This is an impelementation of Style Transfer Net in the paper Image Style Transfer Using Convolutional Neural Networks, by Gatys in PyTorch and from the course Intro to Deep Learning with PyTorch.
In this paper, style transfer uses the features found in the 19-layer VGG Network, which is comprised of a series of convolutional and pooling layers, and a few fully-connected layers.
Run this command on your terminal
$ git clone https://github.com/AhmedTM/StyleCNN
or you can download it directly from github
Help:
$ python train.py -h
Options:
--content-path Path to the content image.
--style-path Path to the style image.
--epochs Number of iterations to update your image.
--alpha The content error weight.
--beta The style error weight.
| Content image | Style image | Output image |
|---|---|---|