-
This repository is for implementation of
Generative Modelsusing Tensorflow 1.12 -
The structure of the code is based on the Hwalsuk Lee's Generative Model github repository
MMC Lab GAN Study Group members
- [GAN] Generative Adversarial Networks
- [DCGAN] Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- [LSGAN] Least Squares Generative Adversarial Networks
- [WGAN] Wasserstein GAN
- [WGAN_GP] Improved Training of Wasserstein GANs
- [CGAN] Conditional Generative Adversarial Nets
- [InfoGAN] Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- [HoloGAN] Unsupervised Learning of 3D Representations From Natural Images
- [SinGAN] Learning a Generative Model from a Single Natural Image
- [PGGAN] Progressive Growing of GANs for Improved Quality, Stability, and Variation
- [StyleGAN] A Style-Based Generator Architecture for Generative Adversarial Networks
- [CycleGAN] Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- [AGGAN] Attention-Guided Generative Adversarial Networks for Unsupervised Image-to-Image Translation
- [StarGAN] Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
- [DMIT] Multi-mapping Image-to-Image Translation via Learning Disentanglement
- Auto-Encoding Variational Bayes (VAE)
- Beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
- Neural Discrete Representation Learning(VQ-VAE)
MNIST
| MNIST | CelebA |
|---|---|
 |
 |
| MNIST | CelebA |
|---|---|
 |
 |
| MNIST | CelebA |
|---|---|
 |
 |
| MNIST | CelebA |
|---|---|
 |
 |
MNIST
MNIST
CelebA
Balloon
Mountain
Starry Night
It took about 2 weeks on TITAN RTX and trained 600k images per stage.
Cherry picked images
Latent interpolation
Fixed latent
No cherry picked images
Selected images
Style Mixing with Latent Codes
Random Images
Selected images
Style Mixing with Latent Codes
Random Images
| Monet to Photo | Photo to Monet |
|---|---|
 |
 |
| Horse to Zebra | Zebra to Horse |
|---|---|
 |
 |
| Horse to Zebra | Zebra to Horse |
|---|---|
 |
 |
CelebA
Summer2Winter
Reconstruction
| MNIST | CelebA |
|---|---|
 |
 |
Latent Space Interpolation (MNIST)
Latent Space Interpolation (CelebA)
Latent Space Interpolation: Beta = 10 (CelebA)
Latent Space Interpolation: Beta = 200 (CelebA)
Reconstruction (MNIST)
| Input | Reconstruction |
|---|---|
 |
 |
Reconstruction (CelebA)
| Input | Reconstruction |
|---|---|
 |
 |
PixelCNN Trained Latent Decoding
| MNIST | CelebA |
|---|---|
 |
 |
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent