Skip to content

Art generation program that combines the content of one image and the style of another to make surprising, novel images, using the algorithm discussed by Gatis, Ecker and Bethge in the paper "Image Style Transfer Using Convolutional Neural Networks". Program has adjustable hyperparameters, making it easy to change the created images.

Notifications You must be signed in to change notification settings

OvidiuSabau/Neural-Style-Transfer

Repository files navigation

Object-Style-Transfer

Art generation program that combines the content of one image and the style of another to make surprising, novel images, using the algorithm discussed by Gatis, Ecker and Bethge in the paper "Image Style Transfer Using Convolutional Neural Networks". Program has adjustable hyperparameters, making it easy to change the created images. Used a pretrained version of the famous VGG-19 convolutional neural network model.

The weights for the VGG-19 network can be downloaded here: https://goo.gl/dgS4GW

About

Art generation program that combines the content of one image and the style of another to make surprising, novel images, using the algorithm discussed by Gatis, Ecker and Bethge in the paper "Image Style Transfer Using Convolutional Neural Networks". Program has adjustable hyperparameters, making it easy to change the created images.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages