通过过一个最简单的神经网络(输入层一个神经元,隐藏层10个神经元,输出层1个神经元)来进行非线性回归。
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
#使用numpy生成200个随机点
#从-0.5到0.5生成均匀分布的200个点(一维)[]增加一个维度
x_data=np.linspace(-0.5,0.5,200)[:,np.newaxis]
#print(x_data)
#正态分布均值为0标准差为0.02
noise = np.random.normal(0,0.02,x_data.shape)
#print(noise)
y_data = np.square(x_data)+noise
#print(y_data)
# 定义两个placeholder
#行不确定1列
x = tf.placeholder(tf.float32,[None,1])
y = tf.placeholder(tf.float32,[None,1])
#定义神经网络中间层10个神经元
Weights_L1=tf.Variable(tf.random_normal([1,10]))
biases_L1=tf.Variable(tf.zeros([1,10]))
Wx_plus_b_L1=tf.matmul(x,Weights_L1)+biases_L1
#激活函数(双曲正弦函数)
L1=tf.nn.tanh(Wx_plus_b_L1)
#定义输出层
Weights_L2 = tf.Variable(tf.random_normal([10,1]))
biases_L2=tf.Variable(tf.zeros([1,1]))
Wx_plus_b_L2 = tf.matmul(L1,Weights_L2)+biases_L2
prediction=tf.nn.tanh(Wx_plus_b_L2)
#二次代价函数
loss = tf.reduce_mean(tf.square(y-prediction))
#梯度下降法
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)
with tf.Session() as sess:
#变量初始化
sess.run(tf.global_variables_initializer())
for _ in range(2000):
sess.run(train_step,feed_dict={x:x_data,y:y_data})
#获得预测值
prediction_value=sess.run(prediction, feed_dict={x:x_data})
#画图
plt.figure()
plt.scatter(x_data,y_data)
plt.plot(x_data,prediction_value,'r-',lw=5)
plt.show()
结果