基于Numpy的神经网络+手写数字识别
基于Numpy的神经网络+手写数字识别
本文代码来自Tariq Rashid所著《Python神经网络编程》
代码分为三个部分,框架如下所示:
# neural network class definition
class neuralNetwork:
# initialise the neural network
def __init__():
pass
# train the neural network
def train():
pass
# query the neural network
def query():
pass
这是一个坚实的框架,可以在这个框架之上,充实神经网络工作的详细细节。
import numpy as np
import scipy.special
import matplotlib.pyplot as plt
#neural network class definition
class neuralNetwork :
#initialise the neural network
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
#learning rate
self.lr = learningrate
#link weight matrices, wih and who
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))
#activation function is the sigmoid function
self.activation_function = lambda x : scipy.special.expit(x)
pass
# train the neural network
def train(self, inputs_list, targets_list):
#convert inputs_list, targets_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 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 layers
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
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
pass
使用以上定义的神经网络类:
#number of input,hidden and output nodes
input_nodes = 784
hidden_nodes = 200
output_nodes = 10
#learning rate is 0.1
learning_rate = 0.1
#create instance of neural network
n = neuralNetwork(input_nodes, hidden_nodes, output_nodes, learning_rate)
#load the minist 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
#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 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
n.train(inputs, targets)
pass
pass
#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])
#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)
#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 matche 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)
以上训练中所用到的数据集:
基于Numpy的神经网络+手写数字识别的更多相关文章
- 基于tensorflow的MNIST手写数字识别(二)--入门篇
http://www.jianshu.com/p/4195577585e6 基于tensorflow的MNIST手写字识别(一)--白话卷积神经网络模型 基于tensorflow的MNIST手写数字识 ...
- 基于TensorFlow的MNIST手写数字识别-初级
一:MNIST数据集 下载地址 MNIST是一个包含很多手写数字图片的数据集,一共4个二进制压缩文件 分别是test set images,test set labels,training se ...
- [Python]基于CNN的MNIST手写数字识别
目录 一.背景介绍 1.1 卷积神经网络 1.2 深度学习框架 1.3 MNIST 数据集 二.方法和原理 2.1 部署网络模型 (1)权重初始化 (2)卷积和池化 (3)搭建卷积层1 (4)搭建卷积 ...
- TensorFlow 卷积神经网络手写数字识别数据集介绍
欢迎大家关注我们的网站和系列教程:http://www.tensorflownews.com/,学习更多的机器学习.深度学习的知识! 手写数字识别 接下来将会以 MNIST 数据集为例,使用卷积层和池 ...
- 深度学习-使用cuda加速卷积神经网络-手写数字识别准确率99.7%
源码和运行结果 cuda:https://github.com/zhxfl/CUDA-CNN C语言版本参考自:http://eric-yuan.me/ 针对著名手写数字识别的库mnist,准确率是9 ...
- 神经网络手写数字识别numpy实现
本文摘自Michael Nielsen的Neural Network and Deep Learning,该书的github网址为:https://github.com/mnielsen/neural ...
- 深度学习(一):Python神经网络——手写数字识别
声明:本文章为阅读书籍<Python神经网络编程>而来,代码与书中略有差异,书籍封面: 源码 若要本地运行,请更改源码中图片与数据集的位置,环境为 Python3.6x. 1 import ...
- 基于多层感知机的手写数字识别(Tensorflow实现)
import numpy as np import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_dat ...
- 基于TensorFlow的MNIST手写数字识别-深入
构建多层卷积神经网络时需要多组W和偏移项b,我们封装2个方法来产生W和b 初级MNIST中用0初始化W和b,这里用噪声初始化进行对称打破,防止产生梯度0,同时用一个小的正值来初始化b避免dead ne ...
随机推荐
- 2017icpc 西安 XOR
XOR Consider an array AAA with n elements . Each of its element is A[i]A[i]A[i] (1≤i≤n)(1 \le i \le ...
- 全文搜索(A-5)-推荐算法
基于内容的推荐算法: 协同过滤推荐算法: 混合推荐算法: 基于内容的推荐算法做了如下假设:用户会喜欢和原来喜欢的物品相类似的项目.
- [K/3Cloud] 关于单据转换的问题
1. 单据转换,是否支持重复下推,支持新增下推和更新下推? 答:支持重复下推,是否允许下推受以下因素: 1).源分录是否是有效状态(源单单头状态会自动影响分录,下同),例如已审核.未关闭.未作废: 2 ...
- http post提交数组
方式一:@RequestParam方式 服务提供方用@RequestParam注解接收参数,参数类型为long数组: @ApiOperation(value = "***", ta ...
- 使用vim正则表达式删除C/C++注释 及 两种注释风格替换
/*对于C风格的注释可以使用如下命令*/ :%s/\_s*\/\*\(\S\|\_s\)\{-}\*\///g //对于C++风格注释 :%s/\/\/.*//g /*...*/ -> //.. ...
- Object-C 打开工程,选择模拟起时,提示"no scheme"
错误提示,如下图: 解决思路:
- 1sting 大数 递推
You will be given a string which only contains ‘1’; You can merge two adjacent ‘1’ to be ‘2’, or lea ...
- HDU 5640 King's Cake【模拟】
题意: 给定长方形,每次从中切去一个最大的正方形,问最终可以得到多少正方形. 分析: 过程类似求gcd,每次减去最小的边即可. 代码: #include <cstdio> #include ...
- sql 按中文排序
sql server:select * from [表名]order by [字段],[字段] collate Chinese_PRC_CS_AS_KS_WS mysql:select * from ...
- Python 出现 can't use a string pattern on a bytes-like object
Python 出现 can't use a string pattern on a bytes-like object 学习了:https://www.cnblogs.com/andrewleeeee ...