norse.torch.functional.receptive_field.temporal_scale_distribution

norse.torch.functional.receptive_field.temporal_scale_distribution(n_scales: int, min_scale: float = 1, max_scale: float | None = None, c: float | None = 1.41421)

Provides temporal scales according to [Lindeberg2016]. The scales will be logarithmic by default, but can be changed by providing other values for c.

Arguments:

n_scales (int): Number of scales to generate min_scale (float): The minimum scale max_scale (Optional[float]): The maximum scale. Defaults to None. If set, c is ignored. c (Optional[float]): The base from which to generate scale values. Should be a value

between 1 to 2, exclusive. Defaults to sqrt(2). Ignored if max_scale is set.

[Lindeberg2016]

Lindeberg 2016, Time-Causal and Time-Recursive Spatio-Temporal Receptive Fields, https://link.springer.com/article/10.1007/s10851-015-0613-9.