深度学习框架keras使用—（2）非线性回归

code：

# -*- coding: utf-8 -*-
"""
Created on Sat Jan  5 09:59:55 2019

@author: Administrator
"""

import keras
import numpy as np
import matplotlib.pyplot as plt
#按顺序构成的模型
from keras.models import Sequential
#全连接层
from keras.layers import Dense, Activation
from keras.optimizers import SGD

#
x_data = np.linspace(-0.5, 0.5, 200)
noise = np.random.normal(0, 0.02, x_data.shape)
y_data = np.square(x_data) + noise

#显示随机点
plt.scatter(x_data, y_data)
plt.show()

#构建一个顺序模型
model = Sequential()
#在模型中添加一个全连接层
#model.add(Dense(units=1, input_dim=1))

#1-10-1
model.add(Dense(units=10, input_dim=1,activation='tanh'))
#model.add(Activation('tanh'))
model.add(Dense(units=1,activation='tanh'))
#model.add(Activation('tanh'))

#sgd:随机梯度下降法
#mse:均方误差
#定义优化算法
sgd = SGD(lr=0.3)
model.compile(optimizer=sgd, loss='mse')

#训练3001个批次
for step in range(3001):
    #每次训练一个批次
    cost = model.train_on_batch(x_data, y_data)
    
    #每500个batch打印一次cost值
    if step % 500 == 0:
        print('cost: ', cost)
        
#打印权值和偏置值
W,b = model.layers[0].get_weights()
print('W: ', W, 'b: ', b)
    
#把x_data 输入网络中， 得到预测值y_pred
y_pred  = model.predict(x_data)

#显示随机点
plt.scatter(x_data, y_data)
#显示预测结果
plt.plot(x_data, y_pred, 'r-', lw=3)
plt.show()

结果：

cost:  0.064330176
cost:  0.00430306
cost:  0.0011232587
cost:  0.0005117228
cost:  0.00044209335
cost:  0.00040804088
cost:  0.00041893712
W:  [[ 0.5783164  -0.9410055   1.6641765  -0.7725851   0.05985442  0.20194814
   0.14009696  0.36796477  0.552523   -0.17267904]] b:  [ 0.12648003  0.30630904  0.66315216  0.19575058 -0.11367042  0.22501782
  0.24458379  0.0840651  -0.0173044   0.122155  ]