deep_bottleneck.datasets package

Submodules

deep_bottleneck.datasets.base_dataset module

class deep_bottleneck.datasets.base_dataset.Dataset(train, test, n_classes)

Bases: object

Representation of a dataset.

classmethod from_labelled_subset(X_train, y_train, X_test, y_test, n_classes)

class deep_bottleneck.datasets.base_dataset.LabelledDataset(examples, labels, one_hot_labels)

Bases: object

Representation of a labelled subset of a dataset.

This could be a trainging, test or validation set.

classmethod from_labels(examples, labels, n_classes)

deep_bottleneck.datasets.fashion_mnist module

deep_bottleneck.datasets.fashion_mnist.load()

Load the Fashion-MNIST dataset

Returns:The fashion mnist dataset.

deep_bottleneck.datasets.harmonics module

deep_bottleneck.datasets.harmonics.import_IB_data_from_mat(name_ID, nb_dir='')

Writes a .npy file to disk containing the harmonics dataset used by Tishby

Parameters:name_ID – Identifier which is going to be part of the output filename Returns:None

deep_bottleneck.datasets.harmonics.load(nb_dir='') → deep_bottleneck.datasets.base_dataset.Dataset

Load the Information Bottleneck harmonics dataset

Returns:The harmonics dataset.

deep_bottleneck.datasets.mnist module

deep_bottleneck.datasets.mnist.load()

Load the MNIST handwritten digits dataset

Returns:The mnist datset.

deep_bottleneck.datasets.mushroom module

deep_bottleneck.datasets.mushroom.load()

Load the mushroom dataset.

Mushrooms are to be classified as either edible or poisonous.

Returns:The mushroom dataset.

Module contents