Build Nengo Processes into the TensorFlow graph.

class nengo_dl.processes.SimProcessBuilder(ops, signals, rng)[source]

Builds a group of SimProcess operators.

Calls the appropriate sub-build class for the different process types.

TF_PROCESS_IMPL : list of Process

the process types that have a custom implementation


This function builds whatever computations need to be executed in each simulation timestep.

signals : signals.SignalDict

mapping from Signal to tf.Tensor (updated by operations)

list of ``tf.Tensor``, optional

if not None, the returned tensors correspond to outputs with possible side-effects, i.e. computations that need to be executed in the tensorflow graph even if their output doesn’t appear to be used

class nengo_dl.processes.GenericProcessBuilder(ops, signals, rng)[source]

Builds all process types for which there is no custom Tensorflow implementation.


These will be executed as native Python functions, requiring execution to move in and out of Tensorflow. This can significantly slow down the simulation, so any performance-critical processes should consider adding a custom Tensorflow implementation for their type instead.

class nengo_dl.processes.LowpassBuilder(ops, signals)[source]

Build a group of LinearFilter neuron operators.