Skip to content
Projets

carpedm20/BEGAN-tensorflow

Voir sur GitHub

carpedm20/BEGAN-tensorflow has 924 GitHub stars and 228 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-20 06:40 UTC. Last push 2018-03-26.

Comment ces chiffres sont mesurés

Progression mesurée des étoiles

in 24h
0
in 7 days
Historique en cours
in 15 days
Historique en cours
in 1 month
Historique en cours

Variations nettes sur des périodes qui se chevauchent, pas des totaux quotidiens. Les mesures absentes restent vides. Les étoiles indiquent l’intérêt, pas la qualité.

À propos

Tensorflow implementation of "BEGAN: Boundary Equilibrium Generative Adversarial Networks"

Apprentissage automatique

README.md

Original

BEGAN in Tensorflow

Tensorflow implementation of BEGAN: Boundary Equilibrium Generative Adversarial Networks.

alt tag

Requirements

Usage

First download CelebA datasets with:

$ apt-get install p7zip-full # ubuntu
$ brew install p7zip # Mac
$ python download.py

or you can use your own dataset by placing images like:

data
└── YOUR_DATASET_NAME
    ├── xxx.jpg (name doesn't matter)
    ├── yyy.jpg
    └── ...

To train a model:

$ python main.py --dataset=CelebA --use_gpu=True
$ python main.py --dataset=YOUR_DATASET_NAME --use_gpu=True

To test a model (use your load_path):

$ python main.py --dataset=CelebA --load_path=CelebA_0405_124806 --use_gpu=True --is_train=False --split valid

Results

Generator output (64x64) with gamma=0.5 after 300k steps

all_G_z0_64x64

Generator output (128x128) with gamma=0.5 after 200k steps

all_G_z0_64x64

Interpolation of Generator output (64x64) with gamma=0.5 after 300k steps

interp_G0_64x64

Interpolation of Generator output (128x128) with gamma=0.5 after 200k steps

interp_G0_128x128

Interpolation of Discriminator output of real images

alt tag
alt tag
alt tag
alt tag
alt tag
alt tag
alt tag
alt tag
alt tag
alt tag
alt tag

Related works

Author

Taehoon Kim / @carpedm20