hxtorch.spiking.modules.hx_module.HXHardwareEntityMixin

class hxtorch.spiking.modules.hx_module.HXHardwareEntityMixin(execution_instance: Optional[ExecutionInstance] = None)

Bases: object

__init__(execution_instance: Optional[ExecutionInstance] = None) → None

Parameters: execution_instance – Execution instance to place to.

Methods

`__init__`([execution_instance])	param execution_instance Execution instance to place to.
`add_to_input_generator`(input, builder)	Add the input to an input module to grenades input generator.
`configure_hw_entity`(neuron_id, neuron_block, …)	Configures a neuron in the given layer with its specific properties.
`extra_repr`()	Add additional information
`post_process`(hw_data, runtime)	This methods needs to be overridden for every derived module that demands hardware observables and is intended to translated hardware- affine datatypes returned by grenade into PyTorch tensors.
`register_hw_entity`()	Register Module in member Experiment
`reset_changed_since_last_run`()	Reset changed_since_last_run.

Attributes

changed_since_last_run

Getter for changed_since_last_run.

add_to_input_generator(input: NeuronHandle, builder: grenade.network.InputGenerator) → None

Add the input to an input module to grenades input generator.

Parameters

module – The module to add the input for.
builder – Grenade’s logical network builder.

property changed_since_last_run

Getter for changed_since_last_run.

Returns: Boolean indicating wether module changed since last run.

configure_hw_entity(neuron_id: int, neuron_block: pylola_vx_v3.NeuronBlock, coord: pyhalco_hicann_dls_vx_v3.LogicalNeuronOnDLS) → pylola_vx_v3.NeuronBlock

Configures a neuron in the given layer with its specific properties. The neurons digital event outputs are enabled according to the given spiking mask.

Parameters

neuron_id – In-population neuron index.
neuron_block – The neuron block hardware entity.
coord – Coordinate of neuron on hardware.

Returns

Configured neuron block.

extra_repr() → str: Add additional information

post_process(hw_data: HardwareObservables, runtime: float) → Tuple[Optional[torch.Tensor], …]

This methods needs to be overridden for every derived module that demands hardware observables and is intended to translated hardware- affine datatypes returned by grenade into PyTorch tensors.

Parameters

hw_data – A HardwareObservables instance holding the hardware data assigned to this module.
runtime – The requested runtime of the experiment on hardware in s.
dt – The expected temporal resolution in hxtorch.

Returns

Hardware data represented as torch.Tensors. Note that torch.Tensors are required here to enable gradient flow.

register_hw_entity() → None: Register Module in member Experiment

reset_changed_since_last_run() → None: Reset changed_since_last_run. Sets the corresponding flag to false.