init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    for i in range(NUM_EPOCHS):
        c, o = sess.run([cost, optimizer], feed_dict={X: X_train, Y: y_train})
        print(np.sum(c))
    X_test = np.array([binary_encode(i) for i in range(1, 100)])
    y_test = np.array([fizz_buzz_encode(i) for i in range(1, 100)])
    pred = sess.run(z2, feed_dict={X:X_test, Y:y_test})