Full-Weight Aggregator

class bacon.aggregators.lsp.full_weight.FullWeightAggregator(*args, **kwargs)

aggregate_float(values: Sequence[float], a: float, weights: Sequence[float]) → float

Aggregate N scalar values with scalar andness a and N weights.

aggregate_tensor(values: Sequence[Any], andness, weights)

Aggregates two tensors using the Full Weight method.

Parameters:

• x1 (torch.Tensor) – First input tensor.

• x2 (torch.Tensor) – Second input tensor.

• andness (float) – Andness.

• w0 (float) – Weight for the first tensor.

• w1 (float) – Weight for the second tensor.

Returns:

Resulting tensor after aggregation.

Return type:

torch.Tensor