spd_learn.modules.LearnedSinusoidalPosition#

class spd_learn.modules.LearnedSinusoidalPosition(sequence_length=30, embed_dim=6, *, device=None, dtype=None)[source]#

Bases: Module

Add learned sinusoidal positional features to log tokens.

Parameters:

  • sequence_length (int, default=30) – Number of ordered input tokens.

  • embed_dim (int, default=6) – Triangular log-coordinate dimension.

  • device (torch.device or str, optional) – Device for parameters and buffers.

  • dtype (torch.dtype, optional) – Data type for parameters and buffers.

forward(x: Tensor) → Tensor[source]#

Encode an ordered log-token sequence.

Parameters:

x (torch.Tensor) – Log tokens of shape (batch, tokens, embed_dim).

Returns:

Encoded tokens with the input shape.

Return type:

torch.Tensor

sinusoid: Tensor#