← Back to API reference

neuraltrain.models.common.FourierEmb

pydantic model neuraltrain.models.common.FourierEmb

Configuration for Fourier positional embedding.

Parameters:

• n_freqs – Number of frequencies (harmonics) used to encode one dimension.

• total_dim –

  If provided instead of n_freqs, this will be used to compute the number of frequencies following this relationship:

  n_freqs = (total_dim / 2) ** (1 / n_dims)

  If the resulting n_freqs is not an integer an exception will be raised.

• n_dims – Number of dimensions to embed. This should be 2 for 2D positions (e.g. MNE layouts) or 3 for 3D positions (e.g. MNE montages).

• margin – How much to extend the range of the embedding to avoid edge effects.

Fields:

• margin (float)

• n_dims (int)

• n_freqs (int | None)

• total_dim (int | None)

field n_freqs: int | None = 12

field total_dim: int | None = None

field n_dims: int = 2

field margin: float = 0.2

build() → FourierEmbModel

← Back to API reference