Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/cedrickchee/stargan-tensorflow

Simple Tensorflow implementation of StarGAN (CVPR 2018 Oral)

https://github.com/cedrickchee/stargan-tensorflow

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.9%) to scientific vocabulary

Keywords

celeba-dataset computer-vision generative-adversarial-network image-to-image-translation stargan tensorflow-models
Last synced: 5 months ago · JSON representation

Repository

Simple Tensorflow implementation of StarGAN (CVPR 2018 Oral)

Basic Info
  • Host: GitHub
  • Owner: cedrickchee
  • License: mit
  • Language: Python
  • Default Branch: master
  • Homepage:
  • Size: 9.2 MB
Statistics
  • Stars: 1
  • Watchers: 3
  • Forks: 1
  • Open Issues: 0
  • Releases: 0
Fork of taki0112/StarGAN-Tensorflow
Topics
celeba-dataset computer-vision generative-adversarial-network image-to-image-translation stargan tensorflow-models
Created over 7 years ago · Last pushed over 7 years ago

https://github.com/cedrickchee/StarGAN-Tensorflow/blob/master/ 



--------------------------------------------------------------------------------

## Overview

This project is fork of TensorFlow implementation of [StarGAN](https://arxiv.org/abs/1711.09020). StarGAN is a unified Generative Adversarial Networks (GANs) for multi-domain image-to-image translation. What this means is, StarGAN can flexibly translate an input image to any desired target domain using only a single generator and a discriminator. You can take a look at the demo video for StarGAN [here](https://www.youtube.com/watch?v=EYjdLppmERE).

## Requirements
* Tensorflow 1.8
* Python 3.6

## Usage
### Downloading the dataset
```python
> python download.py celebA
```

```
 dataset
  celebA
      train
       000001.jpg 
            000002.jpg
            ...
        test (It is not celebA)
            a.jpg (The test image that you wanted)
            b.png
            ...
        list_attr_celeba.txt (For attribute information) 
```

### Train
* python main.py --phase train

### Test
* python main.py --phase test 
* The celebA test image and the image you wanted run simultaneously

### Pretrained model
* Download [checkpoint for 128x128](https://drive.google.com/open?id=1ezwtU1O_rxgNXgJaHcAynVX8KjMt0Ua-)

## Summary
![overview](./assests/overview.PNG)

## Results (128x128, wgan-gp)
### Women
![women](./assests/women.png)

### Men
![men](./assests/men.png)

## Reference
* [StarGAN paper](https://arxiv.org/abs/1711.09020)
* [Author pytorch code](https://github.com/yunjey/StarGAN)

## Author
Junho Kim

Owner

  • Name: Cedric Chee
  • Login: cedrickchee
  • Kind: user
  • Location: PID 1
  • Company: InvictusByte

Lead Software Engineer | LLMs | full stack Go/JS dev, backend | product dev @ startups | 🧑‍🎓 CompSci | alumni: fast.ai, Antler.co

GitHub Events

Total
Last Year