保存和载入回归模型

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
#图形显示
def moving_average(a,w=10):
    if len(a)<w:
        return a[:]
    return [val if idx <w else sum(a[(idx-w):idx])/w for idx,val in enumerate(a)]
tf.reset_default_graph()
X = tf.placeholder("float")
Y = tf.placeholder("float")

# 占位符
inputsict = {
    'x': tf.placeholder("float"),
    'y': tf.placeholder("float")
}
# 生成模拟数据
train_X = np.float32(np.linspace(-1, 1, 100))
train_Y=2*train_X+np.random.randn(*train_X.shape)*0.1 #y=2x
plt.plot(train_X,train_Y,'ro',label='data')
plt.show()
#重置图
#tf.reset_default_graph()
#直接定义模型参数
W=tf.Variable(tf.random_normal([1]),name="weight")
b=tf.Variable(tf.zeros([1]),name="bias")

#字典定义学习参数
paradict={
    'W':tf.Variable(tf.random_normal([1])),
    'b':tf.Variable(tf.zeros([1]))
}
#前向结构
Z=tf.multiply(X,paradict['W'])+paradict['b']

#反向传播优化：
cost=tf.reduce_mean(tf.square(Y-Z))
learning_rate=0.01
optimizer=tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)

#初始化所有变量
init =tf.global_variables_initializer()
#定义参数
training_epochs=20
display_step=2

saver=tf.train.Saver()
savedir="D:/data_savelog/"


#启动Session
with tf.Session() as sess:
    sess.run(init)
    plotdata={"batchsize":[],"loss":[]}
    #向模型输入数据
    for epoch in range(training_epochs):
        for (x,y) in zip(train_X,train_Y):
            sess.run(optimizer,feed_dict={X:x,Y:y})

        #显示训练中的详细信息
        if epoch % display_step==0:
            loss=sess.run(cost,feed_dict={X:train_X,Y:train_Y})
            print("Epoch:",epoch+1,"cost=",loss,"W=",sess.run(paradict['W']),
                  "b=",sess.run(paradict['b']))
            if not (loss=="NA"):
                plotdata["batchsize"].append(epoch)
                plotdata["loss"].append(loss)

    print("Finished!")
    saver.save(sess,savedir+"/linermodel.cpkt")
    print("cost=",sess.run(cost,feed_dict={X:train_X,Y:train_Y}),
        "W=",sess.run(paradict['W']),"b=",sess.run(paradict['b']))
    # 重置图
    print(sess.run(paradict['b']))


with tf.Session() as sess2:
    sess2.run(tf.global_variables_initializer())
    saver.restore(sess2,savedir+"linermodel.cpkt")
    print("x=0.2,Z=",sess2.run(Z,feed_dict={X:0.2}))