hxtorch.spiking.modules.hx_module.HXTorchBaseModule

class hxtorch.spiking.modules.hx_module.HXTorchBaseModule

Bases: hxtorch.spiking.modules.hx_module.HXTorchFunctionMixin, torch.nn.modules.module.Module

__init__() → None

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Methods

__init__()	Initialize internal Module state, shared by both nn.Module and ScriptModule.
exec_forward(input, output)	Inject hardware observables into TensorHandles or execute forward in mock-mode.
forward(*input)	Forward method registering layer operation in given experiment. Input and output references will hold corresponding data as soon as ‘hxtorch.run’ in executed. :param 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.
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.
post_simulation_processing(output)

Attributes

exec_forward(input: Union[Tuple[types.Handle_tensor], types.Handle_tensor], output: types.Handle_tensor) → None

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

forward(*input: Union[Tuple[types.Handle_tensor], types.Handle_tensor]) → types.Handle_tensor

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

post_process(hw_data: hxtorch.spiking.observables.HXTorchObservables, runtime: int) → Optional[Tuple[Optional[torch.Tensor, None], …], None]

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 us.

• 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.

post_simulation_processing(output) → None