CIFAR-100 Computer Vision Project

University of Toronto

Updated 6 months ago

55

views

1

download
Classes (120)
apple
aquarium_fish
aquatic_mammals
baby
bear beaver bed bee
beetle
bicycle bottle bowl
boy
bridge bus butterfly camel can castle
caterpillar
cattle chair
chimpanzee
clock cloud
cockroach
couch crab crocodile cup
dinosaur
dolphin elephant fish
flatfish
flowers
food_containers
forest fox
fruit_and_vegetables
girl
hamster
house
household_electrical_devices
household_furniture
insects kangaroo keyboard lamp
large_carnivores
large_man-made_outdoor_things
large_natural_outdoor_scenes
large_omnivores_and_herbivores
lawn_mower
leopard lion
lizard
lobster
man
maple_tree
medium_mammals
motorcycle mountain mouse mushroom
non-insect_invertebrates
oak_tree
orange
orchid
otter
palm_tree
pear people
pickup_truck
pine_tree
plain
plate
poppy
porcupine
possum
rabbit raccoon
ray
reptiles
road rocket rose
sea
seal
shark shrew
skunk
skyscraper
small_mammals
snail
snake spider squirrel
streetcar
sunflower
sweet_pepper
table tank
telephone
television tiger tractor train trees
trout
tulip
turtle
vehicles_1
vehicles_2
wardrobe
whale
willow_tree
wolf
woman
worm

Metrics

Try This Model
Drop an image or
Description

The CIFAR-10 and CIFAR-100 are labeled subsets of the 80 million tiny images dataset. They were collected by Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton.

The CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images.

The dataset is divided into five training batches and one test batch, each with 10000 images. The test batch contains exactly 1000 randomly-selected images from each class. The training batches contain the remaining images in random order, but some training batches may contain more images from one class than another. Between them, the training batches contain exactly 5000 images from each class.

This dataset is just like the CIFAR-10, except it has 100 classes containing 600 images each. There are 500 training images and 100 testing images per class. The 100 classes in the CIFAR-100 are grouped into 20 superclasses. Each image comes with a "fine" label (the class to which it belongs) and a "coarse" label (the superclass to which it belongs).

The classes are completely mutually exclusive. There is no overlap between automobiles and trucks. "Automobile" includes sedans, SUVs, things of that sort. "Truck" includes only big trucks. Neither includes pickup trucks.

Use This Trained Model

Try it in your browser, or deploy via our Hosted Inference API and other deployment methods.

Supervision

Build Computer Vision Applications Faster with Supervision

Visualize and process your model results with our reusable computer vision tools.

Cite This Project

LICENSE
CC BY 4.0

If you use this dataset in a research paper, please cite it using the following BibTeX:

                        @misc{
                            cifar-100-piz8k_dataset,
                            title = { CIFAR-100 Dataset },
                            type = { Open Source Dataset },
                            author = { University of Toronto },
                            howpublished = { \url{ https://universe.roboflow.com/university-of-toronto-gzhju/cifar-100-piz8k } },
                            url = { https://universe.roboflow.com/university-of-toronto-gzhju/cifar-100-piz8k },
                            journal = { Roboflow Universe },
                            publisher = { Roboflow },
                            year = { 2024 },
                            month = { may },
                            note = { visited on 2024-11-21 },
                            }