edflow.datasets.cifar module

Reference

class edflow.datasets.cifar.CIFAR10(config=None)[source]

Bases: edflow.data.dataset_mixin.DatasetMixin

NAME = 'CIFAR10'
URL = 'https://www.cs.toronto.edu/~kriz/'
FILES = {'DATA': 'cifar-10-python.tar.gz'}
__init__(config=None)[source]

Initialize self. See help(type(self)) for accurate signature.

get_split()[source]
get_example(i)[source]

Note

Please the documentation of DatasetMixin to not be confused.

Add default behaviour for datasets defining an attribute data, which in turn is a dataset. This happens often when stacking several datasets on top of each other.

The default behaviour now is to return self.data.get_example(idx) if possible, and otherwise revert to the original behaviour.

class edflow.datasets.cifar.CIFAR10Train(config=None)[source]

Bases: edflow.datasets.cifar.CIFAR10

class edflow.datasets.cifar.CIFAR10Test(config=None)[source]

Bases: edflow.datasets.cifar.CIFAR10