mirgahney / nural_art

Implementation of Artistic Style Transfer with Artificial Neural Network

Nural_Art

Implementation of Image Style Transfer Using Convolutional Neural Networks.

In this paper, style transfer uses the features found in the 19-layer VGG Network, which is comprised of a series of convolutional and pooling layers, and a few fully-connected layers. In the image below, the convolutional layers are named by stack and their order in the stack. Conv_1_1 is the first convolutional layer that an image is passed through, in the first stack. Conv_2_1 is the first convolutional layer in the second stack. The deepest convolutional layer in the network is conv_5_4.

Requirements :

• Torch >= 0.04
• Torchvision >= 0.2.1

To run the code:

python generate_images.py

The code will reads the images from Images folder and the result will be saved in the same folder under name result.

Sample of the result:

The result obtained by running the code with content_weight = 1 and style_weight = 1e6 on several content images and with a famous style paints.