Upscaling the resolution of images with Super-Resolution GANs (SRGANs)

In Chapter 3, Convolutional Neural Networks, we demonstrated how a CNN can be used to autoencode an image to obtain a compression of the image. In the digital age, it's even more important to be able to scale up the resolution of an image to high quality. For example, a compressed version of an image can easily be shared via the internet. When the image arrives at the receiver, its quality will need to be increased, also known as Super-Resolution imaging (SR). In the following recipe, we will show you how to increase the resolution of an image by training deep learning with the PyTorch framework.

How to do it...

1. First, we need to import...