ImageNetDataModule¶
- class torch_uncertainty.datamodules.ImageNetDataModule(root, batch_size, eval_ood=False, eval_shift=False, shift_severity=1, val_split=None, ood_ds='openimage-o', test_alt=None, procedure=None, train_size=224, interpolation='bilinear', basic_augment=True, rand_augment_opt=None, num_workers=1, pin_memory=True, persistent_workers=True)[source]¶
DataModule for ImageNet.
- Parameters:
root (str) – Root directory of the datasets.
eval_ood (bool) – Whether to evaluate out-of-distribution performance. Defaults to
False.eval_shift (bool) – Whether to evaluate on shifted data. Defaults to
False.shift_severity – int = 1,
batch_size (int) – Number of samples per batch.
val_split (float or Path) – Share of samples to use for validation or path to a yaml file containing a list of validation images ids. Defaults to
0.0.ood_ds (str) – Which out-of-distribution dataset to use. Defaults to
"openimage-o".test_alt (str) – Which test set to use. Defaults to
None.procedure (str) – Which procedure to use. Defaults to
None.train_size (int) – Size of training images. Defaults to
224.interpolation (str) – Interpolation method for the Resize Crops. Defaults to
"bilinear".basic_augment (bool) – Whether to apply base augmentations. Defaults to
True.rand_augment_opt (str) – Which RandAugment to use. Defaults to
None.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.