RoboFlow 100 Underwater dataset Collection

Loads one of the RoboFlow 100 Underwater datasets: "pipes", "aquarium", "objects", or "coral". Images are provided with COCO-style bounding box annotations for object detection tasks.

rf100_underwater_collection(
  dataset,
  split = c("train", "test", "valid"),
  transform = NULL,
  target_transform = NULL,
  download = FALSE
)

Arguments

dataset

Dataset to select within c("pipes", "aquarium", "objects", "coral").

split

the subset of the dataset to choose between c("train", "test", "valid").

transform

Optional transform function applied to the image.

target_transform

Optional transform function applied to the target.

download

Logical. If TRUE, downloads the dataset if not present at root.

Value

A torch dataset. Each element is a named list with:

• x: H x W x 3 array representing the image.

• y: a list containing the target with:

  • image_id: numeric identifier of the x image.

  • labels: numeric identifier of the N bounding-box object class.

  • boxes: a torch_tensor of shape (N, 4) with bounding boxes, each in \((x_{min}, y_{min}, x_{max}, y_{max})\) format.

The returned item inherits the class image_with_bounding_box so it can be visualised with helper functions such as draw_bounding_boxes().

See also

Other detection_dataset: coco_detection_dataset(), pascal_voc_datasets, rf100_biology_collection(), rf100_damage_collection(), rf100_document_collection(), rf100_infrared_collection(), rf100_medical_collection()

Examples

if (FALSE) { # \dontrun{
ds <- rf100_underwater_collection(
  dataset = "objects",
  split = "train",
  transform = transform_to_tensor,
  download = TRUE
)

item <- ds[1]
boxed <- draw_bounding_boxes(item)
tensor_image_browse(boxed)
} # }