target_transform_trimap_masks: Target Transform: Trimap to Boolean Masks

In torchvision: Models, Datasets and Transformations for Images

Target Transform: Trimap to Boolean Masks

Description

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().

Usage

target_transform_trimap_masks(y)

## S3 method for class 'segmentation_target'
target_transform_trimap_masks(y)

Arguments

y	a segmentation_target or a bare list containing a trimap field, a (H, W) tensor with values 1, 2, 3

Details

Creates three mutually exclusive masks:

• Channel 1: Pet pixels (trimap == 1)

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

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

Value

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

See Also

Other target_transforms_segmentation: target_transform_coco_masks()

Examples

## Not run: 
ds <- oxfordiiitpet_segmentation_dataset(
  root = "data",
  target_transform = target_transform_trimap_masks
)
item <- ds[1]
draw_segmentation_masks(item)

## End(Not run)

torchvision documentation built on Oct. 14, 2026, 1:09 a.m.