How to use the saliency.integrated_gradients.IntegratedGradients function in saliency

x_baseline: Baseline value used in integration. Defaults to 0.
      x_steps: Number of integrated steps between baseline and x.
    """
    if x_baseline is None:
      x_baseline = np.zeros_like(x_value)

    assert x_baseline.shape == x_value.shape

    x_diff = x_value - x_baseline

    total_gradients = np.zeros_like(x_value)

    for alpha in np.linspace(0, 1, x_steps):
      x_step = x_baseline + alpha * x_diff

      total_gradients += super(IntegratedGradients, self).GetMask(
          x_step, feed_dict)

    return total_gradients * x_diff / x_steps

def __init__(self, graph, session, y, x):
    super(XRAI, self).__init__(graph, session, y, x)
    # Initialize integrated gradients.
    self._integrated_gradients = IntegratedGradients(graph, session, y, x)