jaxsnn.ConversionConfig

class jaxsnn.ConversionConfig(t_max: float, n_spikes: Dict[str, int], external: bool = False, duplication: Optional[int, None] = None, solver: str = 'eventprop')

Bases: object

Configuration for the conversion from NIR to jaxsnn.

Attributes:

t_max: Maximum time for the simulation. n_spikes: Dictionary with number of spikes to simulate per layer. external: If True, forward pass is executed externally. duplication: Number of duplications for the external hardware LIF. solver: Solver to use for the LIF neuron. Either “eventprop” for the EventProp algorithm or “analytical” for the time-to-first-spike solver.

__init__(t_max: float, n_spikes: Dict[str, int], external: bool = False, duplication: Optional[int, None] = None, solver: str = 'eventprop') → None

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__(t_max, n_spikes[, external, …])

Initialize self.

Attributes

duplication
external
solver

duplication: Optional[int, None] = None

external: bool = False

n_spikes: Dict[str, int]

solver: str = 'eventprop'

t_max: float