Mnist handwritten digital Database

The handwritten digital library is easy to build, but it's always a waste of time. Google Labs Corinna Cortes and the Yann LeCun of the NYU Crown Institute have a handwritten digital database with 60,000 handwritten digital images in the training library and 10,000 in the test library.

Please visit the original station http://yann.lecun.com/exdb/mnist/

The database contains all the images in a file and is inconvenient to use. If I save each image separately, it becomes an independent database of the images.

and hosted in Google Code.

If you have a need, please download here:

http://yann.lecun.com/exdb/mnist/

Http://code.google.com/p/supplement-of-the-mnist-database-of-handwritten-digits/downloads/list

Handwritten Digits MNIST handwritten Digits [Data/mnist_all.mat]
[Training pictures: 0 1 2  3 4 5 6 7 8 9 ]
[Testing pictures: 0 1 2 3  4 5 6 7 8 9 ]
8-bit grayscale images of "0" through "9"; About 6K Training Examples of each class; 1 k test examples USPS handwritten Digits [Data/usps_all.mat]
[pictures: 0123456789 ]
8-bit Grayscale Images of "0" through "9"; 1100 examples of each class. Binary alphadigits [Data/binaryalphadigs.mat] [picture]
binary 20x16 digits of "0" through "9" and capital "A" through "Z". Examples of each class.
from Simon Lucas ' ([email protected] ),  algoval system.

Also provide MATLAB read mnist, USPS, Binary alphadigits database, data for MATLAB hackers, see: http://www.cs.toronto.edu/~roweis/data.html

Reference URL:
[1] http://yann.lecun.com/exdb/mnist/
[2] http://hi.baidu.com/ln0707/blog/item/8207ef010a243d81d53f7c03.html
[3] Http://www.cs.toronto.edu/~roweis/data.html

[4] http://blog.csdn.net/onezeros/archive/2010/05/28/5631930.aspx

How to use the Mnist dataset:

Mnist is a supposedly well-known handwritten digital database, which is said to be handwritten figures of American middle school students, and most of the truth is written quite ugly ... Anyway, fortunately can understand is which number. The topic now is to use the CNN (convolutional neural network) to identify the number of this database. I think CNN really does not understand, but first figure out how to read into the database bar, otherwise there is no real theory can not be drilled. The average person will use MATLAB to do the neural network of East, and I was a general person. Of course, non-ordinary people may use the high-end platform such as Python, anyway, I will not ...

First on the search engine, whether it is Baidu or Google, search "MNIST" the first out of the affirmation is

http://yann.lecun.com/exdb/mnist/Yes, that's it! This page has four compressed package links, download it down, Junior! Then don't be too busy turning off the page, because the data you read later depends on the description of the page.

Here is an example of one of the packages t10k-images_idx3, which describes how to use this database.

This is from verysource.com above download source code, likes one! and praise one!

The% matlab_read_t10k-images_idx3.m% is used to read the T10k-images.idx3-ubyte files in the mnist dataset and convert them into BMP format picture output. % Usage: Run program, will pop up select test picture Data File t10k-labels.idx1-ubyte Path dialog box and% Select Save test Picture Path dialog box, select Path after the program automatically run, the progress bar will show processing progress. The% picture is saved in testimage_00001.bmp~testimage_10000.bmp format in the specified path, 10,000 files occupy 39M of space. % The entire program takes a few minutes to run. % written by [email protected] iprai% 2009-2-22clear all;clc;% Read training picture data file [Filename,pathname] = Uigetfile (' *. * ', ' Select test picture data File T10k-images.idx3-ubyte '); Trainfile = FullFile (pathname,filename); fid = fopen (trainfile, ' R '); %fopen () is the most core function, the import file, ' R ' represents the read-In a = Fread (fid,16, ' uint8 '); % here it is necessary to note that the first 16 bits of the package are descriptive information, and from the page mentioned above you can see what the meaning of the particular person represents. So a variable extracts this information and records it to facilitate the subsequent creation of a matrix and other actions. Magicnum = ((A (1) *256+a (2)) *256+a (3)) *256+a (4); imagenum = ((A (5) *256+a (6)) *256+a (7)) *256+a (8); Imagerow = ((A (9) *256+ A (Ten)) *256+a (one)) *256+a (16), Imagecol = ((A () *256+a (+)) *256+a ()from the page mentioned above can understand the four sentences, given the size of the data setif ((magicnum~=2051) | | |    (imagenum~=10000)) Error (' Not MNIST t10k-images.idx3-ubyte file!    ‘);        Fclose (FID);    Return End% excludes selecting the wrong file. Savedirectory = Uigetdir (', ' Select test picture path: '); h_w = Waitbar (0, ' Please wait, process in >> '); for i=1:imagenum B = fread (Fid,imagerow*im   Agecol, ' uint8 '); %fread () is also one of the core functions, B records the data string of a graph.    Note that this is still a string, is not see any clues. c = Reshape (B,[imagerow imagecol]); % highlights came, reshape re-form the matrix, and finally turned the string over.    Well-known picture is The matrix, here reshape out of the gray matrix is the handwritten number of the matrix. D = C ';    % transpose, because the number of C is sideways ... e = 255-d;    % according to the gray scale theory, 0 is black, 255 is white, in order to make white black word added e E = uint8 (e);    Savepath = fullfile (savedirectory,[' Testimage_ ' num2str (i,d) '. bmp]); Imwrite (E,savepath, ' bmp '); % finally write the picture Waitbar (I/imagenum) with Imwrite; Endfclose (FID); close (h_w);

In the chosen path, there is a whole bunch of pictures of mnist handwritten numbers. If you want to get one, use Imread () to get it!

Mnist handwritten digital Database