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 TabNetCombinerConfig: size: int = schema.PositiveInteger(default=32) # N_a in the paper output_size: int = schema.PositiveInteger(default=32) # N_d in the paper num_steps: int = schema.NonNegativeInteger( default=1) # N_steps in the paper num_total_blocks: int = schema.NonNegativeInteger(default=4) num_shared_blocks: int = schema.NonNegativeInteger(default=2) relaxation_factor: float = 1.5 # gamma in the paper bn_epsilon: float = 1e-3 bn_momentum: float = 0.7 # m_B in the paper # B_v from the paper bn_virtual_bs: Optional[int] = schema.PositiveInteger() sparsity: float = 1e-5 # lambda_sparse in the paper entmax_mode: str = schema.StringOptions( ["entmax15", "sparsemax", "constant", "adaptive"], default="sparsemax") entmax_alpha: float = schema.FloatRange( default=1.5, min=1, max=2) # 1 corresponds to softmax, 2 is sparsemax. dropout: float = schema.FloatRange(default=0.0, min=0, max=1) class Meta: unknown = INCLUDE
class ConcatCombinerConfig: 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() activation: str = "relu" dropout: float = schema.FloatRange(default=0.0, min=0, max=1) flatten_inputs: bool = False residual: bool = False class Meta: unknown = INCLUDE
class TabNetCombinerConfig: size: int = schema.PositiveInteger(default=32) # N_a in the paper output_size: int = schema.PositiveInteger(default=32) # N_d in the paper num_steps: int = schema.NonNegativeInteger(default=1) # N_steps in the paper num_total_blocks: int = schema.NonNegativeInteger(default=4) num_shared_blocks: int = schema.NonNegativeInteger(default=2) relaxation_factor: float = 1.5 # gamma in the paper bn_epsilon: float = 1e-3 bn_momentum: float = 0.7 # m_B in the paper # B_v from the paper bn_virtual_bs: Optional[int] = schema.PositiveInteger() sparsity: float = 1e-5 # lambda_sparse in the paper dropout: float = schema.FloatRange(default=0.0, min=0, max=1) class Meta: unknown = INCLUDE