def layer_norm_compute_python(x, epsilon, scale, bias):
    mean = tf.reduce_mean(x, axis=[-1], keep_dims=True)
    variance = tf.reduce_mean(tf.square(x - mean), axis=[-1], keep_dims=True)
    norm_x = (x - mean) * tf.rsqrt(variance + epsilon)
    return norm_x * scale + bias

def layer_norm(x, filters=None, epsilon=1e-6, scope=None, reuse=None):
    if filters is None:
        filters = x.get_shape()[-1]
    with tf.variable_scope(scope, default_name="layer_norm", values=[x], reuse=reuse):
        scale = tf.get_variable(
            "layer_norm_scale", [filters], regularizer = regularizer, initializer=tf.ones_initializer())
        bias = tf.get_variable(
            "layer_norm_bias", [filters], regularizer = regularizer, initializer=tf.zeros_initializer())
        result = layer_norm_compute_python(x, epsilon, scale, bias)
        return result

--参考QANET代码