Skip to content
Projets

taki0112/BigGAN-Tensorflow

Voir sur GitHub

taki0112/BigGAN-Tensorflow has 258 GitHub stars and 71 forks. Star changes are not measured yet. Last checked 2026-11-15 21:16 UTC. Last push 2019-01-14.

Comment ces chiffres sont mesurés

Progression mesurée des étoiles

in 24h
Mise à jour retardée
in 7 days
Mise à jour retardée
in 15 days
Mise à jour retardée
in 1 month
Mise à jour retardée

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

Simple Tensorflow implementation of "Large Scale GAN Training for High Fidelity Natural Image Synthesis" (BigGAN)

Apprentissage automatique

README.md

Original

BigGAN-Tensorflow

Simple Tensorflow implementation of "Large Scale GAN Training for High Fidelity Natural Image Synthesis" (BigGAN)

main

Issue

  • The paper used orthogonal initialization, but I used random normal initialization. The reason is, when using the orthogonal initialization, it did not train properly.
  • I have applied a hierarchical latent space, but not a class embeddedding.

Usage

dataset

  • mnist and cifar10 are used inside keras
  • For your dataset, put images like this:
├── dataset
   └── YOUR_DATASET_NAME
       ├── xxx.jpg (name, format doesn't matter)
       ├── yyy.png
       └── ...

train

  • python main.py --phase train --dataset celebA-HQ --gan_type hinge

test

  • python main.py --phase test --dataset celebA-HQ --gan_type hinge

Architecture

128x128

256x256

512x512

Author

Junho Kim