PyTorch: Difference between revisions

Revision as of 10:13, 10 May 2024

Revision as of 10:13, 10 May 2024

Line 46:

{{main|Neural network (machine learning)}}

PyTorch defines a module called nn (<code>torch.nn</code>) to describe neural networks and to support training. This module offers a comprehensive collection of building blocks for neural networks, including various layers and activation functions, enabling the construction of complex models. Custom networksNetworks are built by inheriting from the <code>torch.nn</code> module and defining the <code>forwaedforward()</code> function.

== Example ==