AugmentedLSTM.Config¶

Component: AugmentedLSTM

class AugmentedLSTM.Config[source]

Bases: RepresentationBase.Config, ConfigBase

Configuration class for AugmentedLSTM.

dropout¶

Variational dropout probability to use. Defaults to 0.0.

Type:	float

lstm_dim¶

Number of features in the hidden state of the LSTM. Defaults to 32.

Type:	int

num_layers¶

Number of recurrent layers. Eg. setting num_layers=2 would mean stacking two LSTMs together to form a stacked LSTM, with the second LSTM taking in the outputs of the first LSTM and computing the final result. Defaults to 1.

Type:	int

bidirectional¶

If True, becomes a bidirectional LSTM. Defaults to True.

Type:	bool

use_highway¶

If True we append a highway network to the outputs of the LSTM.

Type:	bool

use_bias¶

If True we use a bias in our LSTM calculations, otherwise we don’t.

Type:	bool

All Attributes (including base classes)

load_path: Optional[str] = None

save_path: Optional[str] = None

freeze: bool = False

shared_module_key: Optional[str] = None

dropout: float = 0.0

lstm_dim: int = 32

use_highway: bool = True

bidirectional: bool = False

num_layers: int = 1

use_bias: bool = False

Default JSON

{
    "load_path": null,
    "save_path": null,
    "freeze": false,
    "shared_module_key": null,
    "dropout": 0.0,
    "lstm_dim": 32,
    "use_highway": true,
    "bidirectional": false,
    "num_layers": 1,
    "use_bias": false
}