jcjohnson/fast-neural-style
Feedforward neural networks apply artistic styles to images in real-time using perceptual loss optimization.
Not currently ranked — collecting fresh signals.
star history
This repository implements the ECCV 2016 paper Perceptual Losses for Real-Time Style Transfer and Super-Resolution by Johnson et al., using Torch/Lua. It trains feedforward convolutional networks to apply artistic styles to images hundreds of times faster than optimization-based approaches. The project also includes an implementation of instance normalization to improve stylization quality, and provides pre-trained models, webcam demo, and training code for new style transfer models.
Frequently asked
- What is jcjohnson/fast-neural-style?
- Feedforward neural networks apply artistic styles to images in real-time using perceptual loss optimization.
- Is fast-neural-style open source?
- Yes — jcjohnson/fast-neural-style is an open-source project tracked on heatdrop.
- What language is fast-neural-style written in?
- jcjohnson/fast-neural-style is primarily written in Lua.
- How popular is fast-neural-style?
- jcjohnson/fast-neural-style has 4.4k stars on GitHub.
- Where can I find fast-neural-style?
- jcjohnson/fast-neural-style is on GitHub at https://github.com/jcjohnson/fast-neural-style.