item_transform_random_horizontal_flip: Randomly horizontally flip a dataset item

In torchvision: Models, Datasets and Transformations for Images

Randomly horizontally flip a dataset item

Description

Randomly flips the image inside a dataset item horizontally with a given probability. When a flip occurs, the same coordinate adjustments used by item_transform_hflip are applied to bounding boxes and masks.

Usage

item_transform_random_horizontal_flip(x, p = 0.5)

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.
p	Probability of the item being flipped. Default is 0.5.

Value

A dataset item of the same class. With probability p, the image and targets are horizontally flipped; otherwise they are returned unchanged.

See Also

Other item_random_transforms: item_transform_random_affine(), item_transform_random_crop(), item_transform_random_erasing(), item_transform_random_perspective(), item_transform_random_resize_crop(), 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_horizontal_flip(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.