Class MaskReferenceImage (1.75.0)

MaskReferenceImage(
    reference_id,
    image: typing.Optional[
        typing.Union[bytes, vertexai.vision_models.Image, str]
    ] = None,
    mask_mode: typing.Optional[
        typing.Literal[
            "default", "user_provided", "background", "foreground", "semantic"
        ]
    ] = None,
    dilation: typing.Optional[float] = None,
    segmentation_classes: typing.Optional[typing.List[int]] = None,
)

Mask reference image. This encapsulates the mask reference image type.

Methods

MaskReferenceImage

MaskReferenceImage(
    reference_id,
    image: typing.Optional[
        typing.Union[bytes, vertexai.vision_models.Image, str]
    ] = None,
    mask_mode: typing.Optional[
        typing.Literal[
            "default", "user_provided", "background", "foreground", "semantic"
        ]
    ] = None,
    dilation: typing.Optional[float] = None,
    segmentation_classes: typing.Optional[typing.List[int]] = None,
)

Creates a MaskReferenceImage object.

Parameters
Name	Description
image	typing.Union[bytes, vertexai.vision_models.Image, str, NoneType] Either Image object or Image file bytes. Image can be in PNG or JPEG format.
mask_mode	typing.Optional[typing.Literal['default', 'user_provided', 'background', 'foreground', 'semantic']] Mask mode for the image. Can take the following values: * default: Default mask mode * user_provided: User provided mask * background: Background mask * foreground: Foreground mask * semantic: Semantic mask
dilation	typing.Optional[float] Dilation percentage of the mask
segmentation_classes	typing.Optional[typing.List[int]] List of class IDs for segmentation. Max of 5 IDs