基础模型

1. 回归

#!/usr/bin/python2.7
# -*- coding: UTF-8 -*-



import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

#使用np生成200个随机点
x_data=np.linspace(-0.5,0.5,200)[:,np.newaxis]  # 200*1的矩阵
#生成干扰项
noise=np.random.normal(0,0.02,x_data.shape)  # 和x_data的形状一样
y_data=np.square(x_data)+noise

# 定义两个placeholder
x=tf.placeholder(tf.float32,[None,1])
y=tf.placeholder(tf.float32,[None,1])

#  构建神经网络：输入，x,一个神经元;中间层，10个神经元；输出,一个神经元，y;

# 神经网络中间层
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
L1=tf.nn.tanh(Wx_plus_b_L1)


# 定义输出层

Weights_L2=tf.Variable(tf.random_normal([10,1]))  # 10*1的矩阵
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) # 预测结果

# 输入层不用定义

#二次函数

loss=tf.reduce_mean(tf.square(y-prediction))
train_step=tf.train.GradientDescentOptimizer(0.1).minimize(loss)


with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for _ in range(2000):
        sess.run(train_step,feed_dict={x:x_data,y:y_data})

    # 预测结果(上面模型已经训练完毕)
    prediction_value=sess.run(prediction,feed_dict={x:x_data})
    # 打印结果
    plt.figure()
    plt.scatter(x_data,y_data)
    plt.plot(x_data,prediction_value,'r-',lw=5)
    plt.show()