Shortcuts

Datasets

Torchvision provides many built-in datasets in the torchvision.datasets module, as well as utility classes for building your own datasets.

Built-in datasets

All datasets are subclasses of torch.utils.data.Dataset i.e, they have __getitem__ and __len__ methods implemented. Hence, they can all be passed to a torch.utils.data.DataLoader which can load multiple samples in parallel using torch.multiprocessing workers. For example:

imagenet_data = torchvision.datasets.ImageNet('path/to/imagenet_root/')
data_loader = torch.utils.data.DataLoader(imagenet_data,
                                          batch_size=4,
                                          shuffle=True,
                                          num_workers=args.nThreads)

All the datasets have almost similar API. They all have two common arguments: transform and target_transform to transform the input and target respectively. You can also create your own datasets using the provided base classes.

Caltech101(root, target_type, str] =, …)

Caltech 101 Dataset.

Caltech256(root, transform, …)

Caltech 256 Dataset.

CelebA(root, split, target_type, str] =, …)

Large-scale CelebFaces Attributes (CelebA) Dataset Dataset.

CIFAR10(root, train, transform, …)

CIFAR10 Dataset.

CIFAR100(root, train, transform, …)

CIFAR100 Dataset.

Cityscapes(root, split, mode, target_type, …)

Cityscapes Dataset.

CocoCaptions(root, annFile, transform, …)

MS Coco Captions Dataset.

CocoDetection(root, annFile, transform, …)

MS Coco Detection Dataset.

Country211(root, split, transform, …)

The Country211 Data Set from OpenAI.

DTD(root, split, partition, transform, …)

Describable Textures Dataset (DTD).

EMNIST(root, split, **kwargs)

EMNIST Dataset.

EuroSAT(root, transform, target_transform, …)

RGB version of the EuroSAT Dataset.

FakeData(size, image_size, int, int] =, …)

A fake dataset that returns randomly generated images and returns them as PIL images

FashionMNIST(root, train, transform, …)

Fashion-MNIST Dataset.

FER2013(root, split, transform, target_transform)

FER2013 Dataset.

Flickr8k(root, ann_file, transform, …)

Flickr8k Entities Dataset.

Flickr30k(root, ann_file, transform, …)

Flickr30k Entities Dataset.

Flowers102(root, split, transform, …)

Oxford 102 Flower Dataset.

FlyingChairs(root[, split, transforms])

FlyingChairs Dataset for optical flow.

FlyingThings3D(root[, split, pass_name, …])

FlyingThings3D dataset for optical flow.

Food101(root, split, transform, …)

The Food-101 Data Set.

FGVCAircraft(root, split, annotation_level, …)

FGVC Aircraft Dataset.

GTSRB(root, split, transform, …)

German Traffic Sign Recognition Benchmark (GTSRB) Dataset.

HD1K(root[, split, transforms])

HD1K dataset for optical flow.

HMDB51(root, annotation_path, …)

HMDB51 dataset.

ImageNet(root, split, download, **kwargs)

ImageNet 2012 Classification Dataset.

INaturalist(root, version, target_type, …)

iNaturalist Dataset.

Kinetics400(root, frames_per_clip, …)

Kinetics-400 dataset.

Kitti(root, train, transform, …)

KITTI Dataset.

KittiFlow(root[, split, transforms])

KITTI dataset for optical flow (2015).

KMNIST(root, train, transform, …)

Kuzushiji-MNIST Dataset.

LFWPeople(root, split, image_set, transform, …)

LFW Dataset.

LFWPairs(root, split, image_set, transform, …)

LFW Dataset.

LSUN(root, classes, List[str]] =, transform, …)

LSUN dataset.

MNIST(root, train, transform, …)

MNIST Dataset.

Omniglot(root, background, transform, …)

Omniglot Dataset.

OxfordIIITPet(root, split, target_types, …)

Oxford-IIIT Pet Dataset.

PCAM(root, split, transform, …)

PCAM Dataset.

PhotoTour(root, name, train, transform, download)

Multi-view Stereo Correspondence Dataset.

Places365(root, split, small, download, …)

Places365 classification dataset.

RenderedSST2(root, split, transform, …)

The Rendered SST2 Dataset.

QMNIST(root, what, compat, train, **kwargs)

QMNIST Dataset.

SBDataset(root, image_set, mode, download, …)

Semantic Boundaries Dataset

SBU(root, transform, target_transform, download)

SBU Captioned Photo Dataset.

SEMEION(root, transform, target_transform, …)

SEMEION Dataset.

Sintel(root[, split, pass_name, transforms])

Sintel Dataset for optical flow.

StanfordCars(root, split, transform, …)

Stanford Cars Dataset

STL10(root, split, folds, transform, …)

STL10 Dataset.

SUN397(root, transform, target_transform, …)

The SUN397 Data Set.

SVHN(root, split, transform, …)

SVHN Dataset.

UCF101(root, annotation_path, …)

UCF101 dataset.

USPS(root, train, transform, …)

USPS Dataset.

VOCSegmentation(root, year, image_set, …)

Pascal VOC Segmentation Dataset.

VOCDetection(root, year, image_set, …)

Pascal VOC Detection Dataset.

WIDERFace(root, split, transform, …)

WIDERFace Dataset.

Base classes for custom datasets

DatasetFolder(root, loader, Any], …)

A generic data loader.

ImageFolder(root, transform, …)

A generic data loader where the images are arranged in this way by default: .

VisionDataset(root, transforms, transform, …)

Base Class For making datasets which are compatible with torchvision.

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources