Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/froukje/style-transfer

Last synced: about 1 month ago
JSON representation

Host: GitHub
URL: https://github.com/froukje/style-transfer
Owner: froukje
Created: 2021-06-08T05:47:40.000Z (over 3 years ago)
Default Branch: main
Last Pushed: 2022-11-20T08:54:29.000Z (about 2 years ago)
Last Synced: 2023-07-02T20:20:53.009Z (over 1 year ago)
Language: Jupyter Notebook
Size: 20.8 MB
Stars: 0
Watchers: 1
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md

Awesome Lists containing this project

README

        # Style Transfer

The repository contains a notebook for style transfer of a content and a style image. The notebook follows the tutorial from  [Udacity](https://classroom.udacity.com/courses/ud188/lessons/c1541fd7-e6ec-4177-a5b1-c06f1ce09dd8/concepts/af47e232-fa44-4e5d-b976-95e00430d0cf).

We *recreate* a style transfer method that is outlined in the paper, [Image Style Transfer Using Convolutional Neural Networks, by Gatys](https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Gatys_Image_Style_Transfer_CVPR_2016_paper.pdf) in PyTorch.

The data for the style images used can be downloaded from [kaggle](https://www.kaggle.com/soumikrakshit/images-for-style-transfer), the content images are private.

Here are some results

![guanaco](guanaco_target.png)

![guanaco](picasso_guanaco_target.png)

*Guanaco in Picasso style*

![guanaco](van_gogh_guanaco_target.png)

*Guanaco in Van Gogh style*