sinabs

Network

class Network(analog_model: Optional = None, spiking_model: Optional = None, input_shape: Optional[Union[numpy.ndarray, List, Tuple]] = None, quantize_activation: bool = False, nbit_quantize: Optional[int] = None)

Class of a spiking neural network

spiking_model

torch.nn.Module, a spiking neural network model

analog_model

torch.nn.Module, an artifical neural network model

graph

pandas DataFrame

input_shape

Tuple, size of input

quantize_activation

bool, if true, the analog model will be initialized with a quantization layer after each activation

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

compare_activations(data, name_list: Optional[Union[numpy.ndarray, List, Tuple]] = None, compute_rate: bool = False, verbose: bool = False) -> ([<class 'numpy.ndarray'>], [<class 'numpy.ndarray'>])

Compare activations of the analog model and the SNN for a given data sample

Parameters

• data (np.ndarray) – Data to process

• name_list (List[str]) – list of all layer names (str) whose activations need to be compared

• compute_rate (bool) – True if you want to compute firing rate. By default spike count is returned

• verbose (bool) – print debugging logs to the terminal

Returns

A tuple of lists (ann_activity, snn_activity)

• ann_activity: output activity of the ann layers

• snn_activity: output activity of the snn layers

Return type

tuple

plot_comparison(data, name_list: Optional[Union[numpy.ndarray, List, Tuple]] = None, compute_rate=False)

Plots a scatter plot of all the activations

Parameters

• data – Data to be processed

• name_list – ArrayLike with names of all the layers of interest to be compared

• compute_rate – Compare firing rates instead of spike count

Returns

A tuple of lists (ann_activity, snn_activity)

• ann_activity: output activity of the ann layers

• snn_activity: output activity of the snn layers

Return type

tuple

reset_states()

Reset all neuron states in the submodules