Data
Data stored as numpy arrays (use function [numpy.load](https://docs.scipy.org/doc/numpy/reference/generated/numpy.load.html) to restore data) and compressed with bzip2.

Train set is splitted into 4 parts. Each file econtains matrix of shape [Nх2]. Grayscale image of character is stored at the first column. At the second column is unicode number of character.

Test set is just array of grayscale images.
Example
import numpy as np
    import matplotlib as pyplot

    data = np.load('train-1.npy')
    width, height = 8, 8

    plt.figure(figsize=(16, 20))
    for n, (image, tag) in enumerate(data, 1):
        if n > width * height:
            break
        plt.subplot(height, width, n)
        plt.title(tag)
        plt.imshow(image, cmap='gray')