MXNet-Gluon-Style-Transfer

This repo has been included in official MXNet repo, which provides the implementations of MSG-Net and Neural Style Transfer. We also provide PyTorch and Torch implementations.

Tabe of content

Neural Style

A Neural Algorithm of Artistic Style by Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge.

python main.py optim --content-image images/content/venice-boat.jpg --style-image images/styles/candy.jpg

--content-image: path to content image.
--style-image: path to style image.
--output-image: path for saving the output image.
--content-size: the content image size to test on.
--style-size: the style image size to test on.
--cuda: set it to 1 for running on GPU, 0 for CPU.

Real-time Style Transfer

Multi-style Generative Network for Real-time Transfer [arXiv] [project]
Hang Zhang, Kristin Dana

@article{zhang2017multistyle,
	title={Multi-style Generative Network for Real-time Transfer},
	author={Zhang, Hang and Dana, Kristin},
	journal={arXiv preprint arXiv:1703.06953},
	year={2017}
}

图片.png

Stylize Images Using Pre-trained MSG-Net

Download the pre-trained model
```
python models/download_model.py
```

Test the model

python main.py eval --content-image images/content/venice-boat.jpg --style-image images/styles/candy.jpg --model models/21styles.params --content-size 1024

If you don't have a GPU, simply set --cuda=0. For a different style, set --style-image path/to/style. If you would to stylize your own photo, change the --content-image path/to/your/photo. More options:

--content-image: path to content image you want to stylize.
--style-image: path to style image (typically covered during the training).
--model: path to the pre-trained model to be used for stylizing the image.
--output-image: path for saving the output image.
--content-size: the content image size to test on.
--cuda: set it to 1 for running on GPU, 0 for CPU.