https://github.com/tensorlayer/dcgan

The Simplest DCGAN Implementation
https://github.com/tensorlayer/dcgan

dcgan gan generative-adversarial-network tensorlayer tensorlayerx

Last synced: 4 days ago
JSON representation

The Simplest DCGAN Implementation

• Host: GitHub
• URL: https://github.com/tensorlayer/dcgan
• Owner: tensorlayer
• Created: 2016-11-16T16:39:51.000Z (almost 8 years ago)
• Default Branch: master
• Last Pushed: 2023-05-24T02:39:25.000Z (over 1 year ago)
• Last Synced: 2024-08-01T17:32:53.916Z (3 months ago)
• Topics: dcgan, gan, generative-adversarial-network, tensorlayer, tensorlayerx
• Language: Python
• Homepage: https://github.com/tensorlayer/tensorlayerx
• Size: 2.03 MB
• Stars: 336
• Watchers: 13
• Forks: 116
• Open Issues: 13
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-tensorlayer - DCGAN
• awesome-tensorflow - DCGAN - Deep Convolutional Generative Adversarial Networks (Models/Projects)
• awesome-tensorflow - DCGAN - Deep Convolutional Generative Adversarial Networks (Models/Projects)
• fucking-awesome-tensorflow - DCGAN - Deep Convolutional Generative Adversarial Networks (Models/Projects)

README

        
# DCGAN in TensorLayerX

- This is an implementation of [Deep Convolutional Generative Adversarial Networks](http://arxiv.org/abs/1511.06434).

Looking for Text to Image Synthesis? [click here](https://github.com/zsdonghao/text-to-image)

- For earlier version, please check dcgan [release](https://github.com/tensorlayer/dcgan/releases) and [tensorlayer](https://github.com/tensorlayer/TensorLayer)

- For more computer vision applications, check [TLXCV](https://github.com/tensorlayer/TLXCV)

![alt tag](img/DCGAN.png)

## Prerequisites

🔥🔥🔥🔥🔥🔥 You need install TensorLayerX at first!

🔥🔥🔥🔥🔥🔥 Please install TensorLayerX via source

```

pip install tensorlayerx

```

or 

```

pip install git+https://github.com/tensorlayer/tensorlayerx.git 

```

## Usage

First, download the aligned face images from [google](https://drive.google.com/open?id=0B7EVK8r0v71pWEZsZE9oNnFzTm8) or [baidu](https://pan.baidu.com/s/1eSNpdRG#list/path=%2F) to a `data` folder.

Please place dataset 'img_align_celeba.zip' under 'data/celebA/' by default.

Your directory structure should look like this:

```

dcgan/

    └── data.py

    └── model.py

    └── train.py

    └── README.md

    └── data

          └── celebA

            └── img_align_celeba.zip

```

Second, train the GAN:

    $ python train.py

    

## Result on celebA