Skip to content

yiyi1026/styleTransfer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

30 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Neural Style Transfer

This is a Keras implementation of A Neural Algorithm of Artistic Style by Leon A. Gatys, Alexander S. Ecker and Matthias Bethge.

Content image - Sydney Opera House

images_sydney

Style image - Still Life Painting By Pablo Picasso

images_picasso

Transfer demo

sydney_picasso_tranfer

Output image

images_sydney_picasso_result

Implementation

basic usage:

python styletransfer.py path_to_content_image.jpg path_to_style_image.jpg prefix_for_result

options:

  • content_weight
  • style_weight
  • iter
python styletransfer.py --content_weight 0.015 --iter 1 path_to_content_image.jpg path_to_style_image.jpg prefix_for_result

Dependencies

  • Python 3.x
  • Keras
  • Tensorflow

Reference

This implementation uses some code from Francois Chollet's Neural Style Transfer.

This paper presents an algrithm for generating a mixed image with the content from the content image and the style from another image, using the convolutional neural network(CNN).

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published