https://github.com/pavelgonchar/neural-art-mini

Lightweight version of mxnet neural art implementation
https://github.com/pavelgonchar/neural-art-mini

Last synced: 5 months ago
JSON representation

Lightweight version of mxnet neural art implementation

• Host: GitHub
• URL: https://github.com/pavelgonchar/neural-art-mini
• Owner: pavelgonchar
• License: bsd-2-clause
• Created: 2016-06-04T13:04:05.000Z (almost 9 years ago)
• Default Branch: master
• Last Pushed: 2016-06-05T15:54:12.000Z (almost 9 years ago)
• Last Synced: 2024-11-08T18:45:29.688Z (5 months ago)
• Language: Python
• Size: 15.6 MB
• Stars: 265
• Watchers: 10
• Forks: 35
• Open Issues: 2
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• Awesome-MXNet - neural-art-mini

README

        
# neural-art-mini

Lightweight version of mxnet neural art implementation using ~4.8M SqueezeNet model. Compressed model is less than 500KB

![input](input/minsk.jpg?raw=true "input")

![style](input/starry_night.jpg?raw=true "style")

![output](output/tmp_950.jpg?raw=true "output")

![animated](output/animated.gif?raw=true "animated")

Sources

-------

- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](http://arxiv.org/abs/1602.07360)

- [MXNet Neural Art](https://github.com/dmlc/mxnet/tree/master/example/neural-style)

- [SqueezeNet pre-trained model](https://github.com/DeepScale/SqueezeNet)