Skip to content

Transfer painting styles to chosen images with Deep Learning

Notifications You must be signed in to change notification settings

maurock/neural_transfer_style

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Neural Style Transfer using Deep Learning

Transfer painting styles to chosen images.

This project reproduces the paper "A Neural Algorithm of Artistic Style" by Gatys et al. (https://arxiv.org/abs/1508.06576).

Run

To run the neural style transfer script:

  • place the base image (the image to modify) in reference_images\base_image
  • place the style image (the image from which the style is transferred) in reference_images\style_image
  • run the script main.py in the main directory

After each iteration, an image is generated.

Run example:

python main.py --base_image=jumping_me.jpg --style_image=starry_night.jpg --iterations=20

Arguments description:

  • --base_image - Type string, default jumping_me.jpg, the image to modify
  • --style_image - Type string, default starry_night.jpg, the image from which the style is transferred
  • --iterations - Type int, default 20, the number of iterations

About

Transfer painting styles to chosen images with Deep Learning

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages