What are “VGG54” and “VGG22” derived from the VGG19 CNN?

2017-12-31 16:31:11

In the paper Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network by Christian Ledig et at. the distance between images (used in the loss function) is calculated from feature maps extracted from the VGG19 network. The two used in the article are (a bit confusingly) called VGG22 and VGG54.

What are these feature maps?

What do the designations "22" and "54" mean?