Keras -> SNN IPython notebook

CHANGES.rst

@@ -34,6 +34,12 @@ Release history
   the converted Nengo objects, to make it easier to access converted components.
   (`#134`_)
 - Compatible with TensorFlow 2.2.0. (`#140`_)
+- Added a new ``synapse`` argument to the Converter, which can be used to automatically
+  add synaptic filters on the output of neural layers during the conversion process.
+  (`#141`_)
+- Added a `new example <https://www.nengo.ai/nengo-dl/examples/keras-to-snn.html>`__
+  demonstrating how to use the NengoDL Converter to convert a Keras model to a spiking
+  Nengo network. (`#141`_)
 
 **Changed**
 
@@ -65,6 +71,7 @@ Release history
   data to the wrong input node. This warning can be avoided by passing data for
   all nodes, or using the dictionary input style if you want to only pass data for
   a specific node. (`#139`_)
+- Dictionaries returned by ``sim.predict/evaluate`` will now be ordered. (`#141`_)
 
 **Fixed**
 
@@ -93,6 +100,7 @@ Release history
 .. _#137: https://github.com/nengo/nengo-dl/pull/137
 .. _#139: https://github.com/nengo/nengo-dl/pull/139
 .. _#140: https://github.com/nengo/nengo-dl/pull/140
+.. _#141: https://github.com/nengo/nengo-dl/pull/141
 .. _#142: https://github.com/nengo/nengo-dl/pull/142
 
 3.1.0 (March 4, 2020)

README.rst

@@ -60,8 +60,9 @@ adds a number of unique features, such as:
 - optimizing the parameters of a model through deep learning
   training methods (using the Keras API)
 - faster simulation speed, on both CPU and GPU
-- inserting networks defined using TensorFlow (such as
-  deep learning architectures) directly into a Nengo model
+- automatic conversion from Keras models to Nengo networks
+- inserting  TensorFlow code (individual functions or whole
+  network architectures) directly into a Nengo model
 
 **Documentation**
 

docs/converter.rst

@@ -151,3 +151,9 @@ successfully transformed into a native Nengo network:
 
     converter = nengo_dl.Converter(model, allow_fallback=False)
     assert converter.verify()
+
+Examples
+--------
+
+* :doc:`examples/keras-to-snn`
+* :doc:`examples/tensorflow-models`

docs/examples.rst

@@ -33,6 +33,7 @@ These examples illustrate some different possible use cases for NengoDL:
 
     examples/tensorflow-models
     examples/spiking-mnist
+    examples/keras-to-snn
     examples/lmu
     examples/spa-retrieval
     examples/spa-memory