I am using mean "mu" and "sigma" to execute Gaussian MFS of an ANFIS class

class ANFIS:

def __init__(self, n_inputs, n_rules, learning_rate=1e-2):
    self.n = n_inputs
    self.m = n_rules
    self.inputs = tf.placeholder(tf.float32, shape=(None, n_inputs))  # Input
    self.targets = tf.placeholder(tf.float32, shape=None)  # Desired output
    mu = tf.get_variable("mu", [n_rules * n_inputs],initializer=tf.random_normal_initializer(0,1))  # Means of Gaussian MFS
    

However, I am getting a valueError: that variable mu already exists, disallowing use. Did you mean to set reuse=True or reuse =tf.AUTO_REUSE in python