styletransfer
styletransfer copied to clipboard
Real-time neural style transfer via meta networks
Neural Style Transfer
This repository is for [Neural Style Transfer Via Meta Networks]. The meta network takes in the style image and generated an image transformation network for neural style transfer. The fast generated model is only 449KB
, which is able to real-time execute on a mobile device. For more details please refer and cite this paper
@inproceedings{shen2018style,
author = {Falong Shen, Shuicheng Yan and Gang Zeng},
title = {Neural Style Transfer Via Meta Networks},
booktitle = {CVPR2018},
year = {2018}
}
![](https://github.com/shenfalong/styletransfer/raw/master/python/video.gif)
Installation
This library is based on Caffe. CuDNN 7 and NCCL 1 are required. Please follow the installation instruction of Caffe.
Meta Network Architecture
![](https://github.com/shenfalong/styletransfer/raw/master/python/network.png)
Examples
The size of image transformation network for the following images is 7MB
.
![](https://github.com/shenfalong/styletransfer/raw/master/python/1.png)
![](https://github.com/shenfalong/styletransfer/raw/master/python//2.png)
The size of image transformation network for the following images is 449KB
.
![](https://github.com/shenfalong/styletransfer/raw/master/python/4.png)
Scripts
Python code. Please execute the scripts in Python folder. Meta model is very huge while the generated model is very small.
- pretrained meta models
Meta model train_8 (
130M
), generated model is449KB
. Meta model train_32 (968M
), generated model is7MB
.
Put these models into python/model/ and modify the model name in demo.py.
Pytorch implementation
https://ypw.io/style-transfer/