NengoDL 3.1.0 released

The NengoDL team is happy to announce the release of NengoDL 3.1.0.

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?

The main features of this release are a number of improvements to the NengoDL Keras Converter. It now supports more layer types, and has fewer bugs! We have also made a number of improvements to the speed and memory usage of the NengoDL build process, allowing even larger models to be created in NengoDL. This release also contains support for the new transform=None Connection default in Nengo. This means that some connections that previously had a scalar transform=1 parameter now won’t have any trainable parameters. In most cases this should be the desired behaviour, but if you want the old behaviour back just explicitly set transform=1 on your Connection. 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.