C++读取MNIST数据集

MNIST是一个标准的手写字符测试集。

Mnist数据集对应四个文件:

train-images-idx3-ubyte: training set images 
train-labels-idx1-ubyte: training set labels 
t10k-images-idx3-ubyte:  test set images 
t10k-labels-idx1-ubyte:  test set labels

训练数据集包含60000幅图片,测试集包含10000幅图片。


文件格式:

TRAINING SET LABEL FILE (train-labels-idx1-ubyte):
[offset] [type]          [value]          [description] 
0000     32 bit integer  0x00000801(2049) magic number (MSB first) 
0004     32 bit integer  60000            number of items 
0008     unsigned byte   ??               label 
0009     unsigned byte   ??               label 
........ xxxx     unsigned byte   ??               label

The labels values are 0 to 9.

TRAINING SET IMAGE FILE (train-images-idx3-ubyte):

[offset] [type]          [value]          [description] 
0000     32 bit integer  0x00000803(2051) magic number 
0004     32 bit integer  60000            number of images 
0008     32 bit integer  28               number of rows 
0012     32 bit integer  28               number of columns 
0016     unsigned byte   ??               pixel 
0017     unsigned byte   ??               pixel 
........ 
xxxx     unsigned byte   ??               pixel

Pixels are organized row-wise. Pixel values are 0 to 255. 0 means background (white), 255 means foreground (black).

TEST SET LABEL FILE (t10k-labels-idx1-ubyte):

[offset] [type]          [value]          [description] 
0000     32 bit integer  0x00000801(2049) magic number (MSB first) 
0004     32 bit integer  10000            number of items 
0008     unsigned byte   ??               label 
0009     unsigned byte   ??               label 
........ 
xxxx     unsigned byte   ??               label

The labels values are 0 to 9.

TEST SET IMAGE FILE (t10k-images-idx3-ubyte):

[offset] [type]          [value]          [description] 
0000     32 bit integer  0x00000803(2051) magic number 
0004     32 bit integer  10000            number of images 
0008     32 bit integer  28               number of rows 
0012     32 bit integer  28               number of columns 
0016     unsigned byte   ??               pixel 
0017     unsigned byte   ??               pixel 
........ 
xxxx     unsigned byte   ??               pixel

Pixels are organized row-wise. Pixel values are 0 to 255. 0 means background (white), 255 means foreground (black). 
  

#include <iostream>
#include <fstream>
#include <string>
#include <vector>
using namespace std;

int ReverseInt(int i)
{
	unsigned char ch1, ch2, ch3, ch4;
	ch1 = i & 255;
	ch2 = (i >> 8) & 255;
	ch3 = (i >> 16) & 255;
	ch4 = (i >> 24) & 255;
	return((int)ch1 << 24) + ((int)ch2 << 16) + ((int)ch3 << 8) + ch4;
}

void read_Mnist_Label(string filename, vector<double>&labels)
{
	ifstream file(filename, ios::binary);
	if (file.is_open())
	{
		int magic_number = 0;
		int number_of_images = 0;
		file.read((char*)&magic_number, sizeof(magic_number));
		file.read((char*)&number_of_images, sizeof(number_of_images));
		magic_number = ReverseInt(magic_number);
		number_of_images = ReverseInt(number_of_images);
		cout << "magic number = " << magic_number << endl;
		cout << "number of images = " << number_of_images << endl;
		
	
		for (int i = 0; i < number_of_images; i++)
		{
			unsigned char label = 0;
			file.read((char*)&label, sizeof(label));
			labels.push_back((double)label);
		}
		
	}
}

void read_Mnist_Images(string filename, vector<vector<double>>&images)
{
	ifstream file(filename, ios::binary);
	if (file.is_open())
	{
		int magic_number = 0;
		int number_of_images = 0;
		int n_rows = 0;
		int n_cols = 0;
		unsigned char label;
		file.read((char*)&magic_number, sizeof(magic_number));
		file.read((char*)&number_of_images, sizeof(number_of_images));
		file.read((char*)&n_rows, sizeof(n_rows));
		file.read((char*)&n_cols, sizeof(n_cols));
		magic_number = ReverseInt(magic_number);
		number_of_images = ReverseInt(number_of_images);
		n_rows = ReverseInt(n_rows);
		n_cols = ReverseInt(n_cols);

		cout << "magic number = " << magic_number << endl;
		cout << "number of images = " << number_of_images << endl;
		cout << "rows = " << n_rows << endl;
		cout << "cols = " << n_cols << endl;

		for (int i = 0; i < number_of_images; i++)
		{
			vector<double>tp;
			for (int r = 0; r < n_rows; r++)
			{
				for (int c = 0; c < n_cols; c++)
				{
					unsigned char image = 0;
					file.read((char*)&image, sizeof(image));
					tp.push_back(image);
				}
			}
			images.push_back(tp);
		}
	}
}

int main()
{
	/*
	vector<double>labels;
	read_Mnist_Label("t10k-labels.idx1-ubyte", labels);
	for (auto iter = labels.begin(); iter != labels.end(); iter++)
	{
		cout << *iter << " ";
	}
	*/
	vector<vector<double>>images;
	read_Mnist_Images("t10k-images.idx3-ubyte", images);
	for (int i = 0; i < images.size(); i++)
	{
		for (int j = 0; j < images[0].size(); j++)
		{
			cout << images[i][j] << " ";
		}
	}
	return 0;
}






评论 8
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

N3verL4nd

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值