory B

9. Execute h5tool.py python h5tool.py create_celeba_hq 123456.h5 <path to directory A> <path to directory B>

Reference

tkarras/progressive_growing_of_gans

CelebA