dataeval.utils.data.datasets.CIFAR10¶
-
class dataeval.utils.data.datasets.CIFAR10(root, train=
True, download=False, transform=None, target_transform=None)¶ CIFAR10 Dataset as Torch tensors.
- Parameters:¶
- root : str or pathlib.Path¶
Root directory of the CIFAR10 Dataset.
- train : bool, default True¶
If True, creates dataset from training set, otherwise creates from test set.
- download : bool, default False¶
If true, downloads the dataset from the internet and puts it in root directory. If dataset is already downloaded, it is not downloaded again.
- transform : Callable or None, default None:¶
A function/transform that takes in a PIL image and returns a transformed version. ToImage() and ToDtype(torch.float32, scale=True) are applied by default.
- target_transform : Callable or None, default None:¶
A function/transform that takes in the target and transforms it.