SegmentationLabelsOutput

class flash.image.segmentation.output.SegmentationLabelsOutput(labels_map=None, visualize=False)

A Output which converts the model outputs to the label of the argmax classification per pixel in the image for semantic segmentation tasks.

Parameters

• labels_map (Optional[Dict[int, Tuple[int, int, int]]]) – A dictionary that map the labels ids to pixel intensities.

• visualize (bool) – Whether to visualize the image labels.

static labels_to_image(img_labels, labels_map)

Function that given an image with labels ids and their pixel intensity mapping, creates an RGB representation for visualisation purposes.

Return type

Tensor