Target Transform: Trimap to Boolean Masks

Source: R/transforms-segmentation.R

Converts Oxford-IIIT Pet dataset target $trimap variable (values 1,2,3) into 3-channel boolean masks tensors as target $masks variable in order to ease later-on visualisation via draw_segmentation_mask(). Use as target_transform in oxfordiiitpet_segmentation_dataset().

target_transform_trimap_masks(y)

Arguments

y

List containing trimap field (H, W) tensor with values 1, 2, 3

Value

Modified y list with added masks field (3, H, W) boolean tensor

Details

Creates three mutually exclusive masks:

  • Channel 1: Pet pixels (trimap == 1)

  • Channel 2: Background pixels (trimap == 2)

  • Channel 3: Outline pixels (trimap == 3)

See also

Other target_transforms: target_transform_coco_masks()

Examples

if (FALSE) { # \dontrun{
ds <- oxfordiiitpet_segmentation_dataset(
  root = "data",
  target_transform = target_transform_trimap_masks
)
item <- ds[1]
draw_segmentation_masks(item)
} # }