item_transform_vflip: Vertically flip a dataset item

In torchvision: Models, Datasets and Transformations for Images

Vertically flip a dataset item

Description

Flips the image inside a dataset item vertically. For detection items, bounding box y-coordinates are adjusted to remain correct after the flip. For segmentation items, both the image and the masks are flipped.

Usage

item_transform_vflip(x)

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.

Value

A dataset item of the same class with the image and target vertically flipped.

See Also

Other item_unitary_transforms: item_transform_affine(), item_transform_center_crop(), item_transform_crop(), item_transform_hflip(), item_transform_pad(), item_transform_perspective(), item_transform_resize(), item_transform_rotate()

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_vflip(before)

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

tensor_image_browse(vision_make_grid(before_plot, after_plot, scale = TRUE))

## End(Not run)

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