torchvision

The torchvision package consists of popular datasets, model architectures, and common image transformations for computer vision.

Package Reference

• torchvision.datasets
  • MNIST
  • Fashion-MNIST
  • KMNIST
  • EMNIST
  • QMNIST
  • FakeData
  • COCO
  • LSUN
  • ImageFolder
  • DatasetFolder
  • ImageNet
  • CIFAR
  • STL10
  • SVHN
  • PhotoTour
  • SBU
  • Flickr
  • VOC
  • Cityscapes
  • SBD
  • USPS
  • Kinetics-400
  • HMDB51
  • UCF101
  • CelebA
• torchvision.io
  • Video
• torchvision.models
  • Classification
  • Semantic Segmentation
  • Object Detection, Instance Segmentation and Person Keypoint Detection
  • Video classification
• torchvision.ops
• torchvision.transforms
  • Transforms on PIL Image
  • Transforms on torch.*Tensor
  • Conversion Transforms
  • Generic Transforms
  • Functional Transforms
• torchvision.utils

torchvision.get_image_backend()

Gets the name of the package used to load images

torchvision.set_image_backend(backend)

Specifies the package used to load images.

Parameters

backend (string) – Name of the image backend. one of {‘PIL’, ‘accimage’}. The accimage package uses the Intel IPP library. It is generally faster than PIL, but does not support as many operations.

torchvision.set_video_backend(backend)

Specifies the package used to decode videos.

Parameters

backend (string) – Name of the video backend. one of {‘pyav’, ‘video_reader’}. The pyav package uses the 3rd party PyAv library. It is a Pythonic binding for the FFmpeg libraries. The video_reader package includes a native C++ implementation on top of FFMPEG libraries, and a python API of TorchScript custom operator. It is generally decoding faster than pyav, but perhaps is less robust.