NengoDL Simulator

This is the class that allows users to access the nengo_dl backend. This can be used as a drop-in replacement for nengo.Simulator (i.e., simply replace any instance of nengo.Simulator with nengo_dl.Simulator and everything will continue to function as normal).

In addition, the Simulator exposes features unique to the nengo_dl backend, such as Simulator.train().

Simulator arguments

The nengo_dl Simulator has a number of optional arguments, beyond those in nengo:nengo.Simulator, which control features specific to the nengo_dl backend. The full class documentation can be viewed below; here we will explain the practical usage of these parameters.


This specifies the floating point precision to be used for the simulator’s internal computations. It can be either tf.float32 or tf.float64, for 32 or 64-bit precision, respectively. 32-bit precision is the default, as it is faster, will use less memory, and in most cases will not make a difference in the results of the simulation. However, if very precise outputs are required then this can be changed to tf.float64.


This specifies the computational device on which the simulation will run. The default is None, which means that operations will be assigned according to TensorFlow’s internal logic (generally speaking, this means that things will be assigned to the GPU if tensorflow-gpu is installed, otherwise everything will be assigned to the CPU). The device can be set manually by passing the TensorFlow device specification to this parameter. For example, setting device="/cpu:0" will force everything to run on the CPU. This may be worthwhile for small models, where the extra overhead of communicating with the GPU outweighs the actual computations. On systems with multiple GPUs, device="/gpu:0"/"/gpu:1"/etc. will select which one to use.


This controls how many simulation iterations are executed each time through the outer simulation loop. That is, we could run 20 timesteps as

for i in range(20):
    <run 1 step>


for i in range(5):
    <run 1 step>
    <run 1 step>
    <run 1 step>
    <run 1 step>

This is an optimization process known as “loop unrolling”, and unroll_simulation controls how many simulation steps are unrolled. The first example above would correspond to unroll_simulation=1, and the second would be unroll_simulation=4.

Unrolling the simulation will result in faster simulation speed, but increased build time and memory usage.

In general, unrolling the simulation will have no impact on the output of a simulation. The only case in which unrolling may have an impact is if the number of simulation steps is not evenly divisible by unroll_simulation. In that case extra simulation steps will be executed, and then data will be truncated to the correct number of steps. However, those extra steps could still change the internal state of the simulation, which will affect any subsequent calls to So it is recommended that the number of steps always be evenly divisible by unroll_simulation.


nengo_dl allows a model to be simulated with multiple simultaneous inputs, processing those values in parallel through the network. For example, instead of executing a model three times with three different inputs, the model can be executed once with those three inputs in parallel. minibatch_size specifies how many inputs will be processed at a time. The default is None, meaning that this feature is not used and only one input will be processed at a time (as in standard Nengo simulators).

In order to take advantage of the parallel inputs, multiple inputs need to be passed to via the input_feeds argument. This is discussed in more detail below.

When using Simulator.train(), this parameter controls how many items from the training data will be used for each optimization iteration.


If set to True, nengo_dl will save the structure of the internal simulation graph so that it can be visualized in TensorBoard. This is mainly useful to developers trying to debug the simulator. This data is stored in the <nengo_dl>/data folder, and can be loaded via

tensorboard --logdir <path/to/nengo_dl>

Data will be organized according to the Network label and run number. arguments (and its variations Simulator.step()/ Simulator.run_steps()) also have some optional parameters beyond those in the standard Nengo simulator.


This parameter can be used to override the value of any input Node in a model (an input node is defined as a node with no incoming connections). For example

n_steps = 5

with nengo.Network() as net:
    node = nengo.Node([0])
    p = nengo.Probe(node)

with nengo_dl.Simulator(net) as sim:

will execute the model in the standard way, and if we check the output of node

>>> [[ 0.] [ 0.] [ 0.] [ 0.] [ 0.]]

we see that it is all zero, as defined.

input_feeds is specified as a dictionary of {my_node: override_value} pairs, where my_node is the Node to be overridden and override_value is a numpy array with shape (minibatch_size, n_steps, my_node.size_out) that gives the Node output value on each simulation step. For example, if we instead run the model via

sim.run_steps(n_steps, input_feeds={node: np.ones((1, n_steps, 1))})
>>> [[ 1.] [ 1.] [ 1.] [ 1.] [ 1.]]

we see that the output of node is all ones, which is the override value we specified.

input_feeds are usually used in concert with the minibatching feature of nengo_dl (see above). nengo_dl allows multiple inputs to be processed simultaneously, but when we construct a Node we can only specify one value. For example, if we use minibatching on the above network

mini = 3
with nengo_dl.Simulator(net, minibatch_size=mini) as sim:
>>> [[[ 0.] [ 0.] [ 0.] [ 0.] [ 0.]]
     [[ 0.] [ 0.] [ 0.] [ 0.] [ 0.]]
     [[ 0.] [ 0.] [ 0.] [ 0.] [ 0.]]]

we see that the output is an array of zeros with size (mini, n_steps, 1). That is, we simulated 3 inputs simultaneously, but those inputs all had the same value (the one we defined when the Node was constructed) so it wasn’t very useful. To take full advantage of the minibatching we need to override the node values, so that we can specify a different value for each item in the minibatch:

with nengo_dl.Simulator(net, minibatch_size=mini) as sim:
    sim.run_steps(n_steps, input_feeds={
        node: np.ones((mini, n_steps, 1)) + np.arange(mini)[:, None, None]})
>>> [[[ 0.] [ 0.] [ 0.] [ 0.] [ 0.]]
     [[ 1.] [ 1.] [ 1.] [ 1.] [ 1.]]
     [[ 2.] [ 2.] [ 2.] [ 2.] [ 2.]]]

Here we can see that 3 independent inputs have been processed during the simulation. In a simple network such as this, minibatching will not make much difference. But for larger models it will be much more efficient to process multiple inputs in parallel rather than one at a time.


If set to True, profiling data will be collected while the simulation runs. This will significantly slow down the simulation, so it should be left on False (the default) in most cases. It is mainly used by developers, in order to help identify simulation bottlenecks.

Profiling data will be saved to <nengo_dl>/data/nengo_dl_profile.json. It can be viewed by opening a Chrome browser, navigating to chrome://tracing and loading the nengo_dl_profile.json file.


class nengo_dl.simulator.Simulator(network, dt=0.001, seed=None, model=None, dtype=tf.float32, device=None, unroll_simulation=1, minibatch_size=None, tensorboard=False, step_blocks='deprecated')[source]

Simulate network using the nengo_dl backend.

network : Network or None

a network object to be built and then simulated. If None, then a built model must be passed to model instead

dt : float, optional

length of a simulator timestep, in seconds

seed : int, optional

seed for all stochastic operators used in this simulator

model : Model, optional

pre-built model object

dtype : tf.DType, optional

floating point precision to use for simulation

device : None or "/cpu:0" or "/gpu:[0-n]", optional

device on which to execute computations (if None then uses the default device as determined by Tensorflow)

unroll_simulation : int, optional

unroll simulation loop by explicitly building the given number of iterations into the computation graph (improves simulation speed but increases build time)

minibatch_size : int, optional

the number of simultaneous inputs that will be passed through the network

tensorboard : bool, optional

if True, save network output in the Tensorflow summary format, which can be loaded into Tensorboard


Resets the simulator to initial conditions.

seed : int, optional

if not None, overwrite the default simulator seed with this value (note: this becomes the new default simulator seed)

soft_reset(include_trainable=False, include_probes=False)[source]

Resets the internal state of the simulation, but doesn’t rebuild the graph.

include_trainable : bool, optional

if True, also reset any training that has been performed on network parameters (e.g., connection weights)

include_probes : bool, optional

if True, also clear probe data


Run the simulation for one time step.

kwargs : dict

see run_steps()

run(time_in_seconds, **kwargs)[source]

Simulate for the given length of time.

time_in_seconds : float

amount of time to run the simulation for

kwargs : dict

see run_steps()

run_steps(n_steps, input_feeds=None, profile=False)[source]

Simulate for the given number of steps.

n_steps : int

the number of simulation steps to be executed

input_feeds : dict of {Node: ndarray}

override the values of input Nodes with the given data. arrays should have shape (sim.minibatch_size, n_steps, node.size_out).

profile : bool, optional

if True, collect TensorFlow profiling information while the simulation is running (this will slow down the simulation)


If unroll_simulation=x is specified, and n_steps > x, this will repeatedly execute x timesteps until the the number of steps executed is >= n_steps.

train(inputs, targets, optimizer, n_epochs=1, objective='mse', shuffle=True)[source]

Optimize the trainable parameters of the network using the given optimization method, minimizing the objective value over the given inputs and targets.

inputs : dict of {Node: ndarray}

input values for Nodes in the network; arrays should have shape (batch_size, n_steps, node.size_out)

targets : dict of {Probe: ndarray}

desired output value at Probes, corresponding to each value in inputs; arrays should have shape (batch_size, n_steps, probe.size_in)

optimizer : tf.train.Optimizer

Tensorflow optimizer, e.g. tf.train.GradientDescentOptimizer(learning_rate=0.1)

n_epochs : int, optional

run training for the given number of epochs (complete passes through inputs)

objective : "mse" or callable, optional

the objective to be minimized. passing "mse" will train with mean squared error. a custom function f(output, target) -> loss can be passed that consumes the actual output and target output for a probe in targets and returns a tf.Tensor representing the scalar loss value for that Probe (loss will be averaged across Probes).

shuffle : bool, optional

if True, randomize the data into different minibatches each epoch


  • Deep learning methods require the network to be differentiable, which means that trying to train a network with non-differentiable elements will result in an error. Examples of common non-differentiable elements include LIF, Direct, or processes/neurons that don’t have a custom TensorFlow implementation (see processes.SimProcessBuilder/ neurons.SimNeuronsBuilder)
  • Most TensorFlow optimizers do not have GPU support for networks with sparse reads, which are a common element in Nengo models. If your network contains sparse reads then training will have to be executed on the CPU (by creating the simulator via nengo_dl.Simulator(..., device="/cpu:0")), or is limited to optimizers with GPU support (currently this is only tf.train.GradientDescentOptimizer). Follow this issue for updates on Tensorflow GPU support.
loss(inputs, targets, objective)[source]

Compute the loss value for the given objective and inputs/targets.

inputs : dict of {Node: ndarray}

input values for Nodes in the network; arrays should have shape (batch_size, n_steps, node.size_out)

targets : dict of {Probe: ndarray}

desired output value at Probes, corresponding to each value in inputs; arrays should have shape (batch_size, n_steps, probe.size_in)

objective : "mse" or callable

the objective used to compute loss. passing "mse" will use mean squared error. a custom function f(output, target) -> loss can be passed that consumes the actual output and target output for a probe in targets and returns a tf.Tensor representing the scalar loss value for that Probe (loss will be averaged across Probes)


Calling this function will reset all values in the network, so it should not be intermixed with calls to


Save trainable network parameters to the given path.

path : str

filepath of parameter output file


Load trainable network parameters from the given path.

path : str

filepath of parameter input file


Print current values of trainable network parameters.

msg : str, optional

title for print output, useful to differentiate multiple print calls


Close the simulation, freeing resources.


The simulation cannot be restarted after it is closed. This is not a technical limitation, just a design decision made for all Nengo simulators.


Create a vector of times matching probed data.

Note that the range does not start at 0 as one might expect, but at the first timestep (i.e., dt).

dt : float, optional

the sampling period of the probe to create a range for; if None, the simulator’s dt will be used.

check_gradients(outputs=None, atol=1e-05, rtol=0.001)[source]

Perform gradient checks for the network (used to verify that the analytic gradients are correct).

Raises a simulation error if the difference between analytic and numeric gradient is greater than atol + rtol * numeric_grad (elementwise).

outputs : tf.Tensor or list of tf.Tensor

compute gradients wrt this output (if None, computes wrt each output probe)

atol : float, optional

absolute error tolerance

rtol : float, optional

relative (to numeric grad) error tolerance


Calling this function will reset all values in the network, so it should not be intermixed with calls to