python神经网络编程实现手写数字识别

本文实例为大家分享了python实现手写数字识别的具体代码，供大家参考，具体内容如下

import numpy
import scipy.special
#import matplotlib.pyplot

class neuralNetwork:
  def __init__(self,inputnodes,hiddennodes,outputnodes,learningrate):
    self.inodes=inputnodes
    self.hnodes=hiddennodes
    self.onodes=outputnodes

    self.lr=learningrate

    self.wih=numpy.random.normal(0.0,pow(self.hnodes,-0.5),(self.hnodes,self.inodes))
    self.who=numpy.random.normal(0.0,pow(self.onodes,-0.5),(self.onodes,self.hnodes))

    self.activation_function=lambda x: scipy.special.expit(x)
    pass

  def train(self,inputs_list,targets_list):
    inputs=numpy.array(inputs_list,ndmin=2).T
    targets=numpy.array(targets_list,ndmin=2).T

    hidden_inputs=numpy.dot(self.wih,inputs)
    hidden_outputs=self.activation_function(hidden_inputs)

    final_inputs=numpy.dot(self.who,hidden_outputs)
    final_outputs=self.activation_function(final_inputs)

    output_errors=targets-final_outputs
    hidden_errors=numpy.dot(self.who.T,output_errors)

    self.who+=self.lr*numpy.dot((output_errors*final_outputs*(1.0-final_outputs)),numpy.transpose(hidden_outputs))
    self.wih+=self.lr*numpy.dot((hidden_errors*hidden_outputs*(1.0-hidden_outputs)),numpy.transpose(inputs))
    pass

  def query(self,input_list):
    inputs=numpy.array(input_list,ndmin=2).T

    hidden_inputs=numpy.dot(self.wih,inputs)
    hidden_outputs=self.activation_function(hidden_inputs)

    final_inputs=numpy.dot(self.who,hidden_outputs)
    final_outputs=self.activation_function(final_inputs)

    return final_outputs

input_nodes=784
hidden_nodes=100
output_nodes=10
learning_rate=0.1
n=neuralNetwork(input_nodes,hidden_nodes,output_nodes,learning_rate)

training_data_file=open(r"C:\Users\lsy\Desktop\nn\mnist_train.csv","r")
training_data_list=training_data_file.readlines()
training_data_file.close()
#print(n.wih)
#print("")
epochs=2
for e in range(epochs):
  for record in training_data_list:
    all_values=record.split(",")
    inputs=(numpy.asfarray(all_values[1:])/255.0*0.99)+0.01
    targets=numpy.zeros(output_nodes)+0.01
    targets[int(all_values[0])]=0.99
    n.train(inputs,targets)

#print(n.wih)
#print(len(training_data_list))
#for i in training_data_list:
#  print(i)

test_data_file=open(r"C:\Users\lsy\Desktop\nn\mnist_test.csv","r")
test_data_list=test_data_file.readlines()
test_data_file.close()

scorecard=[]

for record in test_data_list:
  all_values=record.split(",")
  correct_lable=int(all_values[0])
  inputs=(numpy.asfarray(all_values[1:])/255.0*0.99)+0.01
  outputs=n.query(inputs)
  label=numpy.argmax(outputs)
  if(label==correct_lable):
    scorecard.append(1)
  else:
    scorecard.append(0)

scorecard_array=numpy.asarray(scorecard)
print(scorecard_array)
print("")
print(scorecard_array.sum()/scorecard_array.size)
#all_value=test_data_list[0].split(",")
#input=(numpy.asfarray(all_value[1:])/255.0*0.99)+0.01
#print(all_value[0])

#image_array=numpy.asfarray(all_value[1:]).reshape((28,28))

#matplotlib.pyplot.imshow(image_array,cmap="Greys",interpolation="None")
#matplotlib.pyplot.show()
#nn=n.query((numpy.asfarray(all_value[1:])/255.0*0.99)+0.01)
#for i in nn :
#  print(i)

《python神经网络编程》中代码，仅做记录，以备后用。

image_file_name=r"*.JPG"
img_array=scipy.misc.imread(image_file_name,flatten=True)

img_data=255.0-img_array.reshape(784)
image_data=(img_data/255.0*0.99)+0.01

图片对应像素的读取。因训练集灰度值与实际相反，故用255减取反。

import numpy
import scipy.special
#import matplotlib.pyplot
import scipy.misc
from PIL import Image
class neuralNetwork:
  def __init__(self,inputnodes,hiddennodes,outputnodes,learningrate):
    self.inodes=inputnodes
    self.hnodes=hiddennodes
    self.onodes=outputnodes

    self.lr=learningrate

    self.wih=numpy.random.normal(0.0,pow(self.hnodes,-0.5),(self.hnodes,self.inodes))
    self.who=numpy.random.normal(0.0,pow(self.onodes,-0.5),(self.onodes,self.hnodes))

    self.activation_function=lambda x: scipy.special.expit(x)
    pass

  def train(self,inputs_list,targets_list):
    inputs=numpy.array(inputs_list,ndmin=2).T
    targets=numpy.array(targets_list,ndmin=2).T

    hidden_inputs=numpy.dot(self.wih,inputs)
    hidden_outputs=self.activation_function(hidden_inputs)

    final_inputs=numpy.dot(self.who,hidden_outputs)
    final_outputs=self.activation_function(final_inputs)

    output_errors=targets-final_outputs
    hidden_errors=numpy.dot(self.who.T,output_errors)

    self.who+=self.lr*numpy.dot((output_errors*final_outputs*(1.0-final_outputs)),numpy.transpose(hidden_outputs))
    self.wih+=self.lr*numpy.dot((hidden_errors*hidden_outputs*(1.0-hidden_outputs)),numpy.transpose(inputs))
    pass

  def query(self,input_list):
    inputs=numpy.array(input_list,ndmin=2).T

    hidden_inputs=numpy.dot(self.wih,inputs)
    hidden_outputs=self.activation_function(hidden_inputs)

    final_inputs=numpy.dot(self.who,hidden_outputs)
    final_outputs=self.activation_function(final_inputs)

    return final_outputs

input_nodes=784
hidden_nodes=100
output_nodes=10
learning_rate=0.1
n=neuralNetwork(input_nodes,hidden_nodes,output_nodes,learning_rate)

training_data_file=open(r"C:\Users\lsy\Desktop\nn\mnist_train.csv","r")
training_data_list=training_data_file.readlines()
training_data_file.close()
#print(n.wih)
#print("")

#epochs=2
#for e in range(epochs):
for record in training_data_list:
  all_values=record.split(",")
  inputs=(numpy.asfarray(all_values[1:])/255.0*0.99)+0.01
  targets=numpy.zeros(output_nodes)+0.01
  targets[int(all_values[0])]=0.99
  n.train(inputs,targets)

#image_file_name=r"C:\Users\lsy\Desktop\nn\1000-1.JPG"
'''
img_array=scipy.misc.imread(image_file_name,flatten=True)
img_data=255.0-img_array.reshape(784)
image_data=(img_data/255.0*0.99)+0.01
#inputs=(numpy.asfarray(image_data)/255.0*0.99)+0.01
outputs=n.query(image_data)
label=numpy.argmax(outputs)
print(label)
'''
#print(n.wih)
#print(len(training_data_list))
#for i in training_data_list:
#  print(i)

test_data_file=open(r"C:\Users\lsy\Desktop\nn\mnist_test.csv","r")

test_data_list=test_data_file.readlines()
test_data_file.close()

scorecard=[]

total=[0,0,0,0,0,0,0,0,0,0]
rightsum=[0,0,0,0,0,0,0,0,0,0]

for record in test_data_list:
  all_values=record.split(",")
  correct_lable=int(all_values[0])
  inputs=(numpy.asfarray(all_values[1:])/255.0*0.99)+0.01
  outputs=n.query(inputs)
  label=numpy.argmax(outputs)
  total[correct_lable]+=1
  if(label==correct_lable):
    scorecard.append(1)
    rightsum[correct_lable]+=1
  else:
    scorecard.append(0)

scorecard_array=numpy.asarray(scorecard)
print(scorecard_array)
print("")
print(scorecard_array.sum()/scorecard_array.size)
print("")
print(total)
print(rightsum)
for i in range(10):
  print((rightsum[i]*1.0)/total[i])

#all_value=test_data_list[0].split(",")
#input=(numpy.asfarray(all_value[1:])/255.0*0.99)+0.01
#print(all_value[0])

#image_array=numpy.asfarray(all_value[1:]).reshape((28,28))

#matplotlib.pyplot.imshow(image_array,cmap="Greys",interpolation="None")
#matplotlib.pyplot.show()
#nn=n.query((numpy.asfarray(all_value[1:])/255.0*0.99)+0.01)
#for i in nn :
#  print(i)

尝试统计了对于各个数据测试数量及正确率。

原本想验证书后向后查询中数字‘9'识别模糊是因为训练数量不足或错误率过高而产生，然最终结果并不支持此猜想。

另书中只能针对特定像素的图片进行学习，真正手写的图片并不能满足训练条件，实际用处仍需今后有时间改进。

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持我们。