qualia_plugin_snn.learningmodel.pytorch.QuantizedSMLP module

Contains the template for a quantized spiking multi-layer perceptron.

class qualia_plugin_snn.learningmodel.pytorch.QuantizedSMLP.QuantizedSMLP

Bases: SNN

Quantized spiking multi-layer perceptron template.

Should have topology identical to qualia_plugin_snn.learningmodel.pytorch.SMLP.SMLP but with layers replaced with their quantized equivalent.

__init__(input_shape: tuple[int, ...], output_shape: tuple[int, ...], units: list[int], quant_params: QuantizationConfig, timesteps: int, neuron: RecursiveConfigDict | None = None) → None

Construct QuantizedSMLP.

Parameters:

• input_shape (tuple[int, ...]) – Input shape

• output_shape (tuple[int, ...]) – Output shape

• units (list[int]) – List of torch.nn.Linear layer out_features to add in the network

• quant_params (QuantizationConfig) – Quantization configuration dict, see qualia_core.learningmodel.pytorch.Quantizer.Quantizer

• neuron (RecursiveConfigDict | None) – Spiking neuron configuration, see qualia_plugin_snn.learningmodel.pytorch.SNN.SNN.__init__()

• timesteps (int) – Number of timesteps

Return type:

None

forward(input: Tensor) → Tensor

Forward calls each of the MLP layers sequentially.

Parameters:

input (Tensor) – Input tensor

Returns:

Output tensor

Return type:

Tensor