hxtorch.spiking

Modules

hxtorch.spiking.backend
hxtorch.spiking.calibrated_params	Generic parameter object holding hardware configurable neuron parameters.
hxtorch.spiking.datasets
hxtorch.spiking.execution_instance	Definition of ExecutionInstance, wrapping grenade.common.ExecutionInstanceID, and providing functionality for chip instance configuration
hxtorch.spiking.experiment	Defining basic types to create hw-executable instances
hxtorch.spiking.functional
hxtorch.spiking.handle	Defining tensor handles able to hold references to tensors for lazy assignment after hardware data acquisition
hxtorch.spiking.modules
hxtorch.spiking.morphology	User defined neuron morphologies.
hxtorch.spiking.neuron_placement	Defining neuron placement allocator
hxtorch.spiking.observables	Hardware observables object
hxtorch.spiking.run(experiment, runtime)	Execute the given experiment.
hxtorch.spiking.transforms
hxtorch.spiking.utils

Classes

BatchDropout(size, dropout, experiment, …)	Batch dropout layer
CalibratedParams(leak, reset, threshold, …)	Parameters for any (of currently available) forward and backward path.
ExecutionInstance(calib_path, str]] = None, …)
Experiment(mock, dt[, hw_routing_func])	Experiment class for describing experiments on hardware
HXBaseExperimentModule(experiment)
HXModule(experiment, func, …)	PyTorch module supplying basic functionality for elements of SNNs that do have a representation on hardware
HXModuleWrapper(experiment, modules, func)	Class to wrap HXModules
IAFNeuron(size, experiment, func, …[, …])	Integrate-and-fire neuron Caveat: For execution on hardware, this module can only be used in conjunction with a preceding Synapse module.
InputNeuron(size, experiment, execution_instance)	Spike source generating spikes at the times [ms] given in the spike_times array.
Neuron(size, experiment, func, …[, leak, …])	Neuron layer
NeuronHandle(spikes, v_cadc, current, v_madc)	Specialization for HX neuron observables
ReadoutNeuron(size, experiment, func, …)	Readout neuron layer
ReadoutNeuronHandle(v_cadc, current, v_madc)	Specialization for HX neuron observables
SparseSynapse(connections, experiment, func, …)	Sparse synapse layer
Synapse(in_features, out_features, …)	Synapse layer
SynapseHandle(graded_spikes)	Specialization for HX synapses
TensorHandle()	Base class for HX tensor handles.

Functions

hxtorch.spiking.run(experiment: hxtorch.spiking.experiment.Experiment, runtime: Optional[int]) → Optional[_pygrenade_vx_signal_flow.ExecutionTimeInfo]

Execute the given experiment.

TODO: Why is this a standalone function?

Parameters

• experiment – The experiment representing the computational graph to be executed on hardware and/or in software.

• runtime – Only relevant for hardware experiments. Indicates the runtime resolved with experiment.dt.