Are you happy with your logging solution? Would you help us out by taking a 30-second survey? Click here


natural image generation using ConvNets

Subscribe to updates I use eyescream

Statistics on eyescream

Number of watchers on Github 562
Number of open issues 3
Average time to close an issue 8 days
Main language Lua
Average time to merge a PR about 2 hours
Open pull requests 0+
Closed pull requests 0+
Last commit almost 4 years ago
Repo Created over 4 years ago
Repo Last Updated over 1 year ago
Size 59 KB
Organization / Authorfacebook
Page Updated
Do you use eyescream? Leave a review!
View open issues (3)
View eyescream activity
View on github
Fresh, new opensource launches 🚀🚀🚀
Trendy new open source projects in your inbox! View examples

Subscribe to our mailing list

Evaluating eyescream for your project? Score Explanation
Commits Score (?)
Issues & PR Score (?)

The Eyescream Project

Generating Natural Images using Neural Networks.

For our research summary on this work, please read the Arxiv paper:

For a high-level blog post with a live demo, please go to this website:

This repository contains the code to train neural networks and reproduce our results from scratch.


Eyescream requires or works with

  • Mac OS X or Linux
  • NVIDIA GPU with compute capability of 3.5 or above.

Installing Dependencies

  • Install Torch
  • Install the nngraph and tds packages:
luarocks install tds
luarocks install nngraph

Training your neural networks

  • If you want to train the CIFAR-10 image generators, read the README in the cifar/ folder
  • If you want to train the LSUN/Imagenet image generators, read the README in the lsun/ folder

Discuss the paper/code at


See the CONTRIBUTING file for how to help out.


Eyescream is BSD-licensed. We also provide an additional patent grant.

eyescream list of languages used
Other projects in Lua