CIFAR-100
OpenML dataset with id 41983
Author name not available (Why is that?)
Full work available at URL: https://api.openml.org/data/v1/download/21388406/CIFAR-100.arff
Upload date: 23 July 2019
Dataset Characteristics
Number of classes: 100
Number of features: 3,073 (numeric: 3,072, symbolic: 1 and in total binary: 0 )
Number of instances: 60,000
Number of instances with missing values: 0
Number of missing values: 0
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).
This page was built for dataset: CIFAR-100
