hxtorch.spiking.modules.HXBaseExperimentModule

class hxtorch.spiking.modules.HXBaseExperimentModule(experiment: Experiment)

Bases: torch.nn.modules.module.Module

__init__(experiment: Experiment) → None

Parameters

experiment – Experiment to append layer to.

Methods

__init__(experiment)	param experiment Experiment to append layer to.
exec_forward(input, output, hw_map)	Inject hardware observables into TensorHandles or execute forward in mock-mode.
extra_repr()	Add additional information
forward(*input)	Forward method registering layer operation in given experiment.

Attributes

descriptor
func	Getter for function assigned to the module

descriptor = None

exec_forward(input: Union[Tuple[TensorHandle], TensorHandle], output: TensorHandle, hw_map: Dict[grenade.network.PopulationsDescriptor, Any]) → None

Inject hardware observables into TensorHandles or execute forward in mock-mode.

extra_repr() → str

Add additional information

forward(*input: Union[Tuple[hxtorch.spiking.handle.TensorHandle], hxtorch.spiking.handle.TensorHandle]) → hxtorch.spiking.handle.TensorHandle

Forward method registering layer operation in given experiment. Input and output references will hold corresponding data as soon as ‘hxtorch.run’ in executed.

Parameters

input – Reference to TensorHandle holding data tensors as soon as required.

Returns

Returns a Reference to TensorHandle holding result data associated with this layer after ‘hxtorch.run’ is executed.

abstract property func

Getter for function assigned to the module

Returns

Returns the function assigned to the module.

output_type

alias of hxtorch.spiking.handle.TensorHandle

training: bool