target_transform_coco_masks: Target Transform: COCO Polygon Segmentation to Masks

In torchvision: Models, Datasets and Transformations for Images

Target Transform: COCO Polygon Segmentation to Masks

Description

Converts COCO-style polygon segmentation annotations from target ⁠$segmentation⁠ variable into boolean mask tensors as target ⁠$masks⁠ variable in order to ease later-on visualisation via draw_segmentation_mask(). Use as target_transform in coco_segmentation_dataset().

Usage

target_transform_coco_masks(y)

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

Arguments

y	a segmentation_target, as returned by the .getitem() method of coco_segmentation_dataset(), or a bare list with names segmentation, image_height, image_width.

Value

Modified y list with added masks field (N, H, W) boolean tensor, N being the number of classes.

See Also

Other target_transforms_segmentation: target_transform_trimap_masks()

Examples

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

## End(Not run)

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