Multi-style Generative Network for Real-time 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} } |
We also provide PyTorch implementation and MXNet implementation. Please install Torch7 with cuda and cudnn support. The code has been tested on Ubuntu 16.04 with Titan X Pascal and Maxwell.
luarocks install https://raw.githubusercontent.com/zhanghang1989/MSG-Net/master/texture-scm-1.rockspec
git clone [email protected]:zhanghang1989/MSG-Net.git
cd MSG-Net/experiments
bash models/download_models.sh
qlua webcam.lua
th test.lua -input_image images/content/venice-boat.jpg -image_size 1024
eog stylized
Please follow this tutorial to train a new model.
The code benefits from outstanding prior work and their implementations including: