This is a Keras implementation of the paper A Neural Algorithm of Artistic Style by Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge. The paper presents an algorithm for combining the content of one image with the style of another image using convolutional neural networks. Here are some examples of the results that can be obtained with this algorithm:
- Python
- Keras 2.2.4
- Pandas 0.23.4
- Numpy 1.16.2
- Scipy 1.1.0
- Matplotlib
git clone https://github.com/Roshan818/Neural-Style-Transfer.git
cd Neural-Style-Transfer
pip install -r requirements.txt
mkdir input
cd input
mkdir vgg19
mkdir best-artworks-of-all-time
mkdir image-classification
cd ..
- Download the VGG-19 model here and place it in the
input/vgg19
folder. - Download the
best-artworks-of-all-time
dataset here and place it in theinput\best-artworks-of-all-time
. - Download the
image-classification
dataset here and place it in theinput\image-classification
.
Run the file style-transfer-deep-learning-algorithm.ipynb
in Jupyter Notebook.