ceshine/fast-neural-style
Pytorch Implementation of Perceptual Losses for Real-Time Style Transfer and Super-Resolution
| repo name | ceshine/fast-neural-style |
| repo link | https://github.com/ceshine/fast-neural-style |
| homepage | |
| language | Jupyter Notebook |
| size (curr.) | 12705 kB |
| stars (curr.) | 134 |
| created | 2017-07-31 |
| license | |
fast-neural-style
July 2018 Update:
- Upgrade to PyTorch 0.4.0.
- Minor Refactor.
- Allow assigning an independent style weight for each layer.
- Provide a Dockerfile
The code to the first blog post about this project can be found in tag 201707.
Stylize Script Usage Example
python stylize.py models/model_rain_princess_cropped.pth content_images/pic.jpg pic-512.jpg --resize=512
Old README
This personal fun project is heavily based on abhiskk/fast-neural-style with some changes and a video generation notebook/script:
- Use the official pre-trained VGG model
- Output intermediate results during training
- Add Total Variation Regularization as described in the paper
The model uses the method described in Perceptual Losses for Real-Time Style Transfer and Super-Resolution along with Instance Normalization.
