- Final update: 2019. 05. 17.
- All right reserved @ Il Gu Yi 2019
This repository is a collection of various generative models (GAN, VAE, Normalizing flow, Autoregressive models, etc) implemented by TensorFlow version 2.0 style
TensorFlow2.0 (exceptnormalizing_flow/nice.ipynbwhich is based on tf version 1.13.1)- Python 3.6
- Python libraries:
numpy,matplotlib,PIL,imageiourllib,zipfile
- TensorFlow libraries & extensions:
- Jupyter notebook
- OS X and Linux (Not validated on Windows OS)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks paper arXiv:1511.06434
- dcgan.ipynb
| MNIST | Fashion MNIST |
|---|---|
![]() |
![]() |
- Conditional Generative Adversarial Nets arXiv:1411.1784
- cgan.ipynb
| MNIST | ![]() |
| Fashion MNIST | ![]() |
- Least Squares Generative Adversarial Networks arXiv:1611.04076
- lsgan.ipynb
| MNIST | Fashion MNIST |
|---|---|
![]() |
![]() |
- Adversarial Feature Learning arXiv:1605.09782
- bigan.ipynb
| MNIST | ![]() |
| Fashion MNIST | ![]() |
- Wasserstein GAN arXiv:1701.07875
- wgan.ipynb
| MNIST | Fashion MNIST |
|---|---|
![]() |
![]() |
- Improved Training of Wasserstein GANs arXiv:1704.00028
- wgan-gp.ipynb
| MNIST | Fashion MNIST |
|---|---|
![]() |
![]() |
- Image-to-Image Translation with Conditional Adversarial Networks arXiv:1611.07004
- pix2pix.ipynb
| facades | ![]() |
| cityspaces | ![]() |
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks arXiv:1703.10593
- cyclegan.ipynb
| MNIST | ![]() |
| Fashion MNIST | ![]() |
| MNIST | Fashion MNIST |
|---|---|
![]() |
![]() |
- Neural Autoregressive Distribution Estimation arXiv:1605.02226
- nade.ipynb
| MNIST | Fashion MNIST |
|---|---|
![]() |
![]() |
Il Gu Yi




















