CIFAR-100

The CIFAR-100 dataset of images.

The dataset consists of 60,000 32 x 32 color images in 100 classes, with 600 images per class. There are 50,000 training images and 10,000 test images.

Details

• Dataset name: cifar100

• Dataset source: https://www.cs.toronto.edu/~kriz/cifar.html

• Dataset size: 132.03 MB

• Tags: image, classification

• Supported splits: train, test

• ZooDataset classes:

  • CIFAR100Dataset (TF backend)

  • CIFAR100Dataset (Torch backend)

Note

You must have the Torch or TensorFlow backend(s) installed to load this dataset.

Example usage

PythonCLI

import fiftyone as fo
import fiftyone.zoo as foz

dataset = foz.load_zoo_dataset("cifar100", split="test")

session = fo.launch_app(dataset)