incerto.data.CIFAR10

incerto.data.CIFAR10#

class incerto.data.CIFAR10(root='./data', val_split=0.1, seed=42, normalize=True, augmentation=True)[source]#

Bases: VisionDataset

CIFAR-10 dataset with standardized splits.

32x32 color images in 10 classes. 50,000 training + 10,000 test images.

Parameters:
__init__(root='./data', val_split=0.1, seed=42, normalize=True, augmentation=True)[source]#

Initialize vision dataset.

Parameters:

  • root (str | Path) – Root directory for dataset storage

  • val_split (float) – Fraction of training data to use for validation

  • seed (int) – Random seed for reproducible splits

  • normalize (bool)

  • augmentation (bool)

Methods

__init__([root, val_split, seed, normalize, ...])

Initialize vision dataset.

get_datasets()

Get train, validation, and test datasets.

get_transforms([train])

Get data transformations.
__init__(root='./data', val_split=0.1, seed=42, normalize=True, augmentation=True)[source]#

Initialize vision dataset.

Parameters:

  • root (str | Path) – Root directory for dataset storage

  • val_split (float) – Fraction of training data to use for validation

  • seed (int) – Random seed for reproducible splits

  • normalize (bool)

  • augmentation (bool)

get_transforms(train=False)[source]#

Get data transformations.

Parameters:

train (bool)

Return type:

Compose

get_datasets()[source]#

Get train, validation, and test datasets.

Return type:

Tuple[Dataset, Dataset, Dataset]

Contents