keras_example.py 文件源码

def load_data(dataset):
    ''' Loads the dataset
    :type dataset: string
    :param dataset: the path to the dataset (here MNIST)
    '''

    #############
    # LOAD DATA #
    #############

    # Download the MNIST dataset if it is not present
    data_dir, data_file = os.path.split(dataset)
    if data_dir == "" and not os.path.isfile(dataset):
        # Check if dataset is in the data directory.
        new_path = os.path.join(
            os.path.split(__file__)[0],
            "data",
            dataset
        )
        if os.path.isfile(new_path) or data_file == 'mnist.pkl.gz':
            dataset = new_path

    if (not os.path.isfile(dataset)) and data_file == 'mnist.pkl.gz':
        import urllib
        origin = (
            'http://www.iro.umontreal.ca/~lisa/deep/data/mnist/mnist.pkl.gz'
        )
        print('Downloading data from %s' % origin)
        urllib.urlretrieve(origin, dataset)

    print('loading data...')

    # Load the dataset
    f = gzip.open(dataset, 'rb')
    if sys.version_info[0] == 3:
        u = pickle._Unpickler(f)
        u.encoding = 'latin1'
        train_set, valid_set, test_set = u.load()
    else:
        train_set, valid_set, test_set = pickle.load(f)

    f.close()
    #train_set, valid_set, test_set format: tuple(input, target)
    #input is an numpy.ndarray of 2 dimensions (a matrix)
    #which row's correspond to an example. target is a
    #numpy.ndarray of 1 dimensions (vector)) that have the same length as
    #the number of rows in the input. It should give the target
    #target to the example with the same index in the input.

    return train_set, valid_set, test_set