__init__.py 文件源码

def create_mnist_dataset():
    images, labels = get_mnist_raw_data()
    mask = labels != 0
    print("Pre-zero removal:  Label / N : {0}".format([(v, c) for v, c in zip(_range(10), np.bincount(labels))]))
    images = list(itertools.compress(images, mask))
    labels = labels[mask]

    images = images[3::20]
    labels = labels[3::20]

    print("Pre-blobify:  Label / N : {0}".format([(v, c) for v, c in zip(_range(10), np.bincount(labels))]))
    y = np.array(labels, 'int8')
    images, mask = blobify(images)
    y = y[mask]
    print("Post-blobify:  Label / N : {0}".format([(v, c) for v, c in zip(_range(10), np.bincount(y))]))

    print("Extract features...")
    X = np.array([extract_efd_features(img) for img in images])

    try:
        os.makedirs(os.path.expanduser('~/sudokuextract'))
    except:
        pass

    try:
        for i, (img, lbl) in enumerate(zip(images, labels)):
            img = Image.fromarray(img, 'L')
            with open(os.path.expanduser('~/sudokuextract/{1}_{0:04d}.jpg'.format(i + 1, lbl)), 'w') as f:
                img.save(f)
    except Exception as e:
        print(e)

    return images, labels, X, y