deep_bottleneck.datasets package

Submodules

deep_bottleneck.datasets.fashion_mnist module

deep_bottleneck.datasets.fashion_mnist.load()[source]

Load the Fashion-MNIST dataset

The output follows the following naming convention:

  • X is the data
  • y is class, with numbers from 0 to 9
  • Y is class, but coded as a 10-dim vector with one entry set to 1 at the column index corresponding to the class
Returns:Returns two namedtuples, the first one containing training and the second one containing test data respectively. Both come with fields X, y and Y:

deep_bottleneck.datasets.harmonics module

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

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='')[source]

Load the Information Bottleneck harmonics dataset

The output follows the following naming convention:

  • X is the data
  • y is class, with numbers from 0 to 9
  • Y is class, but coded as a 10-dim vector with one entry set to 1 at the column index corresponding to the class
Returns:Returns two namedtuples, the first one containing training and the second one containing test data respectively. Both come with fields X, y and Y:

deep_bottleneck.datasets.mnist module

deep_bottleneck.datasets.mnist.load()[source]

Load the MNIST handwritten digits dataset

The output follows the following naming convention:

  • X is the data
  • y is class, with numbers from 0 to 9
  • Y is class, but coded as a 10-dim vector with one entry set to 1 at the column index corresponding to the class
Returns:Returns two namedtuples, the first one containing training and the second one containing test data respectively. Both come with fields X, y and Y:

deep_bottleneck.datasets.mushroom module

deep_bottleneck.datasets.mushroom.load()[source]

Load the mushroom dataset.

Mushrooms are to be classified as either edible or poisonous. The output follows the following naming convention:

  • X is the data
  • y is class, with numbers from 0 to 9
  • Y is class, but coded as a 10-dim vector with one entry set to 1 at the column index corresponding to the class
Returns:Returns two namedtuples, the first one containing training and the second one containing test data respectively. Both come with fields X, y and Y:

Module contents