OpenImageO#
- class torch_uncertainty.datasets.classification.OpenImageO(root, split=None, transform=None, target_transform=None, download=False)[source]#
OpenImage-O dataset.
- Parameters:
root (str) – Root directory of the datasets.
split (str, optional) – Unused, for API consistency. Defaults to
None
.transform (callable, optional) – A function/transform that takes in a PIL image and returns a transformed version. E.g,
transforms.RandomCrop
. Defaults toNone
.target_transform (callable, optional) – A function/transform that takes in the target and transforms it. Defaults to
None
.download (bool, optional) – 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
.
References
[2] Curation: ViM: Out-Of-Distribution with Virtual-logit Matching. Wang H., et al. In CVPR 2022.