https://github.com/arnoutdevos/styletransfertensorflow
Implementation of "A Neural Algorithm of Artistic Style" in TensorFlow
https://github.com/arnoutdevos/styletransfertensorflow
style-transfer tensorflow
Last synced: 3 months ago
JSON representation
Implementation of "A Neural Algorithm of Artistic Style" in TensorFlow
- Host: GitHub
- URL: https://github.com/arnoutdevos/styletransfertensorflow
- Owner: ArnoutDevos
- Created: 2018-01-08T14:42:59.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2018-01-09T10:24:31.000Z (over 8 years ago)
- Last Synced: 2025-01-08T17:22:05.603Z (over 1 year ago)
- Topics: style-transfer, tensorflow
- Language: Python
- Size: 9.98 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# StyleTransferTensorFlow
Implementation of the paper "[A Neural Algorithm of Artistic Style](http://arxiv.org/abs/1508.06576)" in TensorFlow
The general idea is to take two images, and produce a new image that reflects the content of one but the artistic “style” of the other. We will do this by first formulating a loss function that matches the content and style of each respective image in the feature space of a deep neural network, and then performing gradient descent on the pixels of the image itself.
A more verbose version giving a deeper explanation and going over equations can be found in the following blogpost [A Neural Algorithm of Artistic Style](https://arnoutdevos.github.io/A-Neural-Algorithm-of-Artistic-Style/).
## Usage
### Prerequisites
1. Python 3
2. TensorFlow
3. Python packages : NumPy, SciPy
4. Pretrained VGG19 file : [imagenet-vgg-verydeep-19.mat](http://www.vlfeat.org/matconvnet/models/imagenet-vgg-verydeep-19.mat)
* Download the file from the link above.
* Save the file under `model/`
### Running
```
python StyleTransferTensorFlow.py
```