Real-time neural style transfer via meta networks
Switch branches/tags
Nothing to show
Clone or download
Latest commit cebf7e2 Aug 6, 2018
Permalink
Failed to load latest commit information.
build add data folder Feb 7, 2018
include/caffe add data folder Feb 7, 2018
matlab update makefile Feb 5, 2018
python first commit Jun 4, 2018
src add data folder Feb 7, 2018
tools update makefile Feb 5, 2018
LICENSE LICENSE Mar 23, 2018
Makefile update makefile Feb 5, 2018
Makefile~ add data folder Feb 7, 2018
README.md Update README.md Aug 6, 2018
libcaffe.a add data folder Feb 7, 2018
libcaffe.so add data folder Feb 7, 2018

README.md

License

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}
}

Installation

This library is based on Caffe. CuDNN 7 and NCCL 1 are required. Please follow the installation instruction of Caffe.

Meta Network Architecture

Examples

The size of image transformation network for the following images is 7MB.

The size of image transformation network for the following images is 449KB.

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 is 449KB.
    Meta model train_32 (968M), generated model is 7MB.

Put these models into python/model/ and modify the model name in demo.py.

Pytorch implementation

https://ypw.io/style-transfer/