Builder

The Builder is in charge of mapping (groups of) Nengo operators to the builder objects that know how to translate those operators into a TensorFlow graph.

class nengo_dl.builder.Builder

Manages the operator build classes known to the nengo_dl build process.

classmethod pre_build(ops, signals, op_builds, config)

Setup step for build classes, in which they compute any of the values that are constant across simulation timesteps.

Parameters:

ops : tuple of Operator

The operator group to build into the model

signals : signals.SignalDict

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

op_builds : dict of {tuple of Operator, :class:~`.op_builders.OpBuilder`}

pre_build will populate this dictionary with the OpBuilder objects (which execute the pre-build step in their __init__)

classmethod build(ops, signals, op_builds)

Build the computations implementing a single simulator timestep.

Parameters:

ops : tuple of Operator

The operator group to build into the model

signals : signals.SignalDict

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

op_builds : dict of {tuple of Operator, :class:~`.op_builders.OpBuilder`}

Mapping from operator groups to the pre-built builder objects

classmethod register(nengo_op)

A decorator for adding a class to the build function registry.

Parameters:

nengo_op : Operator

The operator associated with the build function being decorated.

class nengo_dl.builder.OpBuilder(ops, signals, config)

The constructor should set up any computations that are fixed for this op (i.e., things that do not need to be recomputed each timestep).

Parameters:

ops : list of Operator

The operator group to build into the model

signals : signals.SignalDict

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

config : BuildConfig

General repository for config information builders might want (conglomerated into this object so that we can add/remove config data without having to change the function signature all the time).

build_step(signals)

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

Parameters:

signals : signals.SignalDict

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

Returns:

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

build_post(ops, signals, sess, rng)

This function will be called after the graph has been built and session/variables initialized.

This should be used to build any random aspects of the operator.

Note that this function may be called multiple times per session, so it should modify the graph in-place.

Parameters:

ops : list of Operator

The operator group to build into the model

signals : signals.SignalDict

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

sess : tf.Session

The initialized simulation session

rng : RandomState

Seeded random number generator

class nengo_dl.builder.BuildConfig

Stores configuration parameters that may be relevant to parts of the build process.

Parameters:

inference_only : bool

If True the network should be constructed in “inference only” mode (not including any support for training operations).

lif_smoothing : float

Smoothing parameter for LIF gradient approximation.

Create new instance of BuildConfig(inference_only, lif_smoothing)