https://github.com/shikharvaish28/neural-style

Py-Torch implementation of neural style algorithm(Style-transfer)
https://github.com/shikharvaish28/neural-style

artificial-intelligence artificial-neural-networks cnn pytorch style-transfer

Last synced: 16 days ago
JSON representation

Py-Torch implementation of neural style algorithm(Style-transfer)

• Host: GitHub
• URL: https://github.com/shikharvaish28/neural-style
• Owner: shikharvaish28
• Created: 2019-07-07T16:23:50.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2019-10-09T19:14:17.000Z (over 5 years ago)
• Last Synced: 2023-03-08T22:49:28.112Z (almost 2 years ago)
• Topics: artificial-intelligence, artificial-neural-networks, cnn, pytorch, style-transfer
• Language: Jupyter Notebook
• Homepage:
• Size: 11.3 MB
• Stars: 7
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# neural-style

This is a torch implementation of the paper [A Neural Algorithm of Artistic Style](http://arxiv.org/abs/1508.06576)

by Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge.

The paper presents an algorithm for combining the content of one image with the style of another image using

convolutional neural networks. Here's an example that maps the artistic style of

[self-portrait of Picasso](https://raw.githubusercontent.com/shikharvaish28/neural-style/master/inputs/janelle.png)

onto a photograph of [Janelle](https://github.com/shikharvaish28/neural-style/blob/master/inputs/janelle.png):



 

 

 



Applying the style of different images to the same content image gives interesting results.

Here we reproduce Figure 2 from the paper, which renders a photograph of the Tubingen in Germany in a

variety of styles:

















Here are the results of applying the style of various pieces of artwork to this photograph of the

space needle:
















## Setup:

Dependencies:

* [Py-torch](https://pytorch.org/)

Optional dependencies:

* For CUDA backend:

  * CUDA 9.0+

## Author:

[Shikhar Vaish](http://shikhar.engineer)