nip.image_classification.data#
Data classes for the image classification task.
Contains the ImageClassificationDataset
class, which is a dataset for the image
classification task. The dataset is a binary classification problem, where the classes
are selected from a torchvision dataset. The dataset is binarified using one of the
following methods:
“merge”: The classes are shuffled and merged into two classes.
“select_two”: Two classes are selected from the original dataset.
“random”: The classes are selected at random.
Functions
|
Register a dataset wrapper class. |
Classes
|
The CIFAR-100 dataset wrapper. |
|
The CIFAR-10 dataset wrapper. |
|
The Fashion-MNIST dataset wrapper. |
|
A dataset for the image classification task. |
|
The Kuzushiji-MNIST dataset wrapper. |
|
The MNIST dataset wrapper. |
|
The Street View House Numbers dataset wrapper. |
|
A fake dataset for testing. |
|
A wrapper for TorchVision datasets, implementing a common interface. |