基于《Python神经网络编程》分析三层BP神经网络与四层BP神经网络

系统 1290 0
  1. 三层神经网络
    1. 节点数:784*100*10
    2. 学习率: 0.1
    3. 预测结果得分(五次)
      1.  0.9512
      2.  0.9497
      3.  0.9506
      4.  0.9505
      5.  0.9464
    4. 平均预测得分:0.94968
  2. 四层神经网络
    1. 节点数:784*100*100*10
    2. 学习率 :0.1
    3. 预测结果得分(五次)
      1.  0.9095
      2.  0.9142
      3.  0.9033
      4.  0.9130
      5.  0.9046
    4. 平均预测得分:0.90892
  3. 结论:针对这种情况,简单的神经网络对MNIST数据集的分析,增加神经网络层数未能提高学习效果。
  4. 代码(参考 Tariq Rashid的《Python 神经网络编程》)
    1. 三层神经网络 
                          
                            # python notebook for Make Your Own Neural Network
      # code for 3-layer neural network, and code for learning the MNIST dataset
      # 20190603
      
      import numpy as np
      import matplotlib.pyplot as plt
      # scipy.special for the sigmoid function expit()
      import scipy.special as special
      # ensure the plots are inside this notebook, not an external window
      %matplotlib inline
      
      # neural network class definition
      class neuralNetwork(object):
          
          # initialise the neural network
          def __init__(self, inputNodes, hiddenNodes, outputNodes, learningRate=0.5):
              # set number of nodes in each input, hidden, output layer
              self.iNodes = inputNodes
              self.hNodes = hiddenNodes
              self.oNodes = outputNodes
              # link weight matrices, wih and who
              # weights inside the arrays are w_i_j, where link is from node i to node j in 
              # the next layer
              # w11 w21
              # w12 w22 etc
              # pow(x, y), 返回x的y次方
              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.oNodes, -0.5), (self.oNodes, self.hNodes))
              # learning rate
              self.lr = learningRate
              # activation function is the sigmoid function
              # lambda x: special.expit(x)  表示接受x,返回special.expit(x)函数
              self.activation_function = lambda x: special.expit(x)
              pass
          
          # train the neural network
          def train(self, inputs_list, targets_list):
              # convert inputs list to 2d array
              inputs = np.array(inputs_list, ndmin=2).T
              targets = np.array(targets_list, ndmin=2).T
              
              # calculate signals into hidden layer
              hidden_inputs = np.dot(self.wih, inputs)
              # calculate the signals emerging from hidden layer
              hidden_outputs = self.activation_function(hidden_inputs)
              
              # calculate signals into final output layer
              final_inputs = np.dot(self.who, hidden_outputs)
              # calculate signals emerging from final output layer
              final_outputs = self.activation_function(final_inputs)
              
              # error is the (targets - final_outputs)
              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
              # np.transpose(a)  表示矩阵a的转秩
              self.who += self.lr * np.dot(output_errors * final_outputs * 
                                           (1.0 - final_outputs), np.transpose(hidden_outputs))
              
              # update the weights for the links between the input and hidden layers
              self.wih += self.lr * np.dot(hidden_errors * hidden_outputs *
                                          (1.0 - hidden_outputs), np.transpose(inputs))
              
              pass
          
          # query the neural network
          def query(self, inputs_list):
              # convert inputs list to 2d array
              # ndmin=2 表示指定最小维数为2
              # .T 表示矩阵的转秩
              inputs = np.array(inputs_list, ndmin=2).T
              
              # calculate signals into hidden layer
              hidden_inputs = np.dot(self.wih, inputs)
              # calculate the signals emerging from hidden layer
              hidden_outputs = self.activation_function(hidden_inputs)
              
              # calculate signals into final output layer
              final_inputs = np.dot(self.who, hidden_outputs)
              # calculate the signals emerging from final output layer
              final_outputs = self.activation_function(final_inputs)
              
              return final_outputs
          
      
      # number of input, hidden and output nodes
      input_nodes = 784
      hidden_nodes = 100
      output_nodes = 10
      
      # learning rate is 0.3
      learning_rate = 0.1
      
      # creat instance of neural network
      n = neuralNetwork(input_nodes, hidden_nodes, output_nodes, learning_rate)
      
      
      # load the mnist training data CSV file into a list
      training_data_file = open("mnist_dataset/mnist_train.csv", 'r')
      training_data_list = training_data_file.readlines()
      training_data_file.close()
      
      # train the neural network
      # go through all recordes in the training data set
      final_training_data = []
      for record in training_data_list:
          # split the record by the ',' commas
          all_values = record.split(',')
          # scale and shift the inputs
          inputs = (np.asfarray(all_values[1:]) / 255.0 * 0.99) + 0.01
          # create the target output values (all 0.01, except the desired label which is 0.99)
          targets = np.zeros(output_nodes) + 0.01
          # all_values[0] is the target label for this record
          targets[int(all_values[0])] = 0.99
          # train Model
          final_training_data.append([inputs, targets])
          pass
      
      
      # train Model
      for i in range(len(final_training_data)):
          n.train(final_training_data[i][0], final_training_data[i][1])
      
      
      # load the minist test data CSV file into  a list
      test_data_file = open("mnist_dataset/mnist_test.csv", 'r')
      test_data_list = test_data_file.readlines()
      test_data_file.close()
      
      
      # test the neural network
      # scorecard for how well the network performs, initially empty 
      scorecard = []
      
      # go through all the records in the test data set
      for record in test_data_list:
          # split the record by the ',' commas
          all_values = record.split(',')
          # correct answer is the first value
          correct_label = int(all_values[0])
      #     print("Correct label : ", correct_label)
          # scale and shift the inputs
          inputs = (np.asfarray(all_values[1:]) / 255.0 * 0.99) + 0.01
          # query the network
          outputs = n.query(inputs)
          # the index of the highest value corresponds to the label
          label = np.argmax(outputs)
      #     print("NeuralNetwork's answer : ", label)
      
          # append correct or incorrect to list
          if(label == correct_label):
              # network's answer matches correct answer, add 1 to scorecard
              scorecard.append(1)
          else:
              #network's answer doesn't match correct answer, add 0 to scorecard
              scorecard.append(0)
              
              pass
          pass
      
      
      
      # calculate the performance score, the fraction of correct answers
      scorecard_array = np.asarray(scorecard)
      print("Performance : ", scorecard_array.sum() / scorecard_array.size)
                          
                        

       

    2. 四层神经网络
                          
                            # python notebook for Make Your Own Neural Network
      # code for 4-layer neural network, and code for learning the MNIST dataset
      # 20190604
      
      
      import numpy as np
      import matplotlib.pyplot as plt
      # scipy.special for the sigmoid function expit()
      import scipy.special as special
      # ensure the plots are inside this notebook, not an external window
      %matplotlib inline
      
      
      # neural network class definition
      class neuralNetwork(object):
          
          # initialise the neural network
          def __init__(self, inputNodes, hiddenNodes, hiddenNodes_2, outputNodes, learningRate=0.5):
              # set number of nodes in each input, hidden, output layer
              self.iNodes = inputNodes
              self.hNodes = hiddenNodes
              self.hNodes_2 = hiddenNodes_2
              self.oNodes = outputNodes
              # link weight matrices, wih and who
              # weights inside the arrays are w_i_j, where link is from node i to node j in 
              # the next layer
              # w11 w21
              # w12 w22 etc
              # pow(x, y), 返回x的y次方
              self.wih = np.random.normal(0.0, pow(self.hNodes, -0.5), (self.hNodes, self.iNodes))
              self.whh = np.random.normal(0.0, pow(int((self.hNodes + self.hNodes_2) / 2) , -0.5), (self.hNodes_2, self.hNodes))
              self.who = np.random.normal(0.0, pow(self.oNodes, -0.5), (self.oNodes, self.hNodes_2))
              # learning rate
              self.lr = learningRate
              # activation function is the sigmoid function
              # lambda x: special.expit(x)  表示接受x,返回special.expit(x)函数
              self.activation_function = lambda x: special.expit(x)
              pass
          
          # train the neural network
          def train(self, inputs_list, targets_list):
              # convert inputs list to 2d array
              inputs = np.array(inputs_list, ndmin=2).T
              targets = np.array(targets_list, ndmin=2).T
              
              # calculate signals into hidden layer
              hidden_inputs = np.dot(self.wih, inputs)
              # calculate the signals emerging from hidden layer
              hidden_outputs = self.activation_function(hidden_inputs)
              
              # calculate signals into hidden_2 layer
              hidden_2_inputs = np.dot(self.whh, hidden_outputs)
              # calculate the signals emerging from hedden_2 layer
              hidden_2_outputs = self.activation_function(hidden_2_inputs)
              
              # calculate signals into final output layer
              final_inputs = np.dot(self.who, hidden_2_outputs)
              # calculate signals emerging from final output layer
              final_outputs = self.activation_function(final_inputs)
              
              # error is the (targets - final_outputs)
              output_errors = (targets - final_outputs)
              
              
              # hidden layer error is the output_errors, split by weights, recombined at 
              # hidden nodes
              hidden_2_errors = np.dot(self.who.T, output_errors)
              
              # hidden_2 layer error is
              hidden_errors = np.dot(self.whh.T, hidden_2_errors)
              
              # update the weights for the links between the hidden and output layers
              # np.transpose(a)  表示矩阵a的转秩
              self.who += self.lr * np.dot(output_errors * final_outputs * 
                                           (1.0 - final_outputs), np.transpose(hidden_2_outputs))
              
              
              # update the weights for the links between the hideen and hidden_2 layers
              self.whh += self.lr * np.dot(hidden_2_errors * hidden_2_outputs *
                                          (1.0 - hidden_2_outputs), np.transpose(hidden_outputs))
              
              # update the weights for the links between the input and hidden layers
              self.wih += self.lr * np.dot(hidden_errors * hidden_outputs *
                                          (1.0 - hidden_outputs), np.transpose(inputs))
              
              
              
              pass
          
          # query the neural network
          def query(self, inputs_list):
              # convert inputs list to 2d array
              # ndmin=2 表示指定最小维数为2
              # .T 表示矩阵的转秩
              inputs = np.array(inputs_list, ndmin=2).T
              
              # calculate signals into hidden layer
              hidden_inputs = np.dot(self.wih, inputs)
              # calculate the signals emerging from hidden layer
              hidden_outputs = self.activation_function(hidden_inputs)
              
              # calculate signals into hidden_2 layer
              hidden_2_inputs = np.dot(self.whh, hidden_outputs)
              # calculate the signals emerging from hidden_2 layer
              hidden_2_outputs = self.activation_function(hidden_2_inputs)
              
              # calculate signals into final output layer
              final_inputs = np.dot(self.who, hidden_2_outputs)
              # calculate the signals emerging from final output layer
              final_outputs = self.activation_function(final_inputs)
              
              return final_outputs
          
      
      
      # number of input, hidden and output nodes
      input_nodes = 784
      hidden_nodes = 100
      hidden_2_nodes = 100
      output_nodes = 10
      
      # learning rate is 0.3
      learning_rate = 0.1
      
      # creat instance of neural network
      n = neuralNetwork(input_nodes, hidden_nodes, hidden_2_nodes, output_nodes, learning_rate)
      
      
      # load the mnist training data CSV file into a list
      training_data_file = open("mnist_dataset/mnist_train.csv", 'r')
      training_data_list = training_data_file.readlines()
      training_data_file.close()
      
      
      # train the neural network
      # go through all recordes in the training data set
      final_training_data = []
      for record in training_data_list:
          # split the record by the ',' commas
          all_values = record.split(',')
          # scale and shift the inputs
          inputs = (np.asfarray(all_values[1:]) / 255.0 * 0.99) + 0.01
          # create the target output values (all 0.01, except the desired label which is 0.99)
          targets = np.zeros(output_nodes) + 0.01
          # all_values[0] is the target label for this record
          targets[int(all_values[0])] = 0.99
          # train Model
          final_training_data.append([inputs, targets])
          pass
      
      
      # load the mnist training data CSV file into a list
      training_data_file = open("mnist_dataset/mnist_train.csv", 'r')
      training_data_list = training_data_file.readlines()
      training_data_file.close()
      
      
      
      # train the neural network
      # go through all recordes in the training data set
      final_training_data = []
      for record in training_data_list:
          # split the record by the ',' commas
          all_values = record.split(',')
          # scale and shift the inputs
          inputs = (np.asfarray(all_values[1:]) / 255.0 * 0.99) + 0.01
          # create the target output values (all 0.01, except the desired label which is 0.99)
          targets = np.zeros(output_nodes) + 0.01
          # all_values[0] is the target label for this record
          targets[int(all_values[0])] = 0.99
          # train Model
          final_training_data.append([inputs, targets])
          pass
      
      
      
      # train Model
      for i in range(len(final_training_data)):
          n.train(final_training_data[i][0], final_training_data[i][1])
      
      
      
      # load the minist test data CSV file into  a list
      test_data_file = open("mnist_dataset/mnist_test.csv", 'r')
      test_data_list = test_data_file.readlines()
      test_data_file.close()
      
      
      # test the neural network
      # scorecard for how well the network performs, initially empty 
      scorecard = []
      
      # go through all the records in the test data set
      for record in test_data_list:
          # split the record by the ',' commas
          all_values = record.split(',')
          # correct answer is the first value
          correct_label = int(all_values[0])
      #     print("Correct label : ", correct_label)
          # scale and shift the inputs
          inputs = (np.asfarray(all_values[1:]) / 255.0 * 0.99) + 0.01
          # query the network
          outputs = n.query(inputs)
          # the index of the highest value corresponds to the label
          label = np.argmax(outputs)
      #     print("NeuralNetwork's answer : ", label)
      
          # append correct or incorrect to list
          if(label == correct_label):
              # network's answer matches correct answer, add 1 to scorecard
              scorecard.append(1)
          else:
              #network's answer doesn't match correct answer, add 0 to scorecard
              scorecard.append(0)
              
              pass
          pass
      
      
      
      # calculate the performance score, the fraction of correct answers
      scorecard_array = np.asarray(scorecard)
      print("Performance : ", scorecard_array.sum() / scorecard_array.size)
                          
                        

       

 


更多文章、技术交流、商务合作、联系博主

微信扫码或搜索:z360901061

微信扫一扫加我为好友

QQ号联系: 360901061

您的支持是博主写作最大的动力,如果您喜欢我的文章,感觉我的文章对您有帮助,请用微信扫描下面二维码支持博主2元、5元、10元、20元等您想捐的金额吧,狠狠点击下面给点支持吧,站长非常感激您!手机微信长按不能支付解决办法:请将微信支付二维码保存到相册,切换到微信,然后点击微信右上角扫一扫功能,选择支付二维码完成支付。

【本文对您有帮助就好】

您的支持是博主写作最大的动力,如果您喜欢我的文章,感觉我的文章对您有帮助,请用微信扫描上面二维码支持博主2元、5元、10元、自定义金额等您想捐的金额吧,站长会非常 感谢您的哦!!!

发表我的评论
最新评论 总共0条评论