dataset.py

########################################################################
#
# Class for creating a data-set consisting of all files in a directory.
#
# Example usage is shown in the file knifey.py and Tutorial #09.
#
# Implemented in Python 3.5
#
########################################################################
#
# This file is part of the TensorFlow Tutorials available at:
#
# https://github.com/Hvass-Labs/TensorFlow-Tutorials
#
# Published under the MIT License. See the file LICENSE for details.
#
# Copyright 2016 by Magnus Erik Hvass Pedersen
#
########################################################################
import numpy as np


########################################################################
def one_hot_encoded(class_numbers, num_classes=None):
    """
    Generate the One-Hot encoded class-labels from an array of integers.

    For example, if class_number=2 and num_classes=4 then
    the one-hot encoded label is the float array: [0. 0. 1. 0.]

    :param class_numbers:
        Array of integers with class-numbers.
        Assume the integers are from zero to num_classes-1 inclusive.

    :param num_classes:
        Number of classes. If None then use max(class_numbers)+1.

    :return:
        2-dim array of shape: [len(class_numbers), num_classes]
    """

    # Find the number of classes if None is provided.
    # Assumes the lowest class-number is zero.
    if num_classes is None:
        num_classes = np.max(class_numbers) + 1

    return np.eye(num_classes, dtype=float)[class_numbers]