Unlike most of the algorithms in deep learning, NST optimizes a cost function to get pixel values. An NST implementation generally uses a pre-trained convolutional network.
It is simply the idea of using a network trained on one task and putting it to use on an entirely new task.
The following are the three component loss functions:
- Content loss
- Style loss
- Total-variation loss
Each component is individually computed and then combined in a single meta-loss function. By minimizing the meta-loss function, we will be, in turn, jointly optimizing the content, style, and total-variation loss as well.
