1. Johngo学长首页
  2. 技术点详细复盘专题
  3. Python

CV学习笔记-BP神经网络代码Python实例

• Python • 阅读 53

CV学习笔记-BP神经网络代码Python实例

一. 任务描述

给定数据集（txt文件），采用随机梯度下降的方式进行神经网络的学习，完成权重参数的更新，使得输入的数据能够接近输出label。

关于BP神经网络的手推和原理见笔者《CV学习笔记-推理和训练》、《CV学习笔记-BP神经网络》

txt文件类似下图所示

CV学习笔记-BP神经网络代码Python实例

col1col2col3输入1输入2label

; 二. 程序设计

1. 神经网络设计

类： NeuralNetWork
类内初始化： __init__用以设置神经网络的参数（输入层参数、隐藏层参数、输出层参数、学习率）
类内方法： train用于训练数据，更新权重
读取数据： loadDataSet用于在txt文件中读取数据，包括输入值和label值
随机梯度下降处理： stocGradDescent用于处理训练数据的过程

2. 具体设计

  • NeuralNetWork类
class NeuralNetWork:
    def __init__(self, input_nodes, hidden_nodes, out_nodes, lr):

        self.innodes = input_nodes

        self.hnodes = hidden_nodes

        self.onodes = out_nodes

        self.lr = lr

        self.weight_i2h = (numpy.random.normal(0.0, pow(self.hnodes,-0.5), (self.hnodes,self.innodes) )  )

        self.weight_h2o = (numpy.random.normal(0.0, pow(self.onodes,-0.5), (self.onodes,self.hnodes) )  )

        self.activation_function = lambda x: 1.0/(1+np.exp(-x))
        pass

    '''
    训练方法，输入一次训练的输入和label
    '''
    def train(self, inputs_list, targets_list):
        inputs = numpy.array(inputs_list, ndmin=2).T
        target = np.array(targets_list, ndmin=2).T

        hidden_inputs = np.dot(self.weight_i2h, inputs)

        hidden_outputs = self.activation_function(hidden_inputs)

        o_inputs = np.dot(self.weight_h2o, hidden_outputs)

        o_outputs = self.activation_function(o_inputs)

        loss = (target - o_outputs) ** 2 * 0.5

        error = target - o_outputs

        hidden_error = np.dot(self.weight_h2o.T, error * o_outputs * (1 - o_outputs))

        gradO = error * o_outputs * (1 - o_outputs)

        self.weight_h2o += self.lr * np.dot((error * o_outputs * (1 - o_outputs)), np.transpose(hidden_outputs))
        gradI = hidden_error * hidden_outputs * (1 - hidden_outputs)

        self.weight_i2h += self.lr * np.dot((hidden_error * hidden_outputs * (1 - hidden_outputs)),
                                            np.transpose(inputs))
        return loss
  • 读取数据集并处理
def loadDataSet():
    data = []
    label = []
    fr = open('testSet.txt')
    for line in fr.readlines():
        lineArr = line.strip().split()
        data.append([1.0, float(lineArr[0]), float(lineArr[1])])
        label.append(int(lineArr[2]))
    data = np.array(data)
    label = np.array(label)
    return data, label
  • 训练过程处理
def stocGradDescent(data, label):
    m, n = np.shape(data)
    for iter in range(200):
        total_loss = 0
        for i in range(m):

            total_loss += net.train(data[i], label[i])
        print("NO.{} Loss={}".format(iter, total_loss))

三、实践代码

import numpy
import numpy as np

class NeuralNetWork:
    def __init__(self, input_nodes, hidden_nodes, out_nodes, lr):
        self.innodes = input_nodes
        self.hnodes = hidden_nodes
        self.onodes = out_nodes
        self.lr = lr

        self.weight_i2h = (numpy.random.normal(0.0, pow(self.hnodes,-0.5), (self.hnodes,self.innodes) )  )
        self.weight_h2o = (numpy.random.normal(0.0, pow(self.onodes,-0.5), (self.onodes,self.hnodes) )  )
        self.activation_function = lambda x: 1.0/(1+np.exp(-x))
        pass

    def train(self, inputs_list, targets_list):
        inputs = numpy.array(inputs_list, ndmin=2).T
        target = np.array(targets_list, ndmin=2).T
        hidden_inputs = np.dot(self.weight_i2h, inputs)
        hidden_outputs = self.activation_function(hidden_inputs)
        o_inputs = np.dot(self.weight_h2o, hidden_outputs)
        o_outputs = self.activation_function(o_inputs)
        loss = (target - o_outputs) ** 2 * 0.5
        error = target - o_outputs

        hidden_error = np.dot(self.weight_h2o.T, error * o_outputs * (1 - o_outputs))
        gradO = error * o_outputs * (1 - o_outputs)
        self.weight_h2o += self.lr * np.dot((error * o_outputs * (1 - o_outputs)), np.transpose(hidden_outputs))
        gradI = hidden_error * hidden_outputs * (1 - hidden_outputs)
        self.weight_i2h += self.lr * np.dot((hidden_error * hidden_outputs * (1 - hidden_outputs)),
                                            np.transpose(inputs))
        return loss

def loadDataSet():
    data = []
    label = []
    fr = open('testSet.txt')
    for line in fr.readlines():
        lineArr = line.strip().split()
        data.append([1.0, float(lineArr[0]), float(lineArr[1])])
        label.append(int(lineArr[2]))
    data = np.array(data)
    label = np.array(label)
    return data, label

def stocGradDescent(data, label):
    m, n = np.shape(data)
    for iter in range(200):
        total_loss = 0
        for i in range(m):

            total_loss += net.train(data[i], label[i])
        print("NO.{} Loss={}".format(iter, total_loss))

if __name__ == '__main__':
    input_nodes = 3
    hidden_nodes = 3
    output_nodes = 1
    learning_rate = 0.1
    net = NeuralNetWork(input_nodes, hidden_nodes, output_nodes, learning_rate)
    data, label = loadDataSet()
    stocGradDescent(data, label)
    print(net.weight_i2h)
    print(net.weight_h2o)
    pass

txt文本文件内容请自行复制

-0.017612   14.053064   0
-1.395634   4.662541    1
-0.752157   6.538620    0
-1.322371   7.152853    0
0.423363    11.054677   0
0.406704    7.067335    1
0.667394    12.741452   0
-2.460150   6.866805    1
0.569411    9.548755    0
-0.026632   10.427743   0
0.850433    6.920334    1
1.347183    13.175500   0
1.176813    3.167020    1
-1.781871   9.097953    0
-0.566606   5.749003    1
0.931635    1.589505    1
-0.024205   6.151823    1
-0.036453   2.690988    1
-0.196949   0.444165    1
1.014459    5.754399    1
1.985298    3.230619    1
-1.693453   -0.557540   1
-0.576525   11.778922   0
-0.346811   -1.678730   1
-2.124484   2.672471    1
1.217916    9.597015    0
-0.733928   9.098687    0
-3.642001   -1.618087   1
0.315985    3.523953    1
1.416614    9.619232    0
-0.386323   3.989286    1
0.556921    8.294984    1
1.224863    11.587360   0
-1.347803   -2.406051   1
1.196604    4.951851    1
0.275221    9.543647    0
0.470575    9.332488    0
-1.889567   9.542662    0
-1.527893   12.150579   0
-1.185247   11.309318   0
-0.445678   3.297303    1
1.042222    6.105155    1
-0.618787   10.320986   0
1.152083    0.548467    1
0.828534    2.676045    1
-1.237728   10.549033   0
-0.683565   -2.166125   1
0.229456    5.921938    1
-0.959885   11.555336   0
0.492911    10.993324   0
0.184992    8.721488    0
-0.355715   10.325976   0
-0.397822   8.058397    0
0.824839    13.730343   0
1.507278    5.027866    1
0.099671    6.835839    1
-0.344008   10.717485   0
1.785928    7.718645    1
-0.918801   11.560217   0
-0.364009   4.747300    1
-0.841722   4.119083    1
0.490426    1.960539    1
-0.007194   9.075792    0
0.356107    12.447863   0
0.342578    12.281162   0
-0.810823   -1.466018   1
2.530777    6.476801    1
1.296683    11.607559   0
0.475487    12.040035   0
-0.783277   11.009725   0
0.074798    11.023650   0
-1.337472   0.468339    1
-0.102781   13.763651   0
-0.147324   2.874846    1
0.518389    9.887035    0
1.015399    7.571882    0
-1.658086   -0.027255   1
1.319944    2.171228    1
2.056216    5.019981    1
-0.851633   4.375691    1
-1.510047   6.061992    0
-1.076637   -3.181888   1
1.821096    10.283990   0
3.010150    8.401766    1
-1.099458   1.688274    1
-0.834872   -1.733869   1
-0.846637   3.849075    1
1.400102    12.628781   0
1.752842    5.468166    1
0.078557    0.059736    1
0.089392    -0.715300   1
1.825662    12.693808   0
0.197445    9.744638    0
0.126117    0.922311    1
-0.679797   1.220530    1
0.677983    2.556666    1
0.761349    10.693862   0
-2.168791   0.143632    1
1.388610    9.341997    0
0.317029    14.739025   0

四、 效果测试

CV学习笔记-BP神经网络代码Python实例
通过debug看效果：

可见刚开始网络的输出跟label的差距还是很大

CV学习笔记-BP神经网络代码Python实例

可以看到训练到一百多代的时候loss已经有了明显的下降

CV学习笔记-BP神经网络代码Python实例

此时debug看效果，可以看到效果明显改善，网络的输出已经比较小接近于真实label：0了

CV学习笔记-BP神经网络代码Python实例

label为1的效果也靠谱很多了

CV学习笔记-BP神经网络代码Python实例

最后打印出权重参数：

CV学习笔记-BP神经网络代码Python实例

Original: https://blog.csdn.net/qq_38853759/article/details/126039931
Author: Moresweet猫甜
Title: CV学习笔记-BP神经网络代码Python实例

原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/758833/

转载文章受原作者版权保护。转载请注明原作者出处！

赞 (0)
0

【自取】最近整理的，有需要可以领取学习：



Linux核心资料大放送~

全栈面试题汇总（持续更新&可下载）

一个提高学习100%效率的工具！

【超详细】深度学习面试题目！

LeetCode Python刷题答案下载！

LeetCode Java版刷题答案下载！

LeetCode C++ 版本，抓紧保存！

LeetCode GO语言 刷题答案下载！

大家都在看

亲爱的 Coder【最近整理，可免费获取】👉 最新必读书单  | 👏 面试题下载  | 🌎 免费的AI知识星球