mnist手写数字体识别CNN训练测试完美复现，以及自己手写数字进行测试

mnist手写数字体识别，算是计算机视觉、图像识别领域的入门级demo了。就好像你学习编程首先要打出一个’hello world’。

实现手写数字体识别有多种方式，可以用回归法，可以用CNN，可以用RNN，等等。代码简洁程度不同，训练的精度也不尽相同。

---

1、mnist数据集介绍

这个数据集是来自美国国家标准与技术研究所, National Institute of Standards and Technology (NIST)。训练集 (training set) 由来自 250 个不同人手写的数字构成, 其中 50% 是高中学生, 50% 来自人口普查局 (the Census Bureau) 的工作人员. 测试集(test set) 也是同样比例的手写数字数据。

为什么要找这么多人来写呢？就是要增强学习结果的泛化能力，避免最后只认识某几个人的手写体。

import pylab
print('训练数据：',data.train.images)
print('训练集尺寸：',data.train.images.shape)
print('训练集标签尺寸：',data.train.labels.shape)
print('测试集尺寸：',data.test.images.shape)
print('测试集标签尺寸：',data.test.labels.shape)
'''
回归：
训练数据： [[0. 0. 0. ... 0. 0. 0.]
 [0. 0. 0. ... 0. 0. 0.]
 [0. 0. 0. ... 0. 0. 0.]
 ...
 [0. 0. 0. ... 0. 0. 0.]
 [0. 0. 0. ... 0. 0. 0.]
 [0. 0. 0. ... 0. 0. 0.]]
训练集尺寸： (55000, 784)
训练集标签尺寸： (55000, 10)
测试集尺寸： (10000, 784)
测试集标签尺寸： (10000, 10)
'''

可以看到，在这个数据集中，训练集一共有55000个图片，存放在一个矩阵数组中，每一行是一个图片。测试机一共有10000个图片。他们对应的标签就是one_hot编码，例如数字0的标签是1000000000，数字1的标签是0100000000，以此类推。

打印几张mnist中的图片来看一下：

import pylab
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
DATA_DIR = 'MNIST_data'
data = input_data.read_data_sets(DATA_DIR, one_hot=True)
pylab.figure(figsize=(10,10))
for i in range(10): 
    im = data.train.images[i]
    im = im.reshape((28,28))
    pylab.imshow(im)
    pylab.show()
im

这个数字。。。有的连我自己都不认识。

每一个图片是这样保存的，都是一个28*28的数组。

2、softmax回归法实现

回归就是直接根据图片每个位置的像素特征，来训练图片每个位置关于数字0-9的权重，这里把一个28*28的图片直接拉成一个784的向量，缺点显然易见：

• 没有利用到图片的一个空间信息，也就是我们所说的上下文信息。
• 另外，整个程序就像是一个黑盒子，我们不知道机器是怎么学习的。

下面是运行结果：（代码和数据集我会打包进行分享）

Extracting MNIST_data\train-images-idx3-ubyte.gz
Extracting MNIST_data\train-labels-idx1-ubyte.gz
Extracting MNIST_data\t10k-images-idx3-ubyte.gz
Extracting MNIST_data\t10k-labels-idx1-ubyte.gz
Accuracy: 91.83%
Extracting MNIST_data\train-images-idx3-ubyte.gz
Extracting MNIST_data\train-labels-idx1-ubyte.gz
Extracting MNIST_data\t10k-images-idx3-ubyte.gz
Extracting MNIST_data\t10k-labels-idx1-ubyte.gz
Accuracy: 91.29%
Extracting MNIST_data\train-images-idx3-ubyte.gz
Extracting MNIST_data\train-labels-idx1-ubyte.gz
Extracting MNIST_data\t10k-images-idx3-ubyte.gz
Extracting MNIST_data\t10k-labels-idx1-ubyte.gz
Accuracy: 91.82%
Extracting MNIST_data\train-images-idx3-ubyte.gz
Extracting MNIST_data\train-labels-idx1-ubyte.gz
Extracting MNIST_data\t10k-images-idx3-ubyte.gz
Extracting MNIST_data\t10k-labels-idx1-ubyte.gz
Accuracy: 91.67%
Extracting MNIST_data\train-images-idx3-ubyte.gz
Extracting MNIST_data\train-labels-idx1-ubyte.gz
Extracting MNIST_data\t10k-images-idx3-ubyte.gz
Extracting MNIST_data\t10k-labels-idx1-ubyte.gz
Accuracy: 91.29%

精度不是很高，只有91％多一点。

3、卷积神经网络实现及试验

再来看一下强大的神经网络：
step 0, training accuracy 0.08
step 100, training accuracy 0.82
step 200, training accuracy 0.94
step 300, training accuracy 0.92
step 400, training accuracy 0.92
step 500, training accuracy 0.98
step 600, training accuracy 0.92
step 700, training accuracy 0.94
step 800, training accuracy 1
step 900, training accuracy 0.98
step 1000, training accuracy 1
step 1100, training accuracy 0.98
step 1200, training accuracy 0.98
step 1300, training accuracy 0.98
step 1400, training accuracy 0.98
step 1500, training accuracy 0.94
step 1600, training accuracy 1
step 1700, training accuracy 0.96
step 1800, training accuracy 0.98
step 1900, training accuracy 1
step 2000, training accuracy 1
step 2100, training accuracy 0.98
step 2200, training accuracy 0.98
step 2300, training accuracy 0.98
step 2400, training accuracy 1
step 2500, training accuracy 1
step 2600, training accuracy 0.98
step 2700, training accuracy 0.94
step 2800, training accuracy 0.96
step 2900, training accuracy 1
step 3000, training accuracy 0.92
step 3100, training accuracy 1
step 3200, training accuracy 0.98
step 3300, training accuracy 0.98
step 3400, training accuracy 0.98
step 3500, training accuracy 1
step 3600, training accuracy 1
step 3700, training accuracy 1
step 3800, training accuracy 0.96
step 3900, training accuracy 0.98
step 4000, training accuracy 1
step 4100, training accuracy 0.98
step 4200, training accuracy 0.98
step 4300, training accuracy 0.98
step 4400, training accuracy 1
step 4500, training accuracy 0.98
step 4600, training accuracy 1
step 4700, training accuracy 1
step 4800, training accuracy 0.98
step 4900, training accuracy 0.96
step 5000, training accuracy 1
step 5100, training accuracy 0.96
step 5200, training accuracy 1
step 5300, training accuracy 0.98
step 5400, training accuracy 0.98
step 5500, training accuracy 1
step 5600, training accuracy 0.98
step 5700, training accuracy 1
step 5800, training accuracy 1
step 5900, training accuracy 0.98
step 6000, training accuracy 0.92
step 6100, training accuracy 0.98
step 6200, training accuracy 0.96
step 6300, training accuracy 1
step 6400, training accuracy 1
step 6500, training accuracy 1
step 6600, training accuracy 1
step 6700, training accuracy 1
step 6800, training accuracy 1
step 6900, training accuracy 1
step 7000, training accuracy 1
step 7100, training accuracy 1
step 7200, training accuracy 1
step 7300, training accuracy 1
step 7400, training accuracy 1
step 7500, training accuracy 1
step 7600, training accuracy 1
step 7700, training accuracy 0.98
step 7800, training accuracy 1
step 7900, training accuracy 1
step 8000, training accuracy 1
step 8100, training accuracy 1
step 8200, training accuracy 1
step 8300, training accuracy 1
step 8400, training accuracy 0.98
step 8500, training accuracy 0.98
step 8600, training accuracy 1
step 8700, training accuracy 1
step 8800, training accuracy 1
step 8900, training accuracy 1
step 9000, training accuracy 1
step 9100, training accuracy 1
step 9200, training accuracy 1
step 9300, training accuracy 0.98
step 9400, training accuracy 1
step 9500, training accuracy 1
step 9600, training accuracy 1
step 9700, training accuracy 1
step 9800, training accuracy 0.98
step 9900, training accuracy 1
step 10000, training accuracy 1
step 10100, training accuracy 1
step 10200, training accuracy 1
step 10300, training accuracy 1
step 10400, training accuracy 1
step 10500, training accuracy 1
step 10600, training accuracy 1
step 10700, training accuracy 1
step 10800, training accuracy 1
step 10900, training accuracy 1
step 11000, training accuracy 1
step 11100, training accuracy 1
step 11200, training accuracy 1
step 11300, training accuracy 1
step 11400, training accuracy 1
step 11500, training accuracy 1
step 11600, training accuracy 1
step 11700, training accuracy 1
step 11800, training accuracy 1
step 11900, training accuracy 1
step 12000, training accuracy 1
step 12100, training accuracy 1
step 12200, training accuracy 0.96
step 12300, training accuracy 1
step 12400, training accuracy 1
step 12500, training accuracy 1
step 12600, training accuracy 1
step 12700, training accuracy 1
step 12800, training accuracy 1
step 12900, training accuracy 0.98
step 13000, training accuracy 1
step 13100, training accuracy 1
step 13200, training accuracy 1
step 13300, training accuracy 1
step 13400, training accuracy 1
step 13500, training accuracy 1
step 13600, training accuracy 1
step 13700, training accuracy 1
step 13800, training accuracy 1
step 13900, training accuracy 1
step 14000, training accuracy 0.98
step 14100, training accuracy 1
step 14200, training accuracy 1
step 14300, training accuracy 1
step 14400, training accuracy 1
step 14500, training accuracy 0.98
step 14600, training accuracy 1
step 14700, training accuracy 1
step 14800, training accuracy 1
step 14900, training accuracy 1
step 15000, training accuracy 1
step 15100, training accuracy 1
step 15200, training accuracy 1
step 15300, training accuracy 1
step 15400, training accuracy 1
step 15500, training accuracy 1
step 15600, training accuracy 1
step 15700, training accuracy 0.98
step 15800, training accuracy 1
step 15900, training accuracy 1
step 16000, training accuracy 1
step 16100, training accuracy 1
step 16200, training accuracy 1
step 16300, training accuracy 1
step 16400, training accuracy 1
step 16500, training accuracy 1
step 16600, training accuracy 1
step 16700, training accuracy 1
step 16800, training accuracy 1
step 16900, training accuracy 1
step 17000, training accuracy 1
step 17100, training accuracy 1
step 17200, training accuracy 1
step 17300, training accuracy 1
step 17400, training accuracy 1
step 17500, training accuracy 1
step 17600, training accuracy 1
step 17700, training accuracy 1
step 17800, training accuracy 1
step 17900, training accuracy 1
step 18000, training accuracy 1
step 18100, training accuracy 1
step 18200, training accuracy 1
step 18300, training accuracy 1
step 18400, training accuracy 1
step 18500, training accuracy 1
step 18600, training accuracy 1
step 18700, training accuracy 1
step 18800, training accuracy 1
step 18900, training accuracy 1
step 19000, training accuracy 1
step 19100, training accuracy 1
step 19200, training accuracy 1
step 19300, training accuracy 0.98
step 19400, training accuracy 1
step 19500, training accuracy 1
step 19600, training accuracy 1
step 19700, training accuracy 1
step 19800, training accuracy 1
step 19900, training accuracy 1
test accuracy 0.9921
在训练到200步的时候，就超过了回归法，很快就达到了几乎百分之百的准确率。

这个准确率有没有水分呢，我们可以试验一下：

用画图工具手写数字，注意画板要改成28*28的像素，因为这个网络还比较低级。

训练时将权重保存在tf中，自己测试时加载上这个权重就可以了，在代码中都可以看到。

重复测试，可以发现它识别的是非常准的，随便画一个都能识别出来。

这个数据集和代码，有需要的可以在评论区留言，我可以发给你。