Git Product home page Git Product logo

artistic-style's Introduction

Artistic-Style

Very simple implementation of Neural Algorithm of the Artistic Style (Gatys et al. - http://arxiv.org/abs/1508.06576) in Tensorflow. I used VGG implementation from Chris and modified it slightly, stripping away unnecessary layers.

In the examples below I used content image as an initialization, it seems to provide more consistent image, but in the code, you can switch easily to noise initialization on line 109 in style.py. I used Adam for optimizer and let it run for 500 iterations.

To run it, you're going to need:

Usage

  python style.py content_image_path style_image_path [output_image] [{top,center,bottom,left,right}] [content_scale] [style_weight]

  • paths are pretty self-explanatory
  • {top,center,bottom,left,right} specify how to crop the style image to obtain an image of the same size as the content image
  • content_scale specifies scale factor that is applied to the input content image. Smaller the image, faster the stylization.
  • style_weight is a number between 0-1 that specifies emphasis on the style. 0 means no styling, 1 means only styling.

Examples

First thing I had to do - stylize my very handsome profile picture:

artistic-style's People

Contributors

janivanecky avatar kumekay avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

artistic-style's Issues

TypeError: expand_dims() takes exactly 2 arguments (1 given)

The code is wonderful and I'm using python 2.7 to run the code.
It outputs the error message: File "/home/jyc/2thPaper_TensorFlow/Artistic-Style-master/vgg.py", line 20, in __init__self.data_dict = np.load(vgg19_npy_path, encoding='latin1').item(). TypeError: load() got an unexpected keyword argument 'encoding' at first. I guess it's due to the python version I used after I refer to http://docs.scipy.org/doc/numpy/reference/generated/numpy.load.html. The code may be developed under python 3.x. So I remove "encoding='latin1'" and it works.

But then I get another error message: "File "style.py", line 111, in input_image = tf.Variable(np.expand_dims(images[0,:,:,:])) TypeError: expand_dims() takes exactly 2 arguments (1 given)"
I wonder if someone has the same error message.

Thanks!

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.