hubai_sdk.utils.config.OutputConfig

class documentation

class OutputConfig(CustomBaseModel):

Shape, layout, and data type of one model output.

Method	`validate_layout`	Undocumented
Instance Variable	`data_type`	Tensor element type.
Instance Variable	`layout`	Dimension labels such as `"NCHW"`. A default is inferred from `shape` when omitted.
Instance Variable	`name`	Tensor name in the source model.
Instance Variable	`shape`	Tensor dimensions. May be omitted when they can be inferred.
Class Method	`_make_default_layout`	Undocumented

Inherited from CustomBaseModel:

Class Variable model_config Undocumented

@model_validator(mode='after')

def validate_layout(self) -> Self: ¶

Undocumented

data_type: DataType = ¶

Tensor element type.

layout: str | None = ¶

Dimension labels such as "NCHW". A default is inferred from shape when omitted.

name: str = ¶

Tensor name in the source model.

shape: list[int] | None = ¶

Tensor dimensions. May be omitted when they can be inferred.

@model_validator(mode='before')
@classmethod

def _make_default_layout(cls, data: dict[str, Any]) -> dict[str, Any]: ¶

Undocumented