RoboFlow 100 Medical dataset Collection

Source: R/collection-rf100-medical.R

Loads one of the RoboFlow 100 Medical datasets with per-dataset folders and train/valid/test splits.

rf100_medical_collection(
  dataset,
  split = c("train", "test", "valid"),
  transform = NULL,
  target_transform = NULL,
  item_transform = NULL,
  download = FALSE
)

Arguments

dataset

Dataset to select within c("radio_signal", "rheumatology", "knee", "abdomen_mri", "brain_axial_mri", "gynecology_mri", "brain_tumor", "fracture").

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.

item_transform

Optional transform function applied to the whole item, such as item_transform_rotate(), once transform and target_transform have been applied. It is only used by .getitem(), not by the batched .getbatch().

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, auto-oriented and stretched to 640 x 640.

  • 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(), and its y inherits object_detection_target, which target transforms such as target_transform_rotate() dispatch on. The collection itself inherits object_detection_dataset.

Examples

if (FALSE) { # \dontrun{
ds <- rf100_medical_collection(
  dataset = "rheumatology",
  split = "test",
  transform = transform_to_tensor,
  download = TRUE
)
item <- ds[1]
boxed <- draw_bounding_boxes(item)
tensor_image_browse(boxed)
} # }