def step(vectors, axis=-1):
    """
    カプセルネットワークでは非線形の活性化関数が使用される. この関数はベクトルの長さを0~1に圧縮する.
    :param vectors: 圧出される複数のベクトル, 4次元テンソル
    :param axis: 圧縮する軸
    :return: 複数の入力ベクトルと同じ形の一つのテンソル
    """
    s_squared_norm = K.sum(K.square(vectors), axis, keepdims=True)
    return vectors / s_squared_norm

# 前処理として係数を1に初期化
# c.shape = [None, self.num_capsule, self.input_num_capsule].
c = tf.ones(shape=[K.shape(inputs_hat)[0], self.num_capsule, self.input_num_capsule])

assert self.routings > 0, 'The routings should be > 0.'
for i in range(self.routings):
    # inputs_hat.shape=[None, num_capsule, input_num_capsule, dim_capsule]
    # The first two dimensions as `batch` dimension,
    # then matmal: [input_num_capsule] x [input_num_capsule, dim_capsule] -> [dim_capsule].
    # outputs.shape=[None, num_capsule, dim_capsule]
    outputs = step(K.batch_dot(c, inputs_hat, [2, 2]))  # [None, 10, 16]

    if i < self.routings - 1:
        # outputs.shape =  [None, num_capsule, dim_capsule]
        # inputs_hat.shape=[None, num_capsule, input_num_capsule, dim_capsule]
        # The first two dimensions as `batch` dimension,
        # then matmal: [dim_capsule] x [input_num_capsule, dim_capsule]^T -> [input_num_capsule].
        # c.shape=[batch_size, num_capsule, input_num_capsule]
        c += K.batch_dot(outputs, inputs_hat, [2, 3])