src/not_mnist/merge_prune.py

from __future__ import print_function

import os

import numpy as np
# from six.moves.urllib.request import urlretrieve
# from six.moves import cPickle as pickle
import cPickle as pickle

from not_mnist.img_pickle import maybe_pickle, save_obj

image_size = 28  # Pixel width and height.


def make_arrays(nb_rows, img_size):
    if nb_rows:
        dataset = np.ndarray((nb_rows, img_size, img_size), dtype=np.float32)
        labels = np.ndarray(nb_rows, dtype=np.int32)
    else:
        dataset, labels = None, None
    return dataset, labels


def merge_datasets(pickle_files, train_size, valid_size=0):
    num_classes = len(pickle_files)
    valid_dataset, valid_labels = make_arrays(valid_size, image_size)
    train_dataset, train_labels = make_arrays(train_size, image_size)
    vsize_per_class = valid_size // num_classes
    tsize_per_class = train_size // num_classes

    start_v, start_t = 0, 0
    end_v, end_t = vsize_per_class, tsize_per_class
    end_l = vsize_per_class + tsize_per_class
    for label, pickle_file in enumerate(pickle_files):
        try:
            with open(pickle_file, 'rb') as f:
                letter_set = pickle.load(f)
                # let's shuffle the letters to have random validation and training set
                np.random.shuffle(letter_set)
                if valid_dataset is not None:  # None for test dataSet
                    valid_letter = letter_set[:vsize_per_class, :, :]
                    valid_dataset[start_v:end_v, :, :] = valid_letter
                    valid_labels[start_v:end_v] = label
                    start_v += vsize_per_class
                    end_v += vsize_per_class

                train_letter = letter_set[vsize_per_class:end_l, :, :]
                train_dataset[start_t:end_t, :, :] = train_letter
                train_labels[start_t:end_t] = label
                start_t += tsize_per_class
                end_t += tsize_per_class
        except Exception as e:
            print('Unable to process data from', pickle_file, ':', e)
            raise

    return valid_dataset, valid_labels, train_dataset, train_labels


def randomize(dataset, labels):
    permutation = np.random.permutation(labels.shape[0])
    shuffled_dataset = dataset[permutation, :, :]
    shuffled_labels = labels[permutation]
    return shuffled_dataset, shuffled_labels


def merge_prune(train_folders, test_folders):
    train_datasets = maybe_pickle(train_folders, 45000)
    test_datasets = maybe_pickle(test_folders, 1800)

    train_size = 200000
    valid_size = 10000
    test_size = 10000

    valid_dataset, valid_labels, train_dataset, train_labels = merge_datasets(
        train_datasets, train_size, valid_size)
    _, _, test_dataset, test_labels = merge_datasets(test_datasets, test_size)

    print('Training:', train_dataset.shape, train_labels.shape)
    print('Validation:', valid_dataset.shape, valid_labels.shape)
    print('Testing:', test_dataset.shape, test_labels.shape)

    train_dataset, train_labels = randomize(train_dataset, train_labels)
    test_dataset, test_labels = randomize(test_dataset, test_labels)
    valid_dataset, valid_labels = randomize(valid_dataset, valid_labels)

    pickle_file = 'notMNIST.pickle'
    save = {
        'train_dataset': train_dataset,
        'train_labels': train_labels,
        'valid_dataset': valid_dataset,
        'valid_labels': valid_labels,
        'test_dataset': test_dataset,
        'test_labels': test_labels,
    }
    save_obj(pickle_file, save)


if __name__ == "__main__":
    train_folders = ['notMNIST_large/A', 'notMNIST_large/B', 'notMNIST_large/C', 'notMNIST_large/D', 'notMNIST_large/E',
                     'notMNIST_large/F', 'notMNIST_large/G', 'notMNIST_large/H', 'notMNIST_large/I', 'notMNIST_large/J']
    test_folders = ['notMNIST_small/A', 'notMNIST_small/B', 'notMNIST_small/C', 'notMNIST_small/D', 'notMNIST_small/E',
                    'notMNIST_small/F', 'notMNIST_small/G', 'notMNIST_small/H', 'notMNIST_small/I', 'notMNIST_small/J']
    merge_prune(train_folders, test_folders)