import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
#使用numpy生成200个随机点
x_data=np.linspace(-0.5,0.5,200)[:,np.newaxis]
noise=np.random.normal(0,0.02,x_data.shape)
y_data=np.square(x_data)+noise
#定义两个placeholder(占位符)
x=tf.placeholder(tf.float32,[None,1])
y=tf.placeholder(tf.float32,[None,1])
#定义神经网络中间层
Weights_L1=tf.Variable(tf.random_normal([1,10]))#创建一个权值weights_L1,创建一个随机数,它的形状是一行十列(1代表1个输入(1个输入层),10个中间层)
blases_L1=tf.Variable(tf.zeros([1,10]))
Wx_plus_b_L1=tf.matmul(x,Weights_L1)+blases_L1#tf.matmul为矩阵的乘法,得到信号的总和Wx_plus_b_L1
L1=tf.nn.tanh(Wx_plus_b_L1)#激活函数作用于信号的总和Wx_plus_b_L1
#定义输出层(输出层的输入相当于中间层的输出)
Weights_L2=tf.Variable(tf.random_normal([10,1]))#10个中间层,1个输出
blases_L2=tf.Variable(tf.zeros([1,1]))
Wx_plus_b_L2=tf.m