关于Tensorflow模型保存与读取的问题

关于Tensorflow模型保存与读取的问题

求助大神，Tensorflow构架的保存读取问题

想请教一下各位大神，我用tensorflow搭建了一个神经网络，想要保存和读取神经网络的输出，看过一篇相关的代码，自己也尝试着写了一下，但是有问题，哪位大神可以解答一下应该怎么改？代码如下。

import tensorflow as tf
import numpy as np
import pandas as pd

def add_layer_hidden(inputs,in_size,out_size,activation_function=None):
    weights1 = tf.Variable(tf.random_normal([in_size, out_size]),dtype=tf.float32)
    biases1 = tf.Variable(tf.zeros([1, out_size]) + 0.1,dtype=tf.float32)
    a = weights1[0]
    b = weights1[1]
    Wx_plus_b = tf.matmul(inputs, weights1) + biases1
    if activation_function == None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function( Wx_plus_b )
    return outputs,a,b
x_train = np.linspace(0,2,100,endpoint=True)    
X_t=pd.read_csv('E:/test.csv',header=0,encoding='gbk')
X