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.

Try in SPARQL Jump to: Surface forms Disambiguation Statements Elicitation Referenced by

All labels observed (7)

Label	Occurrences
TorchVision datasets	1
torchvision (ecosystem) canonical	1
torchvision.datasets	1
torchvision.io	1
torchvision.models	1
torchvision.ops	1
torchvision.transforms	1

How this entity was disambiguated

This entity first appeared as the object of triple T825511 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07

Target entity: torchvision (ecosystem)
Context triple: [PyTorch, hasComponent, torchvision (ecosystem)]

A. PyTorch
PyTorch is an open-source deep learning framework widely used for building and training neural networks, known for its dynamic computation graph and strong support for research and production in Python.
B. TensorFlow
TensorFlow is an open-source, end-to-end machine learning and deep learning framework widely used for building, training, and deploying neural network models at scale.
C. Keras
Keras is a high-level neural networks API written in Python that simplifies building, training, and deploying deep learning models, often running on top of frameworks like TensorFlow.
D. CIFAR
CIFAR (the Canadian Institute for Advanced Research) is a Canadian global research organization that supports long-term, collaborative, interdisciplinary research, including major initiatives in artificial intelligence.
E. VGG
VGG is a deep convolutional neural network architecture known for its simple, uniform use of small 3×3 filters and great depth, which achieved strong performance in image recognition tasks.
F. None of above. chosen
G. Unsure - the case is ambiguous/there is not enough information to decide.

NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07

Target entity: torchvision (ecosystem)
Target entity description: torchvision is a PyTorch-based computer vision library providing datasets, model architectures, and image transformations commonly used for training and evaluating deep learning models.

A. PyTorch
PyTorch is an open-source deep learning framework widely used for building and training neural networks, known for its dynamic computation graph and strong support for research and production in Python.
B. TensorFlow
TensorFlow is an open-source, end-to-end machine learning and deep learning framework widely used for building, training, and deploying neural network models at scale.
C. Keras
Keras is a high-level neural networks API written in Python that simplifies building, training, and deploying deep learning models, often running on top of frameworks like TensorFlow.
D. CIFAR
CIFAR (the Canadian Institute for Advanced Research) is a Canadian global research organization that supports long-term, collaborative, interdisciplinary research, including major initiatives in artificial intelligence.
E. VGG
VGG is a deep convolutional neural network architecture known for its simple, uniform use of small 3×3 filters and great depth, which achieved strong performance in image recognition tasks.
F. None of above. chosen

Statements (74)

Predicate	Object
instanceOf	PyTorch ecosystem component ⓘ computer vision library ⓘ software library ⓘ
dataset	CIFAR-10 ⓘ surface form: CIFAR10 CIFAR-100 ⓘ surface form: CIFAR100 COCO ⓘ CelebA ⓘ Fashion-MNIST ⓘ surface form: FashionMNIST ImageNet ⓘ MNIST ⓘ SVHN ⓘ VOCDetection ⓘ VOCSegmentation ⓘ
designedFor	deep learning researchers ⓘ machine learning practitioners ⓘ
domain	computer vision ⓘ
framework	PyTorch ⓘ
hasSubmodule	torchvision (ecosystem) self-linksurface differs ⓘ surface form: torchvision.datasets torchvision (ecosystem) self-linksurface differs ⓘ surface form: torchvision.io torchvision (ecosystem) self-linksurface differs ⓘ surface form: torchvision.models torchvision (ecosystem) self-linksurface differs ⓘ surface form: torchvision.ops torchvision (ecosystem) self-linksurface differs ⓘ surface form: 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 ⓘ Inception architecture ⓘ surface form: GoogLeNet Inception architecture ⓘ surface form: InceptionV3 KeypointRCNN ⓘ MaskRCNN ⓘ MobileNetV2 ⓘ ResNet ⓘ RetinaNet ⓘ ShuffleNetV2 ⓘ SqueezeNet ⓘ VGG ⓘ
partOf	PyTorch ⓘ surface form: PyTorch ecosystem
programmingLanguage	Python ⓘ
provides	data loading utilities ⓘ model evaluation utilities ⓘ pretrained models ⓘ standard vision datasets ⓘ
repositoryPlatform	GitHub ⓘ
supports	CPU ⓘ NVIDIA CUDA ⓘ surface form: CUDA GPU ⓘ PyTorch ⓘ surface form: 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 ⓘ