CIFAR100DataModule¶
- class torch_uncertainty.datamodules.CIFAR100DataModule(root, batch_size, eval_ood=False, eval_shift=False, shift_severity=1, val_split=None, basic_augment=True, cutout=None, randaugment=False, auto_augment=None, num_dataloaders=1, num_workers=1, pin_memory=True, persistent_workers=True)[source]¶
DataModule for CIFAR100.
- Parameters:
root (str) – Root directory of the datasets.
eval_ood (bool) – Whether to evaluate out-of-distribution performance.
eval_shift (bool) – Whether to evaluate on shifted data. Defaults to
False. –
batch_size (int) – Number of samples per batch.
val_split (float) – Share of samples to use for validation. Defaults to
0.0.basic_augment (bool) – Whether to apply base augmentations. Defaults to
True.cutout (int) – Size of cutout to apply to images. Defaults to
None.randaugment (bool) – Whether to apply RandAugment. Defaults to
False.auto_augment (str) – Which auto-augment to apply. Defaults to
None.shift_severity (int) – Severity of corruption to apply to CIFAR100-C. Defaults to
1.num_dataloaders (int) – Number of dataloaders to use. Defaults to
1.num_workers (int) – Number of workers to use for data loading. Defaults to
1.pin_memory (bool) – Whether to pin memory. Defaults to
True.persistent_workers (bool) – Whether to use persistent workers. Defaults to
True.