FaceConfig

Bases: ModelConfigBase[FaceConfig]

Configuration for the facial expression model.

Parameters:

Name	Type	Description	Default
`fps_pred`	`Optional[float]`	Number of frames per second to process. Other frames will be omitted from the response. This configuration is not available for the streaming API.	`None`
`prob_threshold`	`Optional[float]`	Face detection probability threshold. Faces detected with a probability less than this threshold will be omitted from the response. This configuration is not available for the streaming API.	`None`
`identify_faces`	`Optional[bool]`	Whether to return identifiers for faces across frames. If true, unique identifiers will be assigned to face bounding boxes to differentiate different faces. If false, all faces will be tagged with an "unknown" ID.	`None`
`min_face_size`	`Optional[float]`	Minimum bounding box side length in pixels to treat as a face. Faces detected with a bounding box side length in pixels less than this threshold will be omitted from the response. This configuration is not available for the streaming API.	`None`
`save_faces`	`Optional[bool]`	Whether to extract and save the detected faces to the artifacts directory included in the response. This configuration is not available for the streaming API.	`None`
`descriptions`	`Optional[Dict[str, Any]]`	Configuration for Descriptions predictions. If missing or null, no Descriptions predictions will be generated.	`None`
`facs`	`Optional[Dict[str, Any]]`	Configuration for FACS predictions. If missing or null, no FACS predictions will be generated.	`None`

Source code in hume/models/config/face_config.py

@dataclass
class FaceConfig(ModelConfigBase["FaceConfig"]):
    """Configuration for the facial expression model.

    Args:
        fps_pred (Optional[float]): Number of frames per second to process. Other frames will be omitted
            from the response.
            This configuration is not available for the streaming API.
        prob_threshold (Optional[float]): Face detection probability threshold. Faces detected with a
            probability less than this threshold will be omitted from the response.
            This configuration is not available for the streaming API.
        identify_faces (Optional[bool]): Whether to return identifiers for faces across frames.
            If true, unique identifiers will be assigned to face bounding boxes to differentiate different faces.
            If false, all faces will be tagged with an "unknown" ID.
        min_face_size (Optional[float]): Minimum bounding box side length in pixels to treat as a face.
            Faces detected with a bounding box side length in pixels less than this threshold will be
            omitted from the response.
            This configuration is not available for the streaming API.
        save_faces (Optional[bool]): Whether to extract and save the detected faces to the artifacts
            directory included in the response.
            This configuration is not available for the streaming API.
        descriptions (Optional[Dict[str, Any]]): Configuration for Descriptions predictions.
            If missing or null, no Descriptions predictions will be generated.
        facs (Optional[Dict[str, Any]]): Configuration for FACS predictions.
            If missing or null, no FACS predictions will be generated.
    """

    fps_pred: Optional[float] = None
    prob_threshold: Optional[float] = None
    identify_faces: Optional[bool] = None
    min_face_size: Optional[float] = None
    save_faces: Optional[bool] = None
    descriptions: Optional[Dict[str, Any]] = None
    facs: Optional[Dict[str, Any]] = None

    @classmethod
    def get_model_type(cls) -> ModelType:
        """Get the configuration model type.

        Returns:
            ModelType: Model type.
        """
        return ModelType.FACE

`get_model_type()` `classmethod`

Get the configuration model type.

Returns:

Name	Type	Description
`ModelType`	`ModelType`	Model type.

Source code in hume/models/config/face_config.py

@classmethod
def get_model_type(cls) -> ModelType:
    """Get the configuration model type.

    Returns:
        ModelType: Model type.
    """
    return ModelType.FACE

FaceConfig

get_model_type() classmethod

`get_model_type()` `classmethod`