tensorlayer / dcgan

The Simplest DCGAN Implementation

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

DCGAN in TensorLayerX

πŸ”₯πŸ”₯πŸ”₯πŸ”₯πŸ”₯πŸ”₯Now, we update this script under TensorLayerX!

TensorLayerX: A Unified Deep Learning and Reinforcement Learning Framework for All Hardwares, Backends and OS.X

This is the TensorLayerX implementation of Deep Convolutional Generative Adversarial Networks. Looking for Text to Image Synthesis ? click here

For earlier version, please check srgan release and tensorlayer.

alt tag

Prerequisites

πŸ”₯πŸ”₯πŸ”₯πŸ”₯πŸ”₯πŸ”₯ You need install TensorLayerX at first!

πŸ”₯πŸ”₯πŸ”₯πŸ”₯πŸ”₯πŸ”₯ Please install TensorLayerX via source

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

Usage

First, download the aligned face images from google or baidu 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

About

The Simplest DCGAN Implementation


Languages

Language:Python 100.0%