CIFAR100N#

class torch_uncertainty.datasets.classification.CIFAR100N(root, train=True, file_arg='fine_label', transform=None, target_transform=None, download=False)[source]#

CIFAR-100N Dataset.

Parameters:

  • root (str) – Root directory of dataset where file cifar-100h-probs.npy exists or will be saved to if download is set to True.

  • train (bool) – For API consistency, not used.

  • file_arg (Literal['fine_label', 'coarse_label']) – The type of label noise to use. One of the following: "fine_label", "coarse_label".

  • transform (Callable[..., Any] | None) – A function/transform that takes in a PIL image and returns a transformed version. E.g, transforms.RandomCrop. Defaults to None.

  • target_transform (Callable[..., Any] | None) – A function/transform that takes in the target and transforms it. Defaults to None.

  • download (bool) – If True, downloads the dataset from the internet and puts it in root directory. If dataset is already downloaded, it is not downloaded again. Defaults to False.