hxtorch.spiking.modules.sparse_synapse.Projection

class hxtorch.spiking.modules.sparse_synapse.Projection(*prj_args, **prj_kwargs)

Bases: hxtorch.spiking.modules.hx_module.HXTorchBaseModule, hxtorch.core.modules.projection.Projection

Base class for projections on BSS-2

__init__(*prj_args, **prj_kwargs) → None: Initialize internal Module state, shared by both nn.Module and ScriptModule.

Methods

`__init__`(prj_args, *prj_kwargs)	Initialize internal Module state, shared by both nn.Module and ScriptModule.
`extra_repr`()	Add additional information
`post_process`(args, *kwargs)	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.
`source_population`()
`target_population`()

Attributes

changed_input_data: bool

changed_topology: bool

extra_repr() → str: Add additional information

in_features: int

out_features: int

output_type: alias of types.Handle_graded_spikes

post_process(*args, **kwargs) → 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.

source_population() → BasePopulation

target_population() → BasePopulation

training: bool

weight: torch.Tensor