Caltech-256 Object Category Dataset — caltech256_detection

Caltech-256 Dataset

caltech256_detection_dataset(
  root = tempdir(),
  transform = NULL,
  target_transform = NULL,
  download = FALSE
)

Arguments

root: Character. Root directory for dataset storage. The dataset will be stored under root/caltech256.
transform: Optional function to apply to each image after loading (e.g., resizing, normalization).
target_transform: Optional function to transform the target label.
download: Logical. If TRUE, downloads and extracts the dataset if it's not already present. Default is FALSE.

Value

An object of class caltech256_detection_dataset, which behaves like a torch dataset. Each element is a named list:

x: A 3 x W x H integer array representing an RGB image.
y: A character string representing the class label.

Details

Loads the Caltech-256 Object Category Dataset, which consists of 30,607 images from 256 distinct object categories. Each category has at least 80 images, with significant variability in object position, scale, and background. #'

Examples

if (FALSE) { # \dontrun{
caltech256 <- caltech256_detection_dataset(download = TRUE)

first_item <- caltech256[1]
first_item$x  # Image array
first_item$y  # Class label, e.g., "ak47"
} # }