NengoDL 2.2.0 released

The NengoDL team is delighted to announce the release of NengoDL 2.2.0 (and 2.1.0, since I forgot to write a release announcement for that one!).

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 a convolutional neural network) 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?

I forgot to write a release announcement for 2.1.0, so I’ll mention highlights since 2.0.0 here. NengoDL is now compatible with the TensorFlow 2.0 beta release, and also supports all of the new features introduced in Nengo core recently (including sparse Transforms, stateful Processes, and the new linear synapse implementation). We’ve also added a lot of new documentation, including two new tutorials and an example demonstrating how to insert a Keras network into NengoDL. We’ve consolidated some useful objective functions in nengo_dl.objectives, and deprecated passing a string "mse" for the objective (use nengo_dl.obj.mse instead). And, as always, we’ve fixed some bugs! 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.

1 Like