tflite_support.task.processor.Segmentation

Represents one Segmentation object in the image segmenter's results.

tflite_support.task.processor.Segmentation(
    height: int,
    width: int,
    colored_labels: List[tflite_support.task.processor.ColoredLabel],
    category_mask: Optional[np.ndarray] = None,
    confidence_masks: Optional[List[ConfidenceMask]] = None
)

height The height of the mask. This is an intrinsic parameter of the model being used, and does not depend on the input image dimensions.
width The width of the mask. This is an intrinsic parameter of the model being used, and does not depend on the input image dimensions.
colored_labels A list of ColoredLabel objects.
category_mask A NumPy 2D-array of the category mask.
confidence_masks A list of ConfidenceMask objects.

Methods

create_from_pb2

View source

@classmethod
create_from_pb2(
    pb2_obj: _SegmentationProto
) -> 'Segmentation'

Creates a Segmentation object from the given protobuf object.

to_pb2

View source

to_pb2() -> _SegmentationProto

Generates a protobuf object to pass to the C++ layer.

__eq__

View source

__eq__(
    other: Any
) -> bool

Checks if this object is equal to the given object.

Args
other The object to be compared with.

Returns
True if the objects are equal.

category_mask None
confidence_masks None