https://github.com/xunhuang1995/sgan

Stacked Generative Adversarial Networks
https://github.com/xunhuang1995/sgan

computer-vision generative-adversarial-network generative-model machine-learning

Last synced: about 1 month ago
JSON representation

Stacked Generative Adversarial Networks

• Host: GitHub
• URL: https://github.com/xunhuang1995/sgan
• Owner: xunhuang1995
• Created: 2016-12-14T00:42:41.000Z (about 8 years ago)
• Default Branch: master
• Last Pushed: 2017-05-14T03:36:03.000Z (over 7 years ago)
• Last Synced: 2024-12-11T09:10:35.670Z (about 2 months ago)
• Topics: computer-vision, generative-adversarial-network, generative-model, machine-learning
• Language: Python
• Homepage: https://arxiv.org/abs/1612.04357
• Size: 41.4 MB
• Stars: 244
• Watchers: 13
• Forks: 51
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Stacked Generative Adversarial Networks

This repository contains code for the paper "[Stacked Generative Adversarial Networks](https://arxiv.org/abs/1612.04357)", CVPR 2017. Part of the code is modified from OpenAI's [implementation](https://github.com/openai/improved-gan) of Improved GAN.

## Architecture







## Samples











## Performance Comprison on CIFAR-10

| Method       |  Inception Score | 

| ------------- | ----------- |

| Infusion training    |  4.62 ± 0.06     | 

| GMAN (best variant)  |  5.34 ± 0.05  | 

| LR-GAN  |  6.11 ± 0.06  | 

| EGAN-Ent-VI  |  7.07 ± 0.10  | 

| Denoising feature matching  |  7.72 ± 0.13 | 

| DCGAN  |  6.58 | 

| SteinGAN |  6.35 | 

| Improved GAN（best variant)  |  8.09 ± 0.07 | 

| AC-GAN |  8.25 ± 0.07 | 

| **SGAN (ours)**   |  **8.59 ± 0.12** | 

## Citations

If you use the code in this repository in your paper, please consider citing:

```

@inproceedings{huang2017sgan,

  title={Stacked Generative Adversarial Networks},

  author={Huang, Xun and Li, Yixuan and Poursaeed, Omid and Hopcroft, John and Belongie, Serge},

  booktitle={CVPR},

  year={2017}

}

```

## Contact

If you have any questions about the code, feel free to email me ([email protected]).