timesead.models.reconstruction.fedformer

Classes

FEDformer

FEDformer performs the attention mechanism on frequency domain and achieved O(N) complexity

Module Contents

class timesead.models.reconstruction.fedformer.FEDformer(window_size: int, input_dim: int, moving_avg: int = 25, model_dim: int = 128, dropout: float = 0.1, num_heads: int = 8, fcn_dim: int = 128, activation: str = 'gelu', encoder_layers: int = 3, version: str = 'fourier', mode_select: str = 'random', modes: int = 32)

Bases: timesead.models.BaseModel

FEDformer performs the attention mechanism on frequency domain and achieved O(N) complexity Paper link: https://proceedings.mlr.press/v162/zhou22g.html

version: str, for FEDformer, there are two versions to choose, options: [Fourier, Wavelets]. mode_select: str, for FEDformer, there are two mode selection method, options: [random, low]. modes: int, modes to be selected.

Parameters:

• window_size (int)

• input_dim (int)

• moving_avg (int)

• model_dim (int)

• dropout (float)

• num_heads (int)

• fcn_dim (int)

• activation (str)

• encoder_layers (int)

• version (str)

• mode_select (str)

• modes (int)

seq_len

version = 'fourier'

mode_select = 'random'

modes = 32

decomp

enc_embedding

encoder

projection

forward(inputs: Tuple[torch.Tensor, Ellipsis]) → Tuple[torch.Tensor, Ellipsis]

Parameters:

inputs (Tuple[torch.Tensor, Ellipsis])

Return type:

Tuple[torch.Tensor, Ellipsis]