The NengoDL team is happy to announce the release of NengoDL 3.2.0.
What is NengoDL?
NengoDL is a backend for Nengo that integrates deep learning methods (supported by the TensorFlow framework) with other Nengo modelling tools. NengoDL allows users to optimize their models using deep learning training methods, improves simulation speed (on CPU or GPU), can automatically convert Keras models to Nengo networks, and makes it easy to insert TensorFlow code (individual functions or whole network 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:
sim.run(10)
you would change that to
with nengo_dl.Simulator(net) as sim:
sim.run(10)
and that’s it!
Information on accessing the more advanced features of NengoDL can be found in the documentation.
What’s new?
In this release we have continued to improve the NengoDL Converter, including support for more layer types, two new options (scale_firing_rates and synapse) to aid in converting non-spiking Keras models to spiking Nengo networks, and a new .layers data structure to make it easier to access the converted Nengo objects. And we added a new example showing how to use the Converter in practice. We’ve also cleaned up how NengoDL treats trainable parameters, non-trainable parameters, and simulation state internally, which should provide a more consistent experience overall when doing things like saving and loading weights. 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.