GitXplorerGitXplorer
V

HDStyleTransfer

public
2 stars
3 forks
4 issues

Commits

List of commits on branch master.
Unverified
b575cf9b53f25e809397b555908e874a07d76237

style_transfert -> style_transfer

VValentinVignal committed 5 years ago
Unverified
a42c0f1f21928b640d21307c025264a08e0f78d4

style_transfert -> style_transfer

VValentinVignal committed 5 years ago
Unverified
d46e6a49e7cab9832b6e569cc52fbec7fcf3b303

Typo read me

VValentinVignal committed 5 years ago
Unverified
e1691042df228dc4cd71fb51a8a53d41c58374da

README

VValentinVignal committed 5 years ago
Verified
afcde6de7e86ea4b52cdaf1578966c611c8de404

Merge pull request #47 from ValentinVignal/st/google-colab

VValentinVignal committed 5 years ago
Verified
c028868f8ceee3517af17acc72ec0a90866ff8b4

Merge pull request #46 from ValentinVignal/st/src

VValentinVignal committed 5 years ago

README

The README file for this repository.

HDStyleTransfer

This repo is a personal project to perform style transfer between images. The goal was to create HD stylized images.

The images size can be at least 1024 x 1024 pixels.

As you see in the results I successfully created acceptable stylized HD images using the GPU of Google Colab. 🎉

Style Transfer

Results

Here are some results of my project:

Content Image Style Image Result Image
logo_veval_2 fractal logo_veval_2
tree_road surface_pro tree_road_surface_pro
tree_road fractal tree_road_fractal

Google colab

The file style_transfer.ipynb will perform the style transfert algorithm for a combination of given images and parameters.

The steps for the setup are explained in the file.

Script

The script style_transfer.py will generate one set of stylized images for one combination of content/style images and parameters

python style_transfer.py

The content and style images must be in a content and style folders or content.zip and style.zip files at the root of the project

The parameters can be changed by creating and editing the files:

  • style_transfer_options.json
  • style_transfer_parameters.json
  • style_transfer_parameters_list.json

It will create a results folder with the stylized images in it.

To apply the style transfer on several images, run the command

python style_transfer.py

as many times as you need