# CIFAR-10 The CIFAR-10 dataset of images. The dataset consists of 60,000 32 x 32 color images in 10 classes, with 6,000 images per class. There are 50,000 training images and 10,000 test images. **Details** - Dataset name: `cifar10` - Dataset source: [https://www.cs.toronto.edu/~kriz/cifar.html](https://www.cs.toronto.edu/~kriz/cifar.html) - Dataset size: 132.40 MB - Tags: `image, classification` - Supported splits: `train, test` - ZooDataset classes: - [`CIFAR10Dataset`](../../api/fiftyone.zoo.datasets.tf.md#fiftyone.zoo.datasets.tf.CIFAR10Dataset) (TF backend) - [`CIFAR10Dataset`](../../api/fiftyone.zoo.datasets.torch.md#fiftyone.zoo.datasets.torch.CIFAR10Dataset) (Torch backend) #### NOTE You must have the [Torch or TensorFlow backend(s)](../api.md#dataset-zoo-ml-backend) installed to load this dataset. **Example usage** Python CLI ```python import fiftyone as fo import fiftyone.zoo as foz dataset = foz.load_zoo_dataset("cifar10", split="test") session = fo.launch_app(dataset) ``` ```shell fiftyone zoo datasets load cifar10 --split test fiftyone app launch cifar10-test ```