We now thoroughly know that top layers of a convolutional network detect lower level features and the deeper layers detect high-level features of an image. But what about the middle layers? They hold content. And as we want the generated image G to have similar contents as the input, our content image C, we would use some activation layers in between to represent content of an image.
We are going to get more visually pleasing outputs if we choose the middle layers of the network ourselves, meaning that it's neither too shallow, nor too deep.
The content loss or feature reconstruction loss (which we want to minimize) can be represented as the following:
Here, nW, nH, and nC are width, height, and number of ...
