The model optimizes a loss function consisting of three terms: feature loss, style loss, and a regularization term,
The 'Feature Reconstruction' loss term leverages a network that has been pre-trained for image classification (in this case VGG-19 based on this research paper). This encourages the 'content network' to have similar feature representation as the pre-trained net.
The style loss is computed using a Gram matrix, which provides a 'good representation of our perception of style within images.'
Total Variation Regularization is used to encourage spatial smoothness.
This approach definitely produces some of the best results that I have seen so far. Enjoy the following renderings. (Click to enlarge.)
Machine Learning, TensorFlow, Deep Learning, Python, Photography