Generative Adversarial Networks Projects

The architecture of SRGANs

In SRGANs, both of the networks are deep convolution neural networks. They contain convolution layers and upsampling layers. Each convolution layer is followed by a batch normalization operation and an activation layer. We will explore the networks in detail in the following sections. The architecture of an SRGAN is shown in the following diagram:

Let's have a look at the architecture of the networks in detail in the following sections.