norm

Normalises a network on the last axis, scale decides if there is a learnable multiplicative factor

Arguments

• g: A grap Class containing an Adjacency Matrix and a Feature vector, as well as a state Class containing the current standart Values for gs(=Graph Size, Number of Nodes in the Graph) and param (=Parameter Count, Number of Features for each Node)
• scale=True: Weather the output of the BatchNormalisationLayer has a learnable scaling Factor. Can be useful to disable this in special Situations, for example, when working in front of an Autoencoder