CIFAR 10

class olympus.datasets.cifar10.CIFAR10(data_path, transform=True, transform_seed=0, cache=None)

Bases: olympus.datasets.dataset.AllDataset

The CIFAR-10 dataset (Canadian Institute For Advanced Research) is a collection of images that are commonly used to train machine learning and computer vision algorithms. It is one of the most widely used datasets for machine learning research. The CIFAR-10 dataset contains 60,000 32x32 color images in 10 different classes. More on wikipedia.

The full specification can be found at here. See also CIFAR100

References

[1]	Alex Krizhevsky, “Learning Multiple Layers of Features from Tiny Images”, 2009.

Attributes:

classes: List[int]

Return the mapping between samples index and their class

input_shape: (3, 32, 32)

Size of a sample stored in this dataset

target_shape: (10,)

There are 10 classes (airplane, automobile, bird, cat, deer, dog, frog, horse, ship, truck)

train_size: 40000

Size of the train dataset

valid_size: 10000

Size of the validation dataset

test_size: 10000

Size of the test dataset

Methods

categories()	Dataset tags so we can filter what we want depending on the task
transforms()

register_datapipe_as_function
register_function

static categories()

Dataset tags so we can filter what we want depending on the task