NengoDL 2.2.1 released

The NengoDL team is pleased to announce the release of NengoDL 2.2.1.

What is NengoDL?

NengoDL is a backend for Nengo that integrates deep learning methods (supported by the TensorFlow framework) with other Nengo modelling tools. This allows users to optimize their models using deep learning training methods, improves simulation speed (on CPU or GPU), and makes it easy to insert TensorFlow models (such as deep learning architectures) into Nengo networks.

How do I use it?

To use NengoDL, replace instances of nengo.Simulator with nengo_dl.Simulator.

For example, if you have a network called net and you run it as

with nengo.Simulator(net) as sim:

you would change that to

with nengo_dl.Simulator(net) as sim:

and that’s it!

Information on accessing the more advanced features of NengoDL can be found in the documentation.

What’s new?

This is a minor release to incorporate some improvements to the package infrastructure. It does not contain any significant user-facing changes. This is the final release that will be cross-compatible between TensorFlow 1.0 and the newly released TensorFlow 2.0 (unless we discover any issues that require a minor bugfix release). The next major release will be NengoDL 3.0, which will be a significant reworking of NengoDL for TensorFlow 2.0 (already in progress). Check out the GitHub release page for a full changelog.

How do I get it?

To install NengoDL, we recommend using pip:

pip install nengo-dl

More detailed installation instructions can be found here.

Where can I learn more?

Where can I get help?

You’re already there! If you have an issue upgrading or have any other questions, please post them in this forum.