Skip to content

Unofficial Implementation for paper "AgileGAN: Stylizing Portraits by Inversion-Consistent Transfer Learning"

Notifications You must be signed in to change notification settings

piddnad/AgileGAN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AgileGAN

Unofficial implementation for paper "AgileGAN: Stylizing Portraits by Inversion-Consistent Transfer Learning"

The code is mainly based on these two repo: AgileGAN-inference and pixel2style2pixel

Installation

Please refer to AgileGAN#requirements and pixel2style2pixel#prerequisites.

Train

  1. Prepare the dataset and pretrained models.

  2. Start training using

python train.py \
    --exp_dir=ffhq_encode \
    --workers=8 \
    --batch_size=4 \
    --test_batch_size=4 \
    --test_workers=8 \
    --val_interval=2500 \
    --save_interval=5000 \
    --start_from_latent_avg

Test

Please refer to AgileGAN-inference

python test.py --path examples/29899.jpg --style cartoon

About

Unofficial Implementation for paper "AgileGAN: Stylizing Portraits by Inversion-Consistent Transfer Learning"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published