tensorflow神经网络拟合非线性函数

# -*- coding: utf-8 -*-
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

plotdata = { "batchsize":[], "loss":[] }
def moving_average(a, w=11):
    if len(a) < w: 
        return a[:]    
    return [val if idx < w else sum(a[(idx-w):idx])/w for idx, val in enumerate(a)]

#生成模拟数据，二次函数关系
train_X = np.linspace(-1, 1, 100)[:, np.newaxis]
train_Y = train_X*train_X + 5 * train_X + np.random.randn(*train_X.shape) * 0.3 

#子图1显示模拟数据点
plt.figure(12)
plt.subplot(221)
plt.plot(train_X, train_Y, ‘ro‘, label=‘Original data‘)
plt.legend()

# 创建模型
# 占位符
X = tf.placeholder("float",[None,1])
Y = tf.placeholder("float",[None,1])
# 模型参数
W1 = tf.Variable(tf.random_normal([1,10]), name="weight")
b1 = tf.Variable(tf.zeros([1,10]), name="bias")
W2 = tf.Variable(tf.random_normal([10,6]), name="weight")
b2 = tf.Variable(tf.zeros([1,6]), name="bias")
W3 = tf.Variable(tf.random_normal([6,1]), name="weight")
b3 = tf.Variable(tf.zeros([1]), name="bias")

# 前向结构
z1 = tf.matmul(X, W1) + b1
z2 = tf.nn.relu(z1)
z3 = tf.matmul(z2, W2) + b2
z4 = tf.nn.relu(z3)
z5 = tf.matmul(z4, W3) + b3

#反向优化
cost =tf.reduce_mean( tf.square(Y - z5))
learning_rate = 0.01
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost) #Gradient descent

# 初始化变量
init = tf.global_variables_initializer()
# 训练参数
training_epochs = 5000
display_step = 2

# 启动session
with tf.Session() as sess:
    sess.run(init)
    for epoch in range(training_epochs+1):
        sess.run(optimizer, feed_dict={X: train_X, Y: train_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, "cost=", loss)
            if not (loss == "NA" ):
                plotdata["batchsize"].append(epoch)
                plotdata["loss"].append(loss)
    print (" Finish")
    
    #图形显示
    plt.subplot(222)    
    plt.plot(train_X, train_Y, ‘ro‘, label=‘Original data‘)
    plt.plot(train_X, sess.run(z5, feed_dict={X: train_X}), label=‘Fitted line‘)
    plt.legend()  
    plotdata["avgloss"] = moving_average(plotdata["loss"])

    plt.subplot(212)
    plt.plot(plotdata["batchsize"], plotdata["avgloss"], ‘b--‘)
    plt.xlabel(‘Minibatch number‘)
    plt.ylabel(‘Loss‘)
    plt.title(‘Minibatch run vs Training loss‘)     
    plt.show()
    #预测结果
    a=[[0.2],[0.3]]
    print ("x=[[0.2],[0.3]]，z5=", sess.run(z5, feed_dict={X: a}))