torchvision (ecosystem)

E96634

PyTorch ecosystem component computer vision library software library

torchvision is a PyTorch-based computer vision library providing datasets, model architectures, and image transformations commonly used for training and evaluating deep learning models.

Aliases (6)

Statements (74)

Predicate	Object
instanceOf	PyTorch ecosystem component → computer vision library → software library →
dataset	CIFAR10 → CIFAR100 → COCO → CelebA → FashionMNIST → ImageNet → MNIST → SVHN → VOCDetection → VOCSegmentation →
designedFor	deep learning researchers → machine learning practitioners →
domain	computer vision →
framework	PyTorch →
hasSubmodule	torchvision.datasets → torchvision.io → torchvision.models → torchvision.ops → torchvision.transforms →
implements	image classification models → image transformations → instance segmentation models → keypoint detection models → object detection models → semantic segmentation models → video transformations →
integratesWith	torch.utils.data.DataLoader →
license	BSD-style license →
modelFamily	DenseNet → FasterRCNN → GoogLeNet → InceptionV3 → KeypointRCNN → MaskRCNN → MobileNetV2 → ResNet → RetinaNet → ShuffleNetV2 → SqueezeNet → VGG →
partOf	PyTorch ecosystem →
programmingLanguage	Python →
provides	data loading utilities → model evaluation utilities → pretrained models → standard vision datasets →
repositoryPlatform	GitHub →
supports	CPU → CUDA → GPU → TorchScript →
supportsTask	image classification → instance segmentation → keypoint detection → object detection → semantic segmentation → video classification →
transformType	CenterCrop → ColorJitter → Compose → Normalize → RandomCrop → RandomHorizontalFlip → RandomResizedCrop → RandomRotation → Resize → ToTensor →
useCase	benchmarking on standard datasets → data augmentation for images → evaluating computer vision models → training deep learning vision models →

Referenced by (6)

Subject (surface form when different)	Predicate
torchvision ("torchvision.datasets") → torchvision ("torchvision.models") → torchvision ("torchvision.transforms") → torchvision ("torchvision.io") → torchvision ("torchvision.ops") →	hasSubmodule
PyTorch →	hasComponent