Class ImageSegmentationModel (1.121.0) 

ImageSegmentationModel(model_id: str, endpoint_name: typing.Optional[str] = None)

Segments an image.

Methods

ImageSegmentationModel

ImageSegmentationModel(model_id: str, endpoint_name: typing.Optional[str] = None)

Creates a _ModelGardenModel.

This constructor should not be called directly. Use {model_class}.from_pretrained(model_name=...) instead.

from_pretrained

from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.T

Loads a _ModelGardenModel.

Exceptions
Type Description
ValueError If model_name is unknown.
ValueError If model does not support this class.

segment_image

segment_image(
    base_image: vertexai.vision_models.Image,
    prompt: typing.Optional[str] = None,
    scribble: typing.Optional[vertexai.preview.vision_models.Scribble] = None,
    mode: typing.Literal[
        "foreground", "background", "semantic", "prompt", "interactive"
    ] = "foreground",
    max_predictions: typing.Optional[int] = None,
    confidence_threshold: typing.Optional[float] = 0.1,
    mask_dilation: typing.Optional[float] = None,
    binary_color_threshold: typing.Optional[float] = None,
) -> vertexai.preview.vision_models.ImageSegmentationResponse

Segments an image.