paddlets.models.anomaly.dl._mtad_gat.model

class Reconstruction(in_chunk_len: int, feature_dim: int, hidden_size: int, out_dim: int, num_layers: int, dropout: float)[source]

Bases: Layer

Reconstruction based Model.

Parameters
  • in_chunk_len (int) – The size of the loopback window, i.e. the number of time steps feed to the model.

  • feature_dim (int) – The number of features.

  • hidden_size (int) – The hidden size.

  • out_dim (int) – The number of output features.

  • num_layers (int) – The number of layer.

  • dropout (float) – Dropout regularization parameter.

_in_chunk_len

The size of the loopback window, i.e. the number of time steps feed to the model.

Type

int

_decoder

The gru decoder layer.

Type

paddle.nn.Layer

_fc

The fc layer.

Type

paddle.nn.Layer

forward(x)[source]

Forward

Parameters

x (paddle.Tensor) – The input data.

Returns

Output of Reconstruction.

Return type

paddle.Tensor)

class Forecasting(feature_dim: int, hidden_size: int, out_dim: int, num_layers: int, dropout: float)[source]

Bases: Layer

Forecasting based Model.

Parameters
  • feature_dim (int) – The number of features.

  • hidden_size (int) – The hidden size.

  • out_dim (int) – The number of output features.

  • num_layers (int) – The number of layer.

  • dropout (float) – Dropout regularization parameter.

_layers

Dynamic graph LayerList.

Type

paddle.nn.Sequential

_dropout

The dropout layer.

Type

paddle.nn.Dropout

_relu

The relu layer.

Type

paddle.nn.RelU

forward(x)[source]

Forward

Parameters

x (paddle.Tensor) – The input data.

Returns

Output of Forecasting.

Return type

paddle.Tensor)