Unifying ML -- The Ivy Stateful API

In this post, we'll be explaining how Ivy's stateful API builds on the functional API and the ivy.Container class to provide other convenient classes in the form of optimizers, network layers and custom trainable modules, which help get your ML projects up and running very quickly! So, without further ado, let's walk through what the stateful API has to offer! The most helpful stateful Ivy class is perhaps the ivy.Module. This can be used to create custom trainable layers or entire networks. Manually defined trainable variables must be specified in the _create_variables method.