Skip to content

Image style transfer- change any image to an artistic image by using Convolutional Neural Network.

Notifications You must be signed in to change notification settings

mayste/StyleTransfer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

Image style transfer

This is an implementation of image style transfer by using CNN with Tensorflow.

The system extracts content and style from an image and combined them together in order to get an artistic image by using a neural network. The code is written in python3 with PyQt5 for the Gui and worked on a pre-trained network with TensorFlow.

This is a collage project based on J. Johnson paper and Leon A. Gatys' paper, you can find our full project paper on this repository.

For using the application you can or download stylemaker.exe and run it on any machine, or run the python code on python3 environment.

NOTE: Please wait, the app takes a few seconds to open.

Example: Picture1

Application GUI and implementation:

Home Screen:

mainWindow

Start image style transfer process:

TransferGui

content and style

processing

showOutput

Help File:

showHelp

Our Results:

Picture3 Picture2

About

Image style transfer- change any image to an artistic image by using Convolutional Neural Network.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages