item_transform_random_resize_crop: Randomly crop a dataset item and resize it

In torchvision: Models, Datasets and Transformations for Images

Randomly crop a dataset item and resize it

Description

Crops the image inside a dataset item to a random area and aspect ratio, then resizes that crop to the given size. For detection items, bounding boxes are cropped along with the image and their coordinates are rescaled to the output size: boxes falling outside the crop are dropped and boxes straddling its border are clipped to it. For segmentation items, the masks are cropped and resized alongside the image with nearest-neighbour sampling, so that they keep their discrete values.

Usage

item_transform_random_resize_crop(
  x,
  size,
  scale = c(0.08, 1),
  ratio = c(3/4, 4/3),
  interpolation = 2
)

Arguments

x	A dataset item, typically an image_with_bounding_box or image_with_segmentation_mask object containing an image tensor and associated target data.
size	(integer vector or integer): Desired output size. If size is an integer vector of length 2 like c(h, w), output size will be matched to this. If size is a bare integer, smaller edge of the image will be matched to this number, i.e., if height > width, then image will be rescaled to ⁠(size * height / width, size)⁠.
scale	(numeric vector of length 2): Range of size of the origin size cropped.
ratio	(numeric vector of length 2): Range of aspect ratio of the origin aspect ratio cropped. ratio cropped.
interpolation	(integer, optional): Desired interpolation. An integer 0 = nearest, 2 = bilinear, and 3 = bicubic or a name from magick::filter_types().

Details

The crop is drawn again for every item, so that a dataset wrapped with this transform yields a different crop on each access.

The area field of a detection target, when present, is rescaled by the area ratio between the crop and the output. For rotated boxes, a crop whose aspect ratio differs from the output one maps the box to a parallelogram: the enclosing box stays exact and the angle is that of the transformed box axis, which is exact whenever both edges are scaled alike.

Value

A dataset item of the same class with the image and target cropped and resized.

See Also

Other item_random_transforms: item_transform_random_affine(), item_transform_random_crop(), item_transform_random_erasing(), item_transform_random_horizontal_flip(), item_transform_random_perspective(), item_transform_random_rotation(), item_transform_random_vertical_flip()

Examples

## Not run: 
url <- "https://upload.wikimedia.org/wikipedia/commons/b/b6/Felis_catus-cat_on_snow.jpg"
img <- base_loader(url) |> transform_to_tensor()

boxes <- torch_tensor(matrix(c(600, 200, 2880, 1860), ncol = 4), dtype = torch_float32())

before <- list(x = img, y = list(boxes = boxes, labels = "cat"))
class(before) <- c("image_with_bounding_box", "list")

after <- item_transform_random_resize_crop(before, size = c(600, 800))

before_plot <- draw_bounding_boxes(before, colors = "blue", width = 10)
after_plot <- draw_bounding_boxes(after, colors = "red", width = 10)
tensor_image_browse(before_plot)
tensor_image_browse(after_plot)

## End(Not run)

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