Code Monkey home page Code Monkey logo

yadcgan-keras's Introduction

yadcgan-keras

Yet Another DCGAN for keras

The aim of DCGAN model is to be able to produce images that would be similar to the train set.

Dataset consists of ~87000 RGB images of size 48x48 from old games. Mainly images are of characters and objects. Images are at original scale. Dataset was extracted from http://spritedatabase.net/ and published with explicit permit of Paul, Sprite Database owner

Requirements:

  • python 2.7
  • keras with theano
  • opencv3, for saving files
  • joblib, to load image dump of big size
  • matplotlib, for debug output
  • GPU card for reasonable training speed

Examples:

After ~5 hours of training After ~16 hours of training

After ~30 hours of training After ~40 hours of training

yadcgan-keras's People

Contributors

dremovd avatar

Stargazers

Vít Listík avatar Ryan Shen avatar June avatar January Desk avatar Nikolay Semyachkin avatar  avatar Andrey Stromnov avatar  avatar  avatar Artem Zarubin avatar Maxim Kochurov avatar Bogunov Ilya avatar

Watchers

Bogunov Ilya avatar James Cloos avatar  avatar  avatar

Forkers

techmind

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.