Skip to content
Simple & Intuitive Tensorflow implementation of StyleGAN (CVPR 2019 Oral)
Python Dockerfile
Branch: master
Clone or download
Latest commit 1cca9da Jul 24, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
assets add assets Jul 10, 2019
dataset Added Dockerfile, and kept dataset directory Jul 11, 2019
.DS_Store add assets Jul 10, 2019
.gitignore Added Dockerfile, and kept dataset directory Jul 11, 2019
Dockerfile Added Dockerfile, and kept dataset directory Jul 11, 2019
LICENSE Initial commit Jun 30, 2019
README.md Update README.md Jul 25, 2019
StyleGAN.py fix_end_iter_for_last_res Jul 15, 2019
main.py modify code Jul 13, 2019
ops.py fix code Jul 13, 2019
requirements.txt Added Dockerfile, and kept dataset directory Jul 11, 2019
utils.py add max_iteration Jul 13, 2019

README.md

StyleGAN-Tensorflow

Simple & Intuitive Tensorflow implementation of "A Style-Based Generator Architecture for Generative Adversarial Networks" (CVPR 2019 Oral)

Official code | Paper | Video | FFHQ Dataset

Other implementation

TF Estimator version

Pretrained model

Checkpoint

Usage

├── dataset
   └── YOUR_DATASET_NAME
       ├── 000001.jpg 
       ├── 000002.png
       └── ...

Train

> python main.py --dataset FFHQ --img_size 1024 --gpu_num 4 --progressive True --phase train

Test

> python main.py --dataset FFHQ --img_size 1024 --progressive True --batch_size 16 --phase test

Draw

Figure02 uncurated

python main.py --dataset FFHQ --img_size 1024 --progressive True --phase draw --draw uncurated

Figure03 style mixing

python main.py --dataset FFHQ --img_size 1024 --progressive True --phase draw --draw style_mix

Figure08 truncation trick

python main.py --dataset FFHQ --img_size 1024 --progressive True --phase draw --draw truncation_trick

Architecture

Our Results (1024x1024)

  • Training time: 2 days 14 hours with V100 * 4
  • max_iteration = 900
    • Official code = 2500

Uncurated

Style mixing

Truncation trick

Generator loss graph

Discriminator loss graph

Author

Junho Kim

You can’t perform that action at this time.