CIFAR-10

E367298
benchmark dataset computer vision dataset image classification dataset

CIFAR-10 is a widely used computer vision dataset of 60,000 labeled low-resolution images across 10 object classes, commonly employed to benchmark image classification algorithms.

Try in SPARQL Jump to: Surface forms Statements Referenced by

All labels observed (3)

Label Occurrences
CIFAR-10 canonical 3
CIFAR-10 dataset 3
CIFAR10 1

Statements (52)

Predicate Object
instanceOf benchmark dataset ⓘ
computer vision dataset ⓘ
image classification dataset ⓘ
baselineModelType convolutional neural network ⓘ
classType mutually exclusive ⓘ
commonlyUsedWith convolutional neural networks ⓘ
containsTestSet true ⓘ
containsTrainingSet true ⓘ
dataFormat Python pickled files ⓘ
binary batch files ⓘ
developedAt University of Toronto ⓘ
developedBy Alex Krizhevsky ⓘ
Geoffrey Hinton ⓘ
difficultyLevel moderate ⓘ
domain natural images ⓘ
downloadURL https://www.cs.toronto.edu/~kriz/cifar.html ⓘ
hasClass airplane ⓘ
automobile ⓘ
bird ⓘ
cat ⓘ
deer ⓘ
dog ⓘ
frog ⓘ
horse ⓘ
ship ⓘ
truck ⓘ
hasColorChannels 3 ⓘ
hasImageHeight 32 ⓘ
hasImagesPerClass 6000 ⓘ
hasImageWidth 32 ⓘ
hasNumberOfClasses 10 ⓘ
hasNumberOfImages 60000 ⓘ
hasNumberOfTestImages 10000 ⓘ
hasNumberOfTrainingImages 50000 ⓘ
hasTestImagesPerClass 1000 ⓘ
hasTrainingImagesPerClass 5000 ⓘ
imageSource tiny images dataset ⓘ
imageType RGB ⓘ
introducedInYear 2009 ⓘ
isBalanced true ⓘ
isPubliclyAvailable true ⓘ
labelType single-label ⓘ
license MIT-like license ⓘ
partOf CIFAR ⓘ
surface form: CIFAR datasets
predecessor tiny images dataset ⓘ
surface form: Tiny Images dataset
publishedBy Canadian Institute for Advanced Research ⓘ
resolution 32x32 pixels ⓘ
typicalSplit 50000 training / 10000 test ⓘ
usedFor benchmarking deep learning models ⓘ
benchmarking machine learning algorithms ⓘ
image classification ⓘ
supervised learning ⓘ

Referenced by (7)

Full triples — surface form annotated when it differs from this entity's canonical label.

ResNet → benchmarkedOn → CIFAR-10 ⓘ
torchvision (ecosystem) → dataset → CIFAR-10 ⓘ
subject surface form: torchvision
this entity surface form: CIFAR10
PixelRNN → datasetUsed → CIFAR-10 ⓘ
Deep Convolutional GAN → appliedTo → CIFAR-10 ⓘ
this entity surface form: CIFAR-10 dataset
Inception Score → commonlyComputedOn → CIFAR-10 ⓘ
this entity surface form: CIFAR-10 dataset
ResNeXt → evaluatedOn → CIFAR-10 ⓘ
this entity surface form: CIFAR-10 dataset
CIFAR-100 → commonlyUsedWith → CIFAR-10 ⓘ