DeepLearning tutorial（6）易用的深度学习框架Keras简介 致读者：本文写于keras开发初期，目前keras已经迭代到1.0版本，很多API都发生了较大的变化，所以本文的粘贴的一些代码可能已经过时，在我的github上有更新后的代码，读者需要的话可以看github上的代码：https://github.com/wepe/MachineLearning
之前我一直在使用Theano，前面五篇Deeplearning相关的文章也是学习Theano的一些笔记，当时已经觉得Theano用起来略显麻烦，有时想实现一个新的结构，就要花很多时间去编程，所以想过将代码模块化，方便重复使用，但因为实在太忙没有时间去做。最近发现了一个叫做Keras的框架，跟我的想法不谋而合，用起来特别简单，适合快速开发。
1. Keras简介
Keras是基于Theano的一个深度学习框架，它的设计参考了Torch，用Python语言编写，是一个高度模块化的神经网络库，支持GPU和CPU。使用文档在这：http://keras.io/，这个框架貌似是刚刚火起来的，使用上的问题可以到github提issue:https://github.com/fchollet/keras
下面简单介绍一下怎么使用Keras，以Mnist数据库为例,编写一个CNN网络结构，你将会发现特别简单。
2. Keras里的模块介绍
- Optimizers 顾名思义，Optimizers包含了一些优化的方法，比如最基本的随机梯度下降SGD,另外还有Adagrad、Adadelta、RMSprop、Adam，一些新的方法以后也会被不断添加进来。 <code class="hljs avrasm has-numbering" style="display: block; padding: 0px; background: transparent; color: inherit; box-sizing: border-box; font-family: "Source Code Pro", monospace;font-size:undefined; white-space: pre; border-radius: 0px; word-wrap: normal;">keras<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">.optimizers</span><span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">.SGD</span>(lr=<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">0.01</span>, momentum=<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">0.9</span>, decay=<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">0.9</span>, nesterov=False)</code><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; background-color: rgb(238, 238, 238); top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right: 1px solid rgb(221, 221, 221); list-style: none; text-align: right;"><li style="box-sizing: border-box; padding: 0px 5px;">1</li></ul><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; background-color: rgb(238, 238, 238); top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right: 1px solid rgb(221, 221, 221); list-style: none; text-align: right;"><li style="box-sizing: border-box; padding: 0px 5px;">1</li></ul> 上面的代码是SGD的使用方法，lr表示学习速率,momentum表示动量项，decay是学习速率的衰减系数(每个epoch衰减一次),Nesterov的值是False或者True，表示使不使用Nesterov momentum。其他的请参考文档。
- Objectives 这是目标函数模块，keras提供了mean_squared_error，mean_absolute_error ，squared_hinge，hinge，binary_crossentropy，categorical_crossentropy这几种目标函数。 这里binary_crossentropy 和 categorical_crossentropy也就是常说的logloss.
- Activations 这是激活函数模块，keras提供了linear、sigmoid、hard_sigmoid、tanh、softplus、relu、softplus，另外softmax也放在Activations模块里(我觉得放在layers模块里更合理些）。此外，像LeakyReLU和PReLU这种比较新的激活函数，keras在keras.layers.advanced_activations模块里提供。
- Initializations 这是参数初始化模块，在添加layer的时候调用init进行初始化。keras提供了uniform、lecun_uniform、normal、orthogonal、zero、glorot_normal、he_normal这几种。
- layers layers模块包含了core、convolutional、recurrent、advanced_activations、normalization、embeddings这几种layer。 其中core里面包含了flatten(CNN的全连接层之前需要把二维特征图flatten成为一维的)、reshape（CNN输入时将一维的向量弄成二维的）、dense(就是隐藏层，dense是稠密的意思),还有其他的就不介绍了。convolutional层基本就是Theano的Convolution2D的封装。
- Preprocessing 这是预处理模块，包括序列数据的处理，文本数据的处理，图像数据的处理。重点看一下图像数据的处理，keras提供了ImageDataGenerator函数,实现data augmentation，数据集扩增，对图像做一些弹性变换，比如水平翻转，垂直翻转，旋转等。
- Models 这是最主要的模块，模型。上面定义了各种基本组件，model是将它们组合起来，下面通过一个实例来说明。
3.一个实例：用CNN分类Mnist
- 数据下载 Mnist数据在其官网上有提供，但是不是图像格式的，因为我们通常都是直接处理图像，为了以后程序能复用，我把它弄成图像格式的，这里可以下载：http://pan.baidu.com/s/1qCdS6，共有42000张图片。
- 读取图片数据 keras要求输入的数据格式是numpy.array类型（numpy是一个python的数值计算的库），所以需要写一个脚本来读入mnist图像，保存为一个四维的data，还有一个一维的label，代码：
<code class="hljs python has-numbering" style="display: block; padding: 0px; background: transparent; color: inherit; box-sizing: border-box; font-family: "Source Code Pro", monospace;font-size:undefined; white-space: pre; border-radius: 0px; word-wrap: normal;"><span class="hljs-comment" style="color: rgb(136, 0, 0); box-sizing: border-box;">#coding:utf-8</span>
<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">"""
Author:wepon
Source:https://github.com/wepe
file:data.py
"""</span>
<span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">import</span> os
<span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">from</span> PIL <span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">import</span> Image
<span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">import</span> numpy <span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">as</span> np
<span class="hljs-comment" style="color: rgb(136, 0, 0); box-sizing: border-box;">#读取文件夹mnist下的42000张图片，图片为灰度图，所以为1通道，</span>
<span class="hljs-comment" style="color: rgb(136, 0, 0); box-sizing: border-box;">#如果是将彩色图作为输入,则将1替换为3，并且data[i,:,:,:] = arr改为data[i,:,:,:] = [arr[:,:,0],arr[:,:,1],arr[:,:,2]]</span>
<span class="hljs-function" style="box-sizing: border-box;"><span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">def</span> <span class="hljs-title" style="box-sizing: border-box;">load_data</span><span class="hljs-params" style="color: rgb(102, 0, 102); box-sizing: border-box;">()</span>:</span>
data = np.empty((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">42000</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">28</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">28</span>),dtype=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">"float32"</span>)
label = np.empty((<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">42000</span>,),dtype=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">"uint8"</span>)
imgs = os.listdir(<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">"./mnist"</span>)
num = len(imgs)
<span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">for</span> i <span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">in</span> range(num):
img = Image.open(<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">"./mnist/"</span> imgs[i])
arr = np.asarray(img,dtype=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">"float32"</span>)
data[i,:,:,:] = arr
label[i] = int(imgs[i].split(<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'.'</span>)[<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">0</span>])
<span class="hljs-keyword" style="color: rgb(0, 0, 136); box-sizing: border-box;">return</span> data,label</code><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; background-color: rgb(238, 238, 238); top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right: 1px solid rgb(221, 221, 221); list-style: none; text-align: right;"><li style="box-sizing: border-box; padding: 0px 5px;">1</li><li style="box-sizing: border-box; padding: 0px 5px;">2</li><li style="box-sizing: border-box; padding: 0px 5px;">3</li><li style="box-sizing: border-box; padding: 0px 5px;">4</li><li style="box-sizing: border-box; padding: 0px 5px;">5</li><li style="box-sizing: border-box; padding: 0px 5px;">6</li><li style="box-sizing: border-box; padding: 0px 5px;">7</li><li style="box-sizing: border-box; padding: 0px 5px;">8</li><li style="box-sizing: border-box; padding: 0px 5px;">9</li><li style="box-sizing: border-box; padding: 0px 5px;">10</li><li style="box-sizing: border-box; padding: 0px 5px;">11</li><li style="box-sizing: border-box; padding: 0px 5px;">12</li><li style="box-sizing: border-box; padding: 0px 5px;">13</li><li style="box-sizing: border-box; padding: 0px 5px;">14</li><li style="box-sizing: border-box; padding: 0px 5px;">15</li><li style="box-sizing: border-box; padding: 0px 5px;">16</li><li style="box-sizing: border-box; padding: 0px 5px;">17</li><li style="box-sizing: border-box; padding: 0px 5px;">18</li><li style="box-sizing: border-box; padding: 0px 5px;">19</li><li style="box-sizing: border-box; padding: 0px 5px;">20</li><li style="box-sizing: border-box; padding: 0px 5px;">21</li><li style="box-sizing: border-box; padding: 0px 5px;">22</li><li style="box-sizing: border-box; padding: 0px 5px;">23</li><li style="box-sizing: border-box; padding: 0px 5px;">24</li><li style="box-sizing: border-box; padding: 0px 5px;">25</li></ul><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; background-color: rgb(238, 238, 238); top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right: 1px solid rgb(221, 221, 221); list-style: none; text-align: right;"><li style="box-sizing: border-box; padding: 0px 5px;">1</li><li style="box-sizing: border-box; padding: 0px 5px;">2</li><li style="box-sizing: border-box; padding: 0px 5px;">3</li><li style="box-sizing: border-box; padding: 0px 5px;">4</li><li style="box-sizing: border-box; padding: 0px 5px;">5</li><li style="box-sizing: border-box; padding: 0px 5px;">6</li><li style="box-sizing: border-box; padding: 0px 5px;">7</li><li style="box-sizing: border-box; padding: 0px 5px;">8</li><li style="box-sizing: border-box; padding: 0px 5px;">9</li><li style="box-sizing: border-box; padding: 0px 5px;">10</li><li style="box-sizing: border-box; padding: 0px 5px;">11</li><li style="box-sizing: border-box; padding: 0px 5px;">12</li><li style="box-sizing: border-box; padding: 0px 5px;">13</li><li style="box-sizing: border-box; padding: 0px 5px;">14</li><li style="box-sizing: border-box; padding: 0px 5px;">15</li><li style="box-sizing: border-box; padding: 0px 5px;">16</li><li style="box-sizing: border-box; padding: 0px 5px;">17</li><li style="box-sizing: border-box; padding: 0px 5px;">18</li><li style="box-sizing: border-box; padding: 0px 5px;">19</li><li style="box-sizing: border-box; padding: 0px 5px;">20</li><li style="box-sizing: border-box; padding: 0px 5px;">21</li><li style="box-sizing: border-box; padding: 0px 5px;">22</li><li style="box-sizing: border-box; padding: 0px 5px;">23</li><li style="box-sizing: border-box; padding: 0px 5px;">24</li><li style="box-sizing: border-box; padding: 0px 5px;">25</li></ul>- 构建CNN，训练 短短二十多行代码，构建一个三个卷积层的CNN，直接读下面的代码吧，有注释，很容易读懂：
<code class="hljs vala has-numbering" style="display: block; padding: 0px; background: transparent; color: inherit; box-sizing: border-box; font-family: "Source Code Pro", monospace;font-size:undefined; white-space: pre; border-radius: 0px; word-wrap: normal;"><span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#导入各种用到的模块组件</span>
from __future__ import absolute_import
from __future__ import print_function
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.advanced_activations import PReLU
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.optimizers import SGD, Adadelta, Adagrad
from keras.utils import np_utils, generic_utils
from six.moves import range
from data import load_data
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#加载数据</span>
data, label = load_data()
print(data.shape[<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">0</span>], <span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">' samples'</span>)
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#label为0~9共10个类别，keras要求格式为binary class matrices,转化一下，直接调用keras提供的这个函数</span>
label = np_utils.to_categorical(label, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">10</span>)
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">###############</span>
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#开始建立CNN模型</span>
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">###############</span>
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#生成一个model</span>
model = Sequential()
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#第一个卷积层，4个卷积核，每个卷积核大小5*5。1表示输入的图片的通道,灰度图为1通道。</span>
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#border_mode可以是valid或者full，具体看这里说明：http://deeplearning.net/software/theano/library/tensor/nnet/conv.html#theano.tensor.nnet.conv.conv2d</span>
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#激活函数用tanh</span>
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#你还可以在model.add(Activation('tanh'))后加上dropout的技巧: model.add(Dropout(0.5))</span>
model.add(Convolution2D(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">4</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">5</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">5</span>, border_mode=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'valid'</span>))
model.add(Activation(<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'tanh'</span>))
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#第二个卷积层，8个卷积核，每个卷积核大小3*3。4表示输入的特征图个数，等于上一层的卷积核个数</span>
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#激活函数用tanh</span>
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#采用maxpooling，poolsize为(2,2)</span>
model.add(Convolution2D(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">8</span>,<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">4</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, border_mode=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'valid'</span>))
model.add(Activation(<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'tanh'</span>))
model.add(MaxPooling2D(poolsize=(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>)))
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#第三个卷积层，16个卷积核，每个卷积核大小3*3</span>
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#激活函数用tanh</span>
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#采用maxpooling，poolsize为(2,2)</span>
model.add(Convolution2D(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">16</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">8</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">3</span>, border_mode=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'valid'</span>))
model.add(Activation(<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'tanh'</span>))
model.add(MaxPooling2D(poolsize=(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">2</span>)))
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#全连接层，先将前一层输出的二维特征图flatten为一维的。</span>
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#Dense就是隐藏层。16就是上一层输出的特征图个数。4是根据每个卷积层计算出来的：(28-5 1)得到24,(24-3 1)/2得到11，(11-3 1)/2得到4</span>
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#全连接有128个神经元节点,初始化方式为normal</span>
model.add(Flatten())
model.add(Dense(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">16</span>*<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">4</span>*<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">4</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">128</span>, init=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'normal'</span>))
model.add(Activation(<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'tanh'</span>))
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#Softmax分类，输出是10类别</span>
model.add(Dense(<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">128</span>, <span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">10</span>, init=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'normal'</span>))
model.add(Activation(<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'softmax'</span>))
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#############</span>
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#开始训练模型</span>
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">##############</span>
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#使用SGD momentum</span>
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#model.compile里的参数loss就是损失函数(目标函数)</span>
sgd = SGD(l2=<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">0.0</span>,lr=<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">0.05</span>, decay=<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1e-6</span>, momentum=<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">0.9</span>, nesterov=True)
model.compile(loss=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">'categorical_crossentropy'</span>, optimizer=sgd,class_mode=<span class="hljs-string" style="color: rgb(0, 136, 0); box-sizing: border-box;">"categorical"</span>)
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#调用fit方法，就是一个训练过程. 训练的epoch数设为10，batch_size为100．</span>
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#数据经过随机打乱shuffle=True。verbose=1，训练过程中输出的信息，0、1、2三种方式都可以，无关紧要。show_accuracy=True，训练时每一个epoch都输出accuracy。</span>
<span class="hljs-preprocessor" style="color: rgb(68, 68, 68); box-sizing: border-box;">#validation_split=0.2，将20%的数据作为验证集。</span>
/*
* 提示：该行代码过长，系统自动注释不进行高亮。一键复制会移除系统注释
* model.fit(data, label, batch_size=<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">100</span>,nb_epoch=<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">10</span>,shuffle=True,verbose=<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">1</span>,show_accuracy=True,validation_split=<span class="hljs-number" style="color: rgb(0, 102, 102); box-sizing: border-box;">0.2</span>)</code><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; background-color: rgb(238, 238, 238); top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right: 1px solid rgb(221, 221, 221); list-style: none; text-align: right;"><li style="box-sizing: border-box; padding: 0px 5px;">1</li><li style="box-sizing: border-box; padding: 0px 5px;">2</li><li style="box-sizing: border-box; padding: 0px 5px;">3</li><li style="box-sizing: border-box; padding: 0px 5px;">4</li><li style="box-sizing: border-box; padding: 0px 5px;">5</li><li style="box-sizing: border-box; padding: 0px 5px;">6</li><li style="box-sizing: border-box; padding: 0px 5px;">7</li><li style="box-sizing: border-box; padding: 0px 5px;">8</li><li style="box-sizing: border-box; padding: 0px 5px;">9</li><li style="box-sizing: border-box; padding: 0px 5px;">10</li><li style="box-sizing: border-box; padding: 0px 5px;">11</li><li style="box-sizing: border-box; padding: 0px 5px;">12</li><li style="box-sizing: border-box; padding: 0px 5px;">13</li><li style="box-sizing: border-box; padding: 0px 5px;">14</li><li style="box-sizing: border-box; padding: 0px 5px;">15</li><li style="box-sizing: border-box; padding: 0px 5px;">16</li><li style="box-sizing: border-box; padding: 0px 5px;">17</li><li style="box-sizing: border-box; padding: 0px 5px;">18</li><li style="box-sizing: border-box; padding: 0px 5px;">19</li><li style="box-sizing: border-box; padding: 0px 5px;">20</li><li style="box-sizing: border-box; padding: 0px 5px;">21</li><li style="box-sizing: border-box; padding: 0px 5px;">22</li><li style="box-sizing: border-box; padding: 0px 5px;">23</li><li style="box-sizing: border-box; padding: 0px 5px;">24</li><li style="box-sizing: border-box; padding: 0px 5px;">25</li><li style="box-sizing: border-box; padding: 0px 5px;">26</li><li style="box-sizing: border-box; padding: 0px 5px;">27</li><li style="box-sizing: border-box; padding: 0px 5px;">28</li><li style="box-sizing: border-box; padding: 0px 5px;">29</li><li style="box-sizing: border-box; padding: 0px 5px;">30</li><li style="box-sizing: border-box; padding: 0px 5px;">31</li><li style="box-sizing: border-box; padding: 0px 5px;">32</li><li style="box-sizing: border-box; padding: 0px 5px;">33</li><li style="box-sizing: border-box; padding: 0px 5px;">34</li><li style="box-sizing: border-box; padding: 0px 5px;">35</li><li style="box-sizing: border-box; padding: 0px 5px;">36</li><li style="box-sizing: border-box; padding: 0px 5px;">37</li><li style="box-sizing: border-box; padding: 0px 5px;">38</li><li style="box-sizing: border-box; padding: 0px 5px;">39</li><li style="box-sizing: border-box; padding: 0px 5px;">40</li><li style="box-sizing: border-box; padding: 0px 5px;">41</li><li style="box-sizing: border-box; padding: 0px 5px;">42</li><li style="box-sizing: border-box; padding: 0px 5px;">43</li><li style="box-sizing: border-box; padding: 0px 5px;">44</li><li style="box-sizing: border-box; padding: 0px 5px;">45</li><li style="box-sizing: border-box; padding: 0px 5px;">46</li><li style="box-sizing: border-box; padding: 0px 5px;">47</li><li style="box-sizing: border-box; padding: 0px 5px;">48</li><li style="box-sizing: border-box; padding: 0px 5px;">49</li><li style="box-sizing: border-box; padding: 0px 5px;">50</li><li style="box-sizing: border-box; padding: 0px 5px;">51</li><li style="box-sizing: border-box; padding: 0px 5px;">52</li><li style="box-sizing: border-box; padding: 0px 5px;">53</li><li style="box-sizing: border-box; padding: 0px 5px;">54</li><li style="box-sizing: border-box; padding: 0px 5px;">55</li><li style="box-sizing: border-box; padding: 0px 5px;">56</li><li style="box-sizing: border-box; padding: 0px 5px;">57</li><li style="box-sizing: border-box; padding: 0px 5px;">58</li><li style="box-sizing: border-box; padding: 0px 5px;">59</li><li style="box-sizing: border-box; padding: 0px 5px;">60</li><li style="box-sizing: border-box; padding: 0px 5px;">61</li><li style="box-sizing: border-box; padding: 0px 5px;">62</li><li style="box-sizing: border-box; padding: 0px 5px;">63</li><li style="box-sizing: border-box; padding: 0px 5px;">64</li><li style="box-sizing: border-box; padding: 0px 5px;">65</li><li style="box-sizing: border-box; padding: 0px 5px;">66</li><li style="box-sizing: border-box; padding: 0px 5px;">67</li><li style="box-sizing: border-box; padding: 0px 5px;">68</li><li style="box-sizing: border-box; padding: 0px 5px;">69</li><li style="box-sizing: border-box; padding: 0px 5px;">70</li><li style="box-sizing: border-box; padding: 0px 5px;">71</li></ul><ul class="pre-numbering" style="box-sizing: border-box; position: absolute; width: 50px; background-color: rgb(238, 238, 238); top: 0px; left: 0px; margin: 0px; padding: 6px 0px 40px; border-right: 1px solid rgb(221, 221, 221); list-style: none; text-align: right;"><li style="box-sizing: border-box; padding: 0px 5px;">1</li><li style="box-sizing: border-box; padding: 0px 5px;">2</li><li style="box-sizing: border-box; padding: 0px 5px;">3</li><li style="box-sizing: border-box; padding: 0px 5px;">4</li><li style="box-sizing: border-box; padding: 0px 5px;">5</li><li style="box-sizing: border-box; padding: 0px 5px;">6</li><li style="box-sizing: border-box; padding: 0px 5px;">7</li><li style="box-sizing: border-box; padding: 0px 5px;">8</li><li style="box-sizing: border-box; padding: 0px 5px;">9</li><li style="box-sizing: border-box; padding: 0px 5px;">10</li><li style="box-sizing: border-box; padding: 0px 5px;">11</li><li style="box-sizing: border-box; padding: 0px 5px;">12</li><li style="box-sizing: border-box; padding: 0px 5px;">13</li><li style="box-sizing: border-box; padding: 0px 5px;">14</li><li style="box-sizing: border-box; padding: 0px 5px;">15</li><li style="box-sizing: border-box; padding: 0px 5px;">16</li><li style="box-sizing: border-box; padding: 0px 5px;">17</li><li style="box-sizing: border-box; padding: 0px 5px;">18</li><li style="box-sizing: border-box; padding: 0px 5px;">19</li><li style="box-sizing: border-box; padding: 0px 5px;">20</li><li style="box-sizing: border-box; padding: 0px 5px;">21</li><li style="box-sizing: border-box; padding: 0px 5px;">22</li><li style="box-sizing: border-box; padding: 0px 5px;">23</li><li style="box-sizing: border-box; padding: 0px 5px;">24</li><li style="box-sizing: border-box; padding: 0px 5px;">25</li><li style="box-sizing: border-box; padding: 0px 5px;">26</li><li style="box-sizing: border-box; padding: 0px 5px;">27</li><li style="box-sizing: border-box; padding: 0px 5px;">28</li><li style="box-sizing: border-box; padding: 0px 5px;">29</li><li style="box-sizing: border-box; padding: 0px 5px;">30</li><li style="box-sizing: border-box; padding: 0px 5px;">31</li><li style="box-sizing: border-box; padding: 0px 5px;">32</li><li style="box-sizing: border-box; padding: 0px 5px;">33</li><li style="box-sizing: border-box; padding: 0px 5px;">34</li><li style="box-sizing: border-box; padding: 0px 5px;">35</li><li style="box-sizing: border-box; padding: 0px 5px;">36</li><li style="box-sizing: border-box; padding: 0px 5px;">37</li><li style="box-sizing: border-box; padding: 0px 5px;">38</li><li style="box-sizing: border-box; padding: 0px 5px;">39</li><li style="box-sizing: border-box; padding: 0px 5px;">40</li><li style="box-sizing: border-box; padding: 0px 5px;">41</li><li style="box-sizing: border-box; padding: 0px 5px;">42</li><li style="box-sizing: border-box; padding: 0px 5px;">43</li><li style="box-sizing: border-box; padding: 0px 5px;">44</li><li style="box-sizing: border-box; padding: 0px 5px;">45</li><li style="box-sizing: border-box; padding: 0px 5px;">46</li><li style="box-sizing: border-box; padding: 0px 5px;">47</li><li style="box-sizing: border-box; padding: 0px 5px;">48</li><li style="box-sizing: border-box; padding: 0px 5px;">49</li><li style="box-sizing: border-box; padding: 0px 5px;">50</li><li style="box-sizing: border-box; padding: 0px 5px;">51</li><li style="box-sizing: border-box; padding: 0px 5px;">52</li><li style="box-sizing: border-box; padding: 0px 5px;">53</li><li style="box-sizing: border-box; padding: 0px 5px;">54</li><li style="box-sizing: border-box; padding: 0px 5px;">55</li><li style="box-sizing: border-box; padding: 0px 5px;">56</li><li style="box-sizing: border-box; padding: 0px 5px;">57</li><li style="box-sizing: border-box; padding: 0px 5px;">58</li><li style="box-sizing: border-box; padding: 0px 5px;">59</li><li style="box-sizing: border-box; padding: 0px 5px;">60</li><li style="box-sizing: border-box; padding: 0px 5px;">61</li><li style="box-sizing: border-box; padding: 0px 5px;">62</li><li style="box-sizing: border-box; padding: 0px 5px;">63</li><li style="box-sizing: border-box; padding: 0px 5px;">64</li><li style="box-sizing: border-box; padding: 0px 5px;">65</li><li style="box-sizing: border-box; padding: 0px 5px;">66</li><li style="box-sizing: border-box; padding: 0px 5px;">67</li><li style="box-sizing: border-box; padding: 0px 5px;">68</li><li style="box-sizing: border-box; padding: 0px 5px;">69</li><li style="box-sizing: border-box; padding: 0px 5px;">70</li><li style="box-sizing: border-box; padding: 0px 5px;">71</li></ul>
*/- 代码使用与结果
代码放在我github的机器学习仓库里：https://github.com/wepe/MachineLearning,非github用户直接点右下的DownloadZip。
在/DeepLearning Tutorials/keras_usage目录下包括data.py,cnn.py两份代码，下载Mnist数据后解压到该目录下，运行cnn.py这份文件即可。
结果如下所示，在Epoch 9达到了0.98的训练集识别率和0.97的验证集识别率：
