Video-Style-Transfer

Fast Style Transfer for Real-Time Video

The model uses the method described in Perceptual Losses for Real-Time Style Transfer and Super-Resolution along with Instance Normalization. The saved-models for examples shown in the README can be downloaded from here.

Requirements

• Python 3.5.2
• OpenCV 3.4.2
• Numpy 1.14.3
• argparse 1.1
• Pytorch 0.4.1

Usages

download repo

• download this repo by the following instruction:

  $ git clone https://github.com/brightyoun/Video-Style-Transfer.git
  $ cd Video-Style-Transfer
  

Demo

• Demo

  $ python neural_style.py eval --model saved_models/[MODEL_PATH] --cuda [1]
  

Train model

python neural_style/neural_style.py train --dataset </path/to/train-dataset> --style-image </path/to/style/image> --save-model-dir </path/to/save-model/folder> --epochs 2 --cuda 1

References

• [ Perceptual Losses for Real-Time Style Transfer and Super-Resolution] (https://link.springer.com/chapter/10.1007/978-3-319-46475-6_43)

Contacts

• Email : [email protected]