Skip to content

Code to synthesise textures using convolutional neural networks as described in Gatys et al. 2015 (http://arxiv.org/abs/1505.07376)

Notifications You must be signed in to change notification settings

leongatys/DeepTextures

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DeepTextures

Code to synthesise textures using convolutional neural networks as described in the paper "Texture Synthesis Using Convolutional Neural Networks" (Gatys et al., NIPS 2015) (http://arxiv.org/abs/1505.07376). More examples of synthesised textures can be found at http://bethgelab.org/deeptextures/.

The IPythonNotebook Example.ipynb contains the code to synthesise the pebble texture shown in Figure 3A (177k parameters) of the revised version of the paper. In the notebook I additionally match the pixel histograms in each colorchannel of the synthesised and original texture, which is not done in the figures in the paper. #Prerequisites

  • To run the code you need a recent version of the Caffe deep learning framework and its dependencies (tested with master branch at commit 20c474fe40fe43dee68545dc80809f30ccdbf99b).
  • The images in the paper were generated using a normalised version of the 19-layer VGG-Network described in the work by Simonyan and Zisserman. The weights in the normalised network are scaled such that the mean activation of each filter over images and positions is equal to 1. The normalised network can be downloaded here and has to be copied into the Models/ folder.

Disclaimer

This software is published for academic and non-commercial use only.

About

Code to synthesise textures using convolutional neural networks as described in Gatys et al. 2015 (http://arxiv.org/abs/1505.07376)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published