Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/Dhar/image-dreamer
"Dreams" images, such as shown in the Google Research blog post on "Inceptionism".
https://github.com/Dhar/image-dreamer
Last synced: 3 days ago
JSON representation
"Dreams" images, such as shown in the Google Research blog post on "Inceptionism".
- Host: GitHub
- URL: https://github.com/Dhar/image-dreamer
- Owner: Dhar
- Created: 2015-07-02T19:39:11.000Z (over 9 years ago)
- Default Branch: master
- Last Pushed: 2015-12-20T22:41:59.000Z (almost 9 years ago)
- Last Synced: 2024-08-02T05:12:22.312Z (3 months ago)
- Language: Python
- Size: 185 KB
- Stars: 105
- Watchers: 16
- Forks: 42
- Open Issues: 10
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# image-dreamer
"Dreams" images, such as shown in the [Google Research blog post on "Inceptionism"](http://googleresearch.blogspot.ch/2015/06/inceptionism-going-deeper-into-neural.html).## What's it do?
Using a deep neural network, it turns images like this:![](https://cloud.githubusercontent.com/assets/235769/8487629/318827be-20c2-11e5-9b3a-ec15b0871a4d.jpg)
Into this:
![](https://cloud.githubusercontent.com/assets/235769/8487642/3f91eb74-20c2-11e5-87aa-87ed27236f22.png)
Read the [Google Research blog post on "Inceptionism"](http://googleresearch.blogspot.ch/2015/06/inceptionism-going-deeper-into-neural.html) to learn more about how it works.
## Installation
* Install [Vagrant](https://www.vagrantup.com/)
* Clone this repo
* `cd image-dreamer`
* `vagrant up`
* Go grab a coffee, this will take a while## Usage
* Copy any JPEG images you want to "dreamify" into the `image-dreamer` directory
* `vagrant ssh`
* `cd /vagrant`
* `ipython dreamify.py `
* Freak out!## Credits
Thanks to the great work of Google's [deepdream](https://github.com/google/deepdream/blob/master/dream.ipynb) team!The Vagrant file and Vagrantbox are based on those provided by [Data Science Toolbox](http://datasciencetoolbox.org/). Big thanks to them for providing the scientific Python bootstrap I needed to get this going!
## Contributing
Have fun, hack, contribute! This is just a starting point, I'd love to see where people take this!If you make changes, please consider issuing a pull request. I'm happy to oblige.
Thanks to @borzoj and @dirtyvader for their contributions!