https://github.com/kautenja/a-neural-algorithm-of-artistic-style
Keras implementation of "A Neural Algorithm of Artistic Style"
https://github.com/kautenja/a-neural-algorithm-of-artistic-style
creative-ai keras-tensorflow style-transfer
Last synced: about 1 month ago
JSON representation
Keras implementation of "A Neural Algorithm of Artistic Style"
- Host: GitHub
- URL: https://github.com/kautenja/a-neural-algorithm-of-artistic-style
- Owner: Kautenja
- License: mit
- Created: 2018-01-14T21:37:23.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2023-03-25T00:59:56.000Z (about 2 years ago)
- Last Synced: 2025-02-27T09:37:40.594Z (2 months ago)
- Topics: creative-ai, keras-tensorflow, style-transfer
- Language: Jupyter Notebook
- Homepage:
- Size: 687 MB
- Stars: 117
- Watchers: 4
- Forks: 37
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# A Neural Algorithm of Artistic Style (Keras Implementation)
An **implementation** of the arXiv preprint
[_A Neural Algorithm of Artistic Style [1]_](#references)
& paper
[_Image Style Transfer Using Convolutional Neural Networks [2]_](#references).
_Supports TensorFlow 2.4.1._
## Style Transfer
[style-transfer.ipynb](style-transfer.ipynb) describes the style transfer
process between a white noise image **x**, a content image **p**, and a style
representation **a**. Performing gradient descent of the content loss and
style loss with respect to **x** impressions the content of **p** into **x**,
bearing local styles, and colors from **a**.
Original Photograph Tubingen, Germany
Claude Monet Houses of Parliament
Pablo Picasso Seated Nude
Edvard Munch The Scream
Vincent van Gogh The Starry Night
William Turner The Shipwreck of The Minotaur
Wassily Kandinsky Composition VII
## Content Reconstruction
[content-reconstruction.ipynb](content-reconstruction.ipynb) describes the
content reconstruction process from white noise. Performing gradient descent
of the content loss on a white noise input **x** for a given content **p**
yields a representation of the networks activation for a given layer _l_.
Layer
Result
block1_conv1
block2_conv1
block3_conv1
block4_conv1
block4_conv2
block5_conv1
## Style Reconstruction
[style-reconstruction.ipynb](style-reconstruction.ipynb) describes the style
reconstruction process on Wassily Kandinsky's Composition VII from white
noise. Performing gradient descent of the style loss on a white noise input
**x** for a given artwork **a** yields a representation of the networks
activation for a given set of layers _L_.
Layer
Result
block1_conv1
block1_conv1, block2_conv1
block1_conv1, block2_conv1, block3_conv1
block1_conv1, block2_conv1, block3_conv1, block4_conv1
block1_conv1, block2_conv1, block3_conv1, block4_conv1, block5_conv1
## Content Layer
[content-layer.ipynb](content-layer.ipynb) visualizes how the style transfer
is affected by using different layers for content loss.
Layer
Result
block1_conv1
block2_conv1
block3_conv1
block4_conv1
block5_conv1
## Style Layers
[style-layers.ipynb](style-layers.ipynb) visualizes how the style transfer is
affected by using different sets of layers for style loss.
Layers
Result
block1_conv1
block1_conv1, block2_conv1
block1_conv1, block2_conv1, block3_conv1
block1_conv1, block2_conv1, block3_conv1, block4_conv1
block1_conv1, block2_conv1, block3_conv1, block4_conv1, block5_conv1
## Optimizers
[optimizers.ipynb](optimizers.ipynb) employs _gradient descent_, _adam_, and
_L-BFGS_ to understand the effect of different black-box optimizers. Gatys et.
al use L-BFGS, but Adam appears to produce comparable results without as much
overhead.
Gradient Descent
Adam
L-BFGS
## TV Loss
[tv-loss.ipynb](tv-loss.ipynb) introduces total-variation loss to reduce
impulse noise in the images.
TV Loss Scale Factor
Result
0
1
10
100
1000
## Photo-Realistic Style Transfer
[photo-realistic-style-transfer.ipynb](photo-realistic-style-transfer.ipynb)
describes the photo-realistic style transfer process. Opposed to transferring
style from an artwork, this notebook explores transferring a nighttime style
from a picture of Piedmont Park at night to a daytime picture of Piedmont Park.
Content
Style
Result
## References
[_[1] L. A. Gatys, A. S. Ecker, and M. Bethge. A neural algorithm of artistic style. arXiv preprint
arXiv:1508.06576, 2015._][ref1]
[ref1]: https://arxiv.org/abs/1508.06576
[_[2] L. A. Gatys, A. S. Ecker, and M. Bethge. Image style transfer using convolutional neural networks. In
Computer Vision and Pattern Recognition (CVPR), 2016 IEEE Conference on, pages 2414–2423.
IEEE, 2016._][ref2]
[ref2]: https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Gatys_Image_Style_Transfer_CVPR_2016_paper.pdf