pugh_torch.datasets.classification package

Submodules

pugh_torch.datasets.classification.cifar module

class pugh_torch.datasets.classification.cifar.CIFAR10(*args, **kwargs)

Bases: pugh_torch.datasets.torchvision.TorchVisionDataset

Note both “val” and “test” splits map to “test”

auto_construct = False

torchvision_constructor

alias of torchvision.datasets.cifar.CIFAR10

class pugh_torch.datasets.classification.cifar.CIFAR100(*args, **kwargs)

Bases: pugh_torch.datasets.classification.cifar.CIFAR10

Note both “val” and “test” splits map to “test”

torchvision_constructor

alias of torchvision.datasets.cifar.CIFAR100

pugh_torch.datasets.classification.imagenet module

Example of a lightly wrapped torchvision dataset.

This is mostly done for greater flexibility of the data processing pipeline.

class pugh_torch.datasets.classification.imagenet.ImageNet(*args, **kwargs)

Bases: pugh_torch.datasets.torchvision.TorchVisionDataset

Attempts to download data.

Parameters

• split (str) – One of {“train”, “val”, “test”}. Which data partition to use. Case insensitive.

• transform (obj) – Whatever format you want. Depends on dataset __getitem__ implementation. Defaults to just a ToTensor transform. This attribute is NOT used anywhere except in the dataset-specific __get__ implementation, or other parent classes of the dataset..

auto_construct = False

download()

Handled by the torchvision dataset

torchvision_constructor

alias of torchvision.datasets.imagenet.ImageNet

pugh_torch.datasets.classification.mnist module

class pugh_torch.datasets.classification.mnist.MNIST(*args, **kwargs)

Bases: pugh_torch.datasets.torchvision.TorchVisionDataset

Note both “val” and “test” splits map to “test”

auto_construct = False

torchvision_constructor

alias of torchvision.datasets.mnist.MNIST

Module contents

pugh_torch.datasets.classification.__init__