class SequenceCombinerConfig:
main_sequence_feature: Optional[str] = None
reduce_output: Optional[str] = schema.ReductionOptions()
encoder: Optional[str] = schema.StringOptions(list(sequence_encoder_registry.keys()))
class Meta:
unknown = INCLUDE
class TransformerCombinerConfig:
num_layers: int = schema.PositiveInteger(default=1)
hidden_size: int = schema.NonNegativeInteger(default=256)
num_heads: int = schema.NonNegativeInteger(default=8)
transformer_fc_size: int = schema.NonNegativeInteger(default=256)
dropout: float = schema.FloatRange(default=0.1, min=0, max=1)
fc_layers: Optional[List[Dict[str, Any]]] = schema.DictList()
num_fc_layers: int = schema.NonNegativeInteger(default=0)
fc_size: int = schema.PositiveInteger(default=256)
use_bias: bool = True
weights_initializer: Union[str, Dict] = schema.InitializerOrDict(default="xavier_uniform")
bias_initializer: Union[str, Dict] = schema.InitializerOrDict(default="zeros")
norm: Optional[str] = schema.StringOptions(["batch", "layer"])
norm_params: Optional[dict] = schema.Dict()
fc_activation: str = "relu"
fc_dropout: float = schema.FloatRange(default=0.0, min=0, max=1)
fc_residual: bool = False
reduce_output: Optional[str] = schema.ReductionOptions(default="mean")
class Meta:
unknown = INCLUDE
class SequenceConcatCombinerConfig:
main_sequence_feature: Optional[str] = None
reduce_output: Optional[str] = schema.ReductionOptions()
class Meta:
unknown = INCLUDE