def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"mnist",
categories=10,
homepage="http://yann.lecun.com/exdb/mnist",
valid_options=dict(split=("train", "test"), ),
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"oxford-iiit-pet",
type=DatasetType.IMAGE,
homepage="https://www.robots.ox.ac.uk/~vgg/data/pets/",
valid_options=dict(split=("trainval", "test"), ),
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
name="stanford-cars",
homepage="https://ai.stanford.edu/~jkrause/cars/car_dataset.html",
dependencies=("scipy", ),
valid_options=dict(split=("test", "train"), ),
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"semeion",
categories=10,
homepage=
"https://archive.ics.uci.edu/ml/datasets/Semeion+Handwritten+Digit",
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"caltech101",
type=DatasetType.IMAGE,
dependencies=("scipy", ),
homepage="http://www.vision.caltech.edu/Image_Datasets/Caltech101",
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"cifar100",
type=DatasetType.RAW,
homepage="https://www.cs.toronto.edu/~kriz/cifar.html",
valid_options=dict(split=("train", "test"), ),
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"celeba",
type=DatasetType.IMAGE,
homepage="https://mmlab.ie.cuhk.edu.hk/projects/CelebA.html",
valid_options=dict(split=("train", "val", "test")),
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"gtsrb",
homepage="https://benchmark.ini.rub.de",
categories=[f"{label:05d}" for label in range(43)],
valid_options=dict(split=("train", "test")),
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"sbd",
dependencies=("scipy", ),
homepage="http://home.bharathh.info/pubs/codes/SBD/download.html",
valid_options=dict(split=("train", "val", "train_noval"), ),
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"country211",
homepage=
"https://github.com/openai/CLIP/blob/main/data/country211.md",
valid_options=dict(split=("train", "val", "test")),
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"clevr",
type=DatasetType.IMAGE,
homepage="https://cs.stanford.edu/people/jcjohns/clevr/",
valid_options=dict(split=("train", "val", "test")),
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"fer2013",
homepage="https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge",
categories=("angry", "disgust", "fear", "happy", "sad", "surprise", "neutral"),
valid_options=dict(split=("train", "test")),
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"qmnist",
categories=10,
homepage="https://github.com/facebookresearch/qmnist",
valid_options=dict(split=("train", "test", "test10k", "test50k",
"nist"), ),
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"usps",
homepage=
"https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/multiclass.html#usps",
valid_options=dict(split=("train", "test"), ),
categories=10,
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"pcam",
homepage="https://github.com/basveeling/pcam",
categories=2,
valid_options=dict(split=("train", "test", "val")),
dependencies=["h5py"],
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"svhn",
dependencies=("scipy", ),
categories=10,
homepage="http://ufldl.stanford.edu/housenumbers/",
valid_options=dict(split=("train", "test", "extra")),
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"kmnist",
categories=[
"o", "ki", "su", "tsu", "na", "ha", "ma", "ya", "re", "wo"
],
homepage="http://codh.rois.ac.jp/kmnist/index.html.en",
valid_options=dict(split=("train", "test"), ),
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"dtd",
homepage="https://www.robots.ox.ac.uk/~vgg/data/dtd/",
valid_options=dict(
split=("train", "test", "val"),
fold=tuple(str(fold) for fold in range(1, 11)),
),
)
def _make_info(self) -> DatasetInfo:
name = "coco"
categories, super_categories = zip(
*DatasetInfo.read_categories_file(BUILTIN_DIR /
f"{name}.categories"))
return DatasetInfo(
name,
dependencies=("pycocotools", ),
categories=categories,
homepage="https://cocodataset.org/",
valid_options=dict(
split=("train", "val"),
year=("2017", "2014"),
annotations=(*self._ANN_DECODERS.keys(), None),
),
extra=dict(category_to_super_category=FrozenMapping(
zip(categories, super_categories))),
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"voc",
type=DatasetType.IMAGE,
homepage="http://host.robots.ox.ac.uk/pascal/VOC/",
valid_options=dict(
split=("train", "val", "test"),
year=("2012", ),
task=("detection", "segmentation"),
),
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"cub200",
homepage=
"http://www.vision.caltech.edu/visipedia/CUB-200-2011.html",
dependencies=("scipy", ),
valid_options=dict(
split=("train", "test"),
year=("2011", "2010"),
),
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"sbd",
type=DatasetType.IMAGE,
dependencies=("scipy", ),
homepage="http://home.bharathh.info/pubs/codes/SBD/download.html",
valid_options=dict(
split=("train", "val", "train_noval"),
boundaries=(True, False),
segmentation=(False, True),
),
)
def _make_info(self) -> DatasetInfo:
name = "imagenet"
categories, wnids = zip(
*DatasetInfo.read_categories_file(BUILTIN_DIR /
f"{name}.categories"))
return DatasetInfo(
name,
dependencies=("scipy", ),
categories=categories,
homepage="https://www.image-net.org/",
valid_options=dict(split=("train", "val", "test")),
extra=dict(
wnid_to_category=FrozenMapping(zip(wnids, categories)),
category_to_wnid=FrozenMapping(zip(categories, wnids)),
sizes=FrozenMapping([
(DatasetConfig(split="train"), 1_281_167),
(DatasetConfig(split="val"), 50_000),
(DatasetConfig(split="test"), 100_000),
]),
),
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"eurosat",
homepage="https://github.com/phelber/eurosat",
categories=(
"AnnualCrop",
"Forest",
"HerbaceousVegetation",
"Highway",
"Industrial,"
"Pasture",
"PermanentCrop",
"Residential",
"River",
"SeaLake",
),
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"emnist",
categories=list(string.digits + string.ascii_uppercase + string.ascii_lowercase),
homepage="https://www.westernsydney.edu.au/icns/reproducible_research/publication_support_materials/emnist",
valid_options=dict(
split=("train", "test"),
image_set=(
"Balanced",
"By_Merge",
"By_Class",
"Letters",
"Digits",
"MNIST",
),
),
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"fashionmnist",
categories=(
"T-shirt/top",
"Trouser",
"Pullover",
"Dress",
"Coat",
"Sandal",
"Shirt",
"Sneaker",
"Bag",
"Ankle boot",
),
homepage="https://github.com/zalandoresearch/fashion-mnist",
valid_options=dict(split=("train", "test"), ),
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"cifar10",
type=DatasetType.RAW,
homepage="https://www.cs.toronto.edu/~kriz/cifar.html",
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
type(self).__name__.lower(),
homepage="https://www.cs.toronto.edu/~kriz/cifar.html",
valid_options=dict(split=("train", "test")),
)
def info(self) -> DatasetInfo:
return DatasetInfo(
"caltech101",
categories=HERE / "caltech101.categories",
homepage="http://www.vision.caltech.edu/Image_Datasets/Caltech101",
)
def _make_info(self) -> DatasetInfo:
return DatasetInfo(
"caltech256",
type=DatasetType.IMAGE,
homepage="http://www.vision.caltech.edu/Image_Datasets/Caltech256",
)