Python神经网络实现手写数字识别
程序员文章站
2022-05-21 23:52:43
...
利用Python制作简易的神经网络
* 实现手写数字的识别
* github项目地址:https://github.com/coding-cheng/mnist
* 完整的数据集:
训练集 :http://www.pjreddie.com/midea/files/mnist_train.csv
测试集 :http://www.pjreddie.com/midea/files/mnist_test.csv
* 参考书籍 : 《Python神经网络编程》
* github项目分为以下几个部分:
1. neural_network.py : 神经网络
2. train.py : 训练模型,并保存模型
3. test.py : 测试模型,并且保存模型的准确率
4. useyournum.py : 可使用自己写的数字作为测试对象
5. mnist_dataset : 部分训练测试数据
6. save_model : 保存训练后的模型数据
7. yournum : 用于保存你所写的数字
8. accuracy : 保存测试准确率
数据集网盘下载地址:
链接:https://pan.baidu.com/s/1d_JpNKqIoK86a7pcGoB_Hw
提取码:qbn9
- 项目结构
- 简易神经网络的搭建
import numpy as np
import scipy.special
class neuralNetwork():
# initialise the neuralNetwork
def __init__(self, inputnodes, hiddennodes, outputnodes, learningrate):
# 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
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
self.activation_function = lambda x: scipy.special.expit(x)
# train the neuralNetwork
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 from 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)
# output layer error is the (target - actual)
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 layer
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 layer
self.wih += self.lr * np.dot((hidden_errors * hidden_outputs * (1.0 - hidden_outputs)), np.transpose(inputs))
# query the neural network
def query(self, inputs_list):
# convert inputs list to 2d array
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
fianl_outputs = self.activation_function(final_inputs)
return fianl_outputs
- 训练模块
from neural_network import neuralNetwork
import numpy as np
# number of input, hidden and output nodes
input_nodes = 784 # 28*28
hidden_nodes = 500
output_nodes = 10
# learning rate is 0.3
learning_rate = 0.1
# create instance of neural network
n = neuralNetwork(input_nodes, hidden_nodes, output_nodes, learning_rate)
training_data_file = open("mnist_dataset/mnist_train_100.csv", "r")
training_data_list = training_data_file.readlines()
training_data_file.close()
# train the neural network
# epochs is the number of times the training data set is used for training
epochs = 5
for e in range(epochs):
# go through all records in the training data set
for record in training_data_list:
# split the record by ',' 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, expert 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
n.train(inputs, targets)
save_wih_file = "save_model/wih.npy"
np.save(save_wih_file, n.wih)
save_who_file = "save_model/who.npy"
np.save(save_who_file, n.who)
- 测试模块
from neural_network import neuralNetwork
import numpy as np
# number of input, hidden and output nodes
input_nodes = 784 # 28*28
hidden_nodes = 100
output_nodes = 10
# learning rate is 0.3
learning_rate = 0.3
# create instance of neural network
n = neuralNetwork(input_nodes, hidden_nodes, output_nodes, learning_rate)
save_wih_file = "save_model/wih.npy"
save_who_file = "save_model/who.npy"
n.wih = np.load(save_wih_file)
n.who = np.load(save_who_file)
# load the mnist test data csv file into a list
test_data_file = open("mnist_dataset/mnist_test_10.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 records in the test data set
for record in test_data_list:
# split the record by ',' commas
all_values = record.split(',')
# correct answer is 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(label, "network's answer")
# 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 1 to scorecard
scorecard.append(0)
# calculate the performance score, the fraction of correct answers
scorecard_array = np.asarray(scorecard)
performance = scorecard_array.sum() / scorecard_array.size
print("performance = ", performance)
save_accuracy = "accuracy.txt"
with open(save_accuracy, 'a') as f:
f.write("Learning rate is : " + str(n.lr))
f.write(" Accuracy is : " + str(performance) + '\n')
- 使用你自己的手写数字
from PIL import Image
import numpy as np
from neural_network import neuralNetwork
import matplotlib.pyplot as plt
import imageio
# number of input, hidden and output nodes
input_nodes = 784 # 28*28
hidden_nodes = 100
output_nodes = 10
# learning rate is 0.3
learning_rate = 0.1
# create instance of neural network
n = neuralNetwork(input_nodes, hidden_nodes, output_nodes, learning_rate)
# change pixel value
file_in = 'yournum/yournum.png'
width = 28
height = 28
file_out = 'yournum/yournum_c.png'
image = Image.open(file_in)
resized_image = image.resize((width, height), Image.ANTIALIAS)
resized_image.save(file_out)
save_wih_file = "save_model/wih.npy"
save_who_file = "save_model/who.npy"
n.wih = np.load(save_wih_file)
n.who = np.load(save_who_file)
# test the neural network
image_file_name = "yournum/yournum_c.png"
img_array = imageio.imread(image_file_name, as_gray=True)
img_data = 255.0 - img_array.reshape(784)
img_data = (img_data / 255.0 * 0.99) + 0.01
# query the network
outputs = n.query(img_data)
for i in range(10):
print(i, " ", outputs[i])
result = np.argmax(outputs)
print("Neural network predicts ", result)
image_array = np.asfarray(img_data).reshape((28, 28))
plt.imshow(image_array, cmap='Greys', interpolation='None')
plt.show()