timesead.models.reconstruction.autoformer

Classes

Autoformer

Autoformer is the first method to achieve the series-wise connection,

Module Contents

class timesead.models.reconstruction.autoformer.Autoformer(window_size: int, input_dim: int, moving_avg: int = 25, model_dim: int = 128, dropout: float = 0.1, attention_factor: int = 1, num_heads: int = 8, fcn_dim: int = 128, activation: str = 'gelu', encoder_layers: int = 3)

Bases: timesead.models.BaseModel

Autoformer is the first method to achieve the series-wise connection, with inherent O(LlogL) complexity Paper link: https://openreview.net/pdf?id=I55UqU-M11y

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Parameters:

• window_size (int)

• input_dim (int)

• moving_avg (int)

• model_dim (int)

• dropout (float)

• attention_factor (int)

• num_heads (int)

• fcn_dim (int)

• activation (str)

• encoder_layers (int)

seq_len

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]