SNN

class lightautoml.ml_algo.torch_based.nn_models.SNN(n_in, n_out, hidden_size=[512, 512, 512], num_init_features=None, drop_rate=0.1, **kwargs)

Bases: Module

Realisation of ‘snn’ model.

Parameters:

• n_in (int) – Input dim.

• n_out (int) – Output dim.

• hidden_size (List[int]) – List of hidden dims.

• drop_rate (Union[float, List[float]]) – Dropout rate for each layer separately or altogether.

• num_init_features (Optional[int]) – If not none add fc layer before model with certain dim.

forward(x)

Forward-pass.

Return type:

Tensor

reset_parameters()

Init weights.