# -*- coding: utf-8 -*- """ Created on Fri Apr 17 20:13:37 2020 @author: ASUS """ # load the file import numpy as np import scipy.special class neuralNetwork: def __init__(self,inputnodes,hiddennodes,outputnodes,learningrate): self.inodes=inputnodes self.hnodes=hiddennodes self.onodes=outputnodes self.lr=learningrate #link weight self.wih=np.random.normal(0.0,pow(self.hnodes,-0.5),(self.hnodes,self.inodes)) self.who=np.random.normal(0.0,pow(self.hnodes,-0.5),(self.onodes,self.hnodes)) #activation function self.activation_function=lambda x: scipy.special.expit(x) pass def train(self,input_list,target_list): # convert inputs list to 2d array inputs=np.array(input_list,ndmin=2).T targets=np.array(target_list,ndmin=2).T #calculate signals into hidden layer hidden_inputs=np.dot(self.wih,inputs) hidden_output=self.activation_function(hidden_inputs) #calculate signals into final layer final_inputs=np.dot(self.who,hidden_output) final_outputs=self.activation_function(final_inputs) # the error output_errors=targets-final_outputs #hidden layer error is the output_errors,split by weights recombined at hidden nodes hidden_errors=np.dot(self.who.T,output_errors) # update the weights for the links between the hidden and output layers self.who+=self.lr*np.dot((output_errors*final_outputs*(1.0-final_outputs)),np.transpose(hidden_output)) self.wih+=self.lr*np.dot((hidden_errors*hidden_output*(1.0-hidden_output)),np.transpose(inputs)) pass def query(self,input_list): #convert inputs list to 2d array inputs=np.array(input_list,ndmin=2).T #calculate signals into hidden layer hidden_inputs=np.dot(self.wih,inputs) hidden_output=self.activation_function(hidden_inputs) #calculate signals into out layer final_inputs=np.dot(self.who,hidden_output) final_outputs=self.activation_function(final_inputs) return final_outputs input_nodes=17 hidden_nodes=100 output_nodes=2 learning_rate=0.3 # create instance of neural network n=neuralNetwork(input_nodes,hidden_nodes,output_nodes,learning_rate) # load the mnist training data csv file into list training_data_file=open('C:\\Users\\ASUS\\test.csv','r') training_data_list=training_data_file.readlines() training_data_file.close() # train the nerual network # go through all records in the training data set for record in training_data_list: #split the record by the ',' commas all_values=record.split(',') all_values = list(map(int, all_values))#需要对导入数据转换数值类型 #scale and shift the inputs inputs=(np.asfarray(all_values[1:])/15*0.99)+0.01 #creat the target output values targets=all_values[0] n.train(inputs,targets) pass
这是一个单个隐藏层的神经元网络
训练文件的格式为18位数组，首位表示输赢，后17位表示手牌状态