dataeval.utils.data.datasets.VOCDetection¶

class dataeval.utils.data.datasets.VOCDetection(root, year='2012', image_set='train', download=False, transform=None, target_transform=None, transforms=None)¶

Pascal VOC Detection Dataset.

Parameters:¶

root : str or pathlib.Path¶

Root directory of the VOC Dataset.

year : "2007", "2008", "2009", "2010", "2011" or "2012", default "2012"¶

The dataset year.

image_set : "train", "trainval", "val", or "test", default "train"¶

“test” is only valid for the year “2007”

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. E.g, torchvision.transforms.RandomCrop

target_transform : Callable or None, default None:¶

A function/transform that takes in the target and transforms it.

transforms : Callable or None, default None¶

A function/transform that takes input sample and its target as entry and returns a transformed version.