Ahmed9275/Vit-Cifar100
Image Classification
•
Updated
•
450
•
2
Datasets:
Tasks:
Image Classification
Languages:
English
Multilinguality:
monolingual
Size Categories:
10K<n<100K
Language Creators:
found
Annotations Creators:
crowdsourced
Source Datasets:
extended|other-80-Million-Tiny-Images
License:
unknown
img
image
| fine_label
class label
100 classes
| coarse_label
class label
20 classes
|
|---|---|---|
 | 19
(cattle) | 11
(large_omnivores_and_herbivores) |
 | 29
(dinosaur) | 15
(reptiles) |
 | 0
(apple) | 4
(fruit_and_vegetables) |
 | 11
(boy) | 14
(people) |
 | 1
(aquarium_fish) | 1
(fish) |
 | 86
(telephone) | 5
(household_electrical_devices) |
 | 90
(train) | 18
(vehicles_1) |
 | 28
(cup) | 3
(food_containers) |
 | 23
(cloud) | 10
(large_natural_outdoor_scenes) |
 | 31
(elephant) | 11
(large_omnivores_and_herbivores) |
 | 39
(keyboard) | 5
(household_electrical_devices) |
 | 96
(willow_tree) | 17
(trees) |
 | 82
(sunflower) | 2
(flowers) |
 | 17
(castle) | 9
(large_man-made_outdoor_things) |
 | 71
(sea) | 10
(large_natural_outdoor_scenes) |
 | 39
(keyboard) | 5
(household_electrical_devices) |
 | 8
(bicycle) | 18
(vehicles_1) |
 | 97
(wolf) | 8
(large_carnivores) |
 | 80
(squirrel) | 16
(small_mammals) |
 | 71
(sea) | 10
(large_natural_outdoor_scenes) |
 | 74
(shrew) | 16
(small_mammals) |
 | 59
(pine_tree) | 17
(trees) |
 | 70
(rose) | 2
(flowers) |
 | 87
(television) | 5
(household_electrical_devices) |
 | 59
(pine_tree) | 17
(trees) |
 | 84
(table) | 6
(household_furniture) |
 | 64
(possum) | 12
(medium_mammals) |
 | 52
(oak_tree) | 17
(trees) |
 | 42
(leopard) | 8
(large_carnivores) |
 | 64
(possum) | 12
(medium_mammals) |
 | 8
(bicycle) | 18
(vehicles_1) |
 | 17
(castle) | 9
(large_man-made_outdoor_things) |
 | 47
(maple_tree) | 17
(trees) |
 | 65
(rabbit) | 16
(small_mammals) |
 | 21
(chimpanzee) | 11
(large_omnivores_and_herbivores) |
 | 22
(clock) | 5
(household_electrical_devices) |
 | 81
(streetcar) | 19
(vehicles_2) |
 | 11
(boy) | 14
(people) |
 | 24
(cockroach) | 7
(insects) |
 | 84
(table) | 6
(household_furniture) |
 | 78
(snake) | 15
(reptiles) |
 | 45
(lobster) | 13
(non-insect_invertebrates) |
 | 49
(mountain) | 10
(large_natural_outdoor_scenes) |
 | 97
(wolf) | 8
(large_carnivores) |
 | 56
(palm_tree) | 17
(trees) |
 | 76
(skyscraper) | 9
(large_man-made_outdoor_things) |
 | 11
(boy) | 14
(people) |
 | 90
(train) | 18
(vehicles_1) |
 | 89
(tractor) | 19
(vehicles_2) |
 | 78
(snake) | 15
(reptiles) |
 | 73
(shark) | 1
(fish) |
 | 14
(butterfly) | 7
(insects) |
 | 87
(television) | 5
(household_electrical_devices) |
 | 9
(bottle) | 3
(food_containers) |
 | 71
(sea) | 10
(large_natural_outdoor_scenes) |
 | 6
(bee) | 7
(insects) |
 | 47
(maple_tree) | 17
(trees) |
 | 20
(chair) | 6
(household_furniture) |
 | 98
(woman) | 14
(people) |
 | 47
(maple_tree) | 17
(trees) |
 | 36
(hamster) | 16
(small_mammals) |
 | 55
(otter) | 0
(aquatic_mammals) |
 | 72
(seal) | 0
(aquatic_mammals) |
 | 43
(lion) | 8
(large_carnivores) |
 | 51
(mushroom) | 4
(fruit_and_vegetables) |
 | 35
(girl) | 14
(people) |
 | 83
(sweet_pepper) | 4
(fruit_and_vegetables) |
 | 33
(forest) | 10
(large_natural_outdoor_scenes) |
 | 27
(crocodile) | 15
(reptiles) |
 | 53
(orange) | 4
(fruit_and_vegetables) |
 | 92
(tulip) | 2
(flowers) |
 | 50
(mouse) | 16
(small_mammals) |
 | 15
(camel) | 11
(large_omnivores_and_herbivores) |
 | 89
(tractor) | 19
(vehicles_2) |
 | 36
(hamster) | 16
(small_mammals) |
 | 18
(caterpillar) | 7
(insects) |
 | 89
(tractor) | 19
(vehicles_2) |
 | 46
(man) | 14
(people) |
 | 33
(forest) | 10
(large_natural_outdoor_scenes) |
 | 42
(leopard) | 8
(large_carnivores) |
 | 39
(keyboard) | 5
(household_electrical_devices) |
 | 64
(possum) | 12
(medium_mammals) |
 | 75
(skunk) | 12
(medium_mammals) |
 | 38
(kangaroo) | 11
(large_omnivores_and_herbivores) |
 | 23
(cloud) | 10
(large_natural_outdoor_scenes) |
 | 42
(leopard) | 8
(large_carnivores) |
 | 66
(raccoon) | 12
(medium_mammals) |
 | 77
(snail) | 13
(non-insect_invertebrates) |
 | 49
(mountain) | 10
(large_natural_outdoor_scenes) |
 | 18
(caterpillar) | 7
(insects) |
 | 46
(man) | 14
(people) |
 | 15
(camel) | 11
(large_omnivores_and_herbivores) |
 | 35
(girl) | 14
(people) |
 | 69
(rocket) | 19
(vehicles_2) |
 | 95
(whale) | 0
(aquatic_mammals) |
 | 83
(sweet_pepper) | 4
(fruit_and_vegetables) |
 | 75
(skunk) | 12
(medium_mammals) |
 | 99
(worm) | 13
(non-insect_invertebrates) |
 | 73
(shark) | 1
(fish) |
 | 93
(turtle) | 15
(reptiles) |
Dataset Card for CIFAR-100
Dataset Summary
The CIFAR-100 dataset consists of 60000 32x32 colour images in 100 classes, with 600 images per class. There are 500 training images and 100 testing images per class. There are 50000 training images and 10000 test images. The 100 classes are grouped into 20 superclasses. There are two labels per image - fine label (actual class) and coarse label (superclass).
Supported Tasks and Leaderboards
image-classification: The goal of this task is to classify a given image into one of 100 classes. The leaderboard is available here.
Languages
English
Dataset Structure
Data Instances
A sample from the training set is provided below:
{
'img': <PIL.PngImagePlugin.PngImageFile image mode=RGB size=32x32 at 0x2767F58E080>, 'fine_label': 19,
'coarse_label': 11
}
Data Fields
img: APIL.Image.Imageobject containing the 32x32 image. Note that when accessing the image column:dataset[0]["image"]the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the"image"column, i.e.dataset[0]["image"]should always be preferred overdataset["image"][0]fine_label: anintclassification label with the following mapping:0: apple1: aquarium_fish2: baby3: bear4: beaver5: bed6: bee7: beetle8: bicycle9: bottle10: bowl11: boy12: bridge13: bus14: butterfly15: camel16: can17: castle18: caterpillar19: cattle20: chair21: chimpanzee22: clock23: cloud24: cockroach25: couch26: cra27: crocodile28: cup29: dinosaur30: dolphin31: elephant32: flatfish33: forest34: fox35: girl36: hamster37: house38: kangaroo39: keyboard40: lamp41: lawn_mower42: leopard43: lion44: lizard45: lobster46: man47: maple_tree48: motorcycle49: mountain50: mouse51: mushroom52: oak_tree53: orange54: orchid55: otter56: palm_tree57: pear58: pickup_truck59: pine_tree60: plain61: plate62: poppy63: porcupine64: possum65: rabbit66: raccoon67: ray68: road69: rocket70: rose71: sea72: seal73: shark74: shrew75: skunk76: skyscraper77: snail78: snake79: spider80: squirrel81: streetcar82: sunflower83: sweet_pepper84: table85: tank86: telephone87: television88: tiger89: tractor90: train91: trout92: tulip93: turtle94: wardrobe95: whale96: willow_tree97: wolf98: woman99: wormcoarse_label: anintcoarse classification label with following mapping:0: aquatic_mammals1: fish2: flowers3: food_containers4: fruit_and_vegetables5: household_electrical_devices6: household_furniture7: insects8: large_carnivores9: large_man-made_outdoor_things10: large_natural_outdoor_scenes11: large_omnivores_and_herbivores12: medium_mammals13: non-insect_invertebrates14: people15: reptiles16: small_mammals17: trees18: vehicles_119: vehicles_2
Data Splits
| name | train | test |
|---|---|---|
| cifar100 | 50000 | 10000 |
Dataset Creation
Curation Rationale
[More Information Needed]
Source Data
Initial Data Collection and Normalization
[More Information Needed]
Who are the source language producers?
[More Information Needed]
Annotations
Annotation process
[More Information Needed]
Who are the annotators?
[More Information Needed]
Personal and Sensitive Information
[More Information Needed]
Considerations for Using the Data
Social Impact of Dataset
[More Information Needed]
Discussion of Biases
[More Information Needed]
Other Known Limitations
[More Information Needed]
Additional Information
Dataset Curators
[More Information Needed]
Licensing Information
[More Information Needed]
Citation Information
@TECHREPORT{Krizhevsky09learningmultiple,
author = {Alex Krizhevsky},
title = {Learning multiple layers of features from tiny images},
institution = {},
year = {2009}
}
Contributions
Thanks to @gchhablani for adding this dataset.
- Downloads last month
- 51,020
Homepage:
CIFAR Datasets
Paper:
Paper
Leaderboard:
Leaderboard:
Point of Contact:
Point of Contact:
Size of downloaded dataset files:
169 MB
Size of the auto-converted Parquet files:
142 MB
Number of rows:
60,000
