有人说，2018年人工智能已经进入了全球爆发的时刻。个性化信息推送、人脸识别、语音操控等人工智能技术，已“入侵”日常生活的细枝末节。

十多年前，所有的企业都在想办法互联网化，如今，所有的互联网企业都在试图AI化，据数据统计，平均每 10.9 个小时会诞生一家 AI 企业。在这样的背景下，不难想象，未来机器学习技术将会是技术人的新门槛和领域。

那么问题来了，作为一名技术者，我该如何转型/学习 AI 技术？别着急，本文将带你入门AI第一课：《手把手教你Keras实现CNN》，让你实现手写数字识别准确率达到99.6%！（附完整代码）。

在我们安装过Tensorflow后，安装Keras默认将TF作为后端，Keras实现卷积网络的代码十分简洁，而且keras中的callback类提供对模型训练过程中变量的检测方法，能够根据检测变量的情况及时的调整模型的学习效率和一些参数． 下面的例子，MNIST数据作为测试：

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

import matplotlib.image as pimg

import seaborn as sb # 一个构建在matplotlib上的绘画模块，支持numpy,pandas等数据结构

%matplotlib inline

from sklearn.model_selection import train_test_split

from sklearn.metrics import confusion_matrix # 混淆矩阵

import itertools

# keras

from keras.utils import to_categorical #数字标签转化成one-hot编码

from keras.models import Sequential

from keras.layers import Dense,Dropout,Flatten,Conv2D,MaxPool2D

from keras.optimizers import RMSprop

from keras.preprocessing.image import ImageDataGenerator

from keras.callbacks import ReduceLROnPlateau

Using TensorFlow backend.

# 设置绘画风格

sb.set(style='white', context='notebook', palette='deep')

# 加载数据

train_data = pd.read_csv('data/train.csv')

test_data = pd.read_csv('data/test.csv')

#train_x = train_data.drop(labels=['label'],axis=1) # 去掉标签列

train_x = train_data.iloc[:,1:]

train_y = train_data.iloc[:,0]

del train_data # 释放一下内存

# 观察一下训练数据的分布情况

g = sb.countplot(train_y)

train_y.value_counts()

1 4684

7 4401

3 4351

9 4188

2 4177

6 4137

0 4132

4 4072

8 4063

5 3795

Name: label, dtype: int64

train_x.isnull().describe() # 检查是否存在确实值

train_x.isnull().any().describe()

count 784

unique 1

top False

freq 784

dtype: object

test_data.isnull().any().describe()

count 784

unique 1

top False

freq 784

dtype: object

# 归一化

train_x = train_x/255.0

test_x = test_data/255.0

del test_data

转换数据的shape

# reshape trian_x, test_x

#train_x = train_x.values.reshape(-1, 28, 28, 1)

#test_x = test_x.values.reshape(-1, 28, 28, 1)

train_x = train_x.as_matrix().reshape(-1, 28, 28, 1)

test_x = test_x.as_matrix().reshape(-1, 28, 28, 1)

# 吧标签列转化为one-hot 编码格式

train_y = to_categorical(train_y, num_classes = 10)

#从训练数据中分出十分之一的数据作为验证数据

random_seed = 3

train_x , val_x , train_y, val_y = train_test_split(train_x, train_y, test_size=0.1, random_state=random_seed)

一个训练样本

plt.imshow(train_x[0][:,:,0])

使用Keras搭建CNN

model = Sequential()

# 第一个卷积层，32个卷积核，大小５x5，卷积模式SAME,激活函数relu,输入张量的大小

model.add(Conv2D(filters= 32, kernel_size=(5,5), padding='Same', activation='relu',input_shape=(28,28,1)))

model.add(Conv2D(filters= 32, kernel_size=(5,5), padding='Same', activation='relu'))

# 池化层,池化核大小２x2

model.add(MaxPool2D(pool_size=(2,2)))

# 随机丢弃四分之一的网络连接，防止过拟合

model.add(Dropout(0.25))

model.add(Conv2D(filters= 64, kernel_size=(3,3), padding='Same', activation='relu'))

model.add(Conv2D(filters= 64, kernel_size=(3,3), padding='Same', activation='relu'))

model.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))

model.add(Dropout(0.25))

# 全连接层,展开操作，

model.add(Flatten())

# 添加隐藏层神经元的数量和激活函数

model.add(Dense(256, activation='relu'))

model.add(Dropout(0.25))

# 输出层

model.add(Dense(10, activation='softmax'))

# 设置优化器

# lr :学习效率，　decay :lr的衰减值

optimizer = RMSprop(lr = 0.001, decay=0.0)

# 编译模型

# loss:损失函数，metrics：对应性能评估函数

model.compile(optimizer=optimizer, loss = 'categorical_crossentropy',metrics=['accuracy'])

创建一个callback类的实例

# keras的callback类提供了可以跟踪目标值，和动态调整学习效率

# moitor : 要监测的量，这里是验证准确率

# matience: 当经过３轮的迭代，监测的目标量，仍没有变化，就会调整学习效率

# verbose : 信息展示模式，去０或１

# factor :　每次减少学习率的因子，学习率将以lr = lr*factor的形式被减少

# mode：‘auto’，‘min’，‘max’之一，在min模式下，如果检测值触发学习率减少。在max模式下，当检测值不再上升则触发学习率减少。

# epsilon：阈值，用来确定是否进入检测值的“平原区”

# cooldown：学习率减少后，会经过cooldown个epoch才重新进行正常操作

# min_lr：学习率的下限

learning_rate_reduction = ReduceLROnPlateau(monitor = 'val_acc', patience = 3,

verbose = 1, factor=0.5, min_lr = 0.00001)

epochs = 40

batch_size = 100

数据增强处理

# 数据增强处理，提升模型的泛化能力，也可以有效的避免模型的过拟合

# rotation_range : 旋转的角度

# zoom_range : 随机缩放图像

# width_shift_range : 水平移动占图像宽度的比例

# height_shift_range

# horizontal_filp : 水平反转

# vertical_filp : 纵轴方向上反转

data_augment = ImageDataGenerator(rotation_range= 10,zoom_range= 0.1,

width_shift_range = 0.1,height_shift_range = 0.1,

horizontal_flip = False, vertical_flip = False)

训练模型

history = model.fit_generator(data_augment.flow(train_x, train_y, batch_size=batch_size),

epochs= epochs, validation_data = (val_x,val_y),

verbose =2, steps_per_epoch=train_x.shape[0]//batch_size,

callbacks=[learning_rate_reduction])

Epoch 1/40

359s - loss: 0.4529 - acc: 0.8498 - val_loss: 0.0658 - val_acc: 0.9793

Epoch 2/40

375s - loss: 0.1188 - acc: 0.9637 - val_loss: 0.0456 - val_acc: 0.9848

Epoch 3/40

374s - loss: 0.0880 - acc: 0.9734 - val_loss: 0.0502 - val_acc: 0.9845

Epoch 4/40

375s - loss: 0.0750 - acc: 0.9767 - val_loss: 0.0318 - val_acc: 0.9902

Epoch 5/40

374s - loss: 0.0680 - acc: 0.9800 - val_loss: 0.0379 - val_acc: 0.9888

Epoch 6/40

369s - loss: 0.0584 - acc: 0.9823 - val_loss: 0.0267 - val_acc: 0.9910

Epoch 7/40

381s - loss: 0.0556 - acc: 0.9832 - val_loss: 0.0505 - val_acc: 0.9824

Epoch 8/40

381s - loss: 0.0531 - acc: 0.9842 - val_loss: 0.0236 - val_acc: 0.9912

Epoch 9/40

376s - loss: 0.0534 - acc: 0.9839 - val_loss: 0.0310 - val_acc: 0.9910

Epoch 10/40

379s - loss: 0.0537 - acc: 0.9848 - val_loss: 0.0274 - val_acc: 0.9917

Epoch 11/40

375s - loss: 0.0501 - acc: 0.9856 - val_loss: 0.0254 - val_acc: 0.9931

Epoch 12/40

382s - loss: 0.0492 - acc: 0.9860 - val_loss: 0.0212 - val_acc: 0.9924

Epoch 13/40

380s - loss: 0.0482 - acc: 0.9864 - val_loss: 0.0259 - val_acc: 0.9919

Epoch 14/40

373s - loss: 0.0488 - acc: 0.9858 - val_loss: 0.0305 - val_acc: 0.9905

Epoch 15/40

Epoch 00014: reducing learning rate to 0.000500000023749.

370s - loss: 0.0493 - acc: 0.9853 - val_loss: 0.0259 - val_acc: 0.9919

Epoch 16/40

367s - loss: 0.0382 - acc: 0.9888 - val_loss: 0.0176 - val_acc: 0.9936

Epoch 17/40

376s - loss: 0.0376 - acc: 0.9891 - val_loss: 0.0187 - val_acc: 0.9945

Epoch 18/40

376s - loss: 0.0410 - acc: 0.9885 - val_loss: 0.0220 - val_acc: 0.9926

Epoch 19/40

371s - loss: 0.0385 - acc: 0.9886 - val_loss: 0.0194 - val_acc: 0.9933

Epoch 20/40

372s - loss: 0.0345 - acc: 0.9894 - val_loss: 0.0186 - val_acc: 0.9938

Epoch 21/40

Epoch 00020: reducing learning rate to 0.000250000011874.

375s - loss: 0.0395 - acc: 0.9888 - val_loss: 0.0233 - val_acc: 0.9945

Epoch 22/40

369s - loss: 0.0313 - acc: 0.9907 - val_loss: 0.0141 - val_acc: 0.9955

Epoch 23/40

376s - loss: 0.0308 - acc: 0.9910 - val_loss: 0.0187 - val_acc: 0.9945

Epoch 24/40

374s - loss: 0.0331 - acc: 0.9908 - val_loss: 0.0170 - val_acc: 0.9940

Epoch 25/40

372s - loss: 0.0325 - acc: 0.9904 - val_loss: 0.0166 - val_acc: 0.9948

Epoch 26/40

Epoch 00025: reducing learning rate to 0.000125000005937.

373s - loss: 0.0319 - acc: 0.9904 - val_loss: 0.0167 - val_acc: 0.9943

Epoch 27/40

372s - loss: 0.0285 - acc: 0.9915 - val_loss: 0.0138 - val_acc: 0.9950

Epoch 28/40

375s - loss: 0.0280 - acc: 0.9913 - val_loss: 0.0150 - val_acc: 0.9950

Epoch 29/40

Epoch 00028: reducing learning rate to 6.25000029686e-05.

377s - loss: 0.0281 - acc: 0.9924 - val_loss: 0.0158 - val_acc: 0.9948

Epoch 30/40

374s - loss: 0.0265 - acc: 0.9920 - val_loss: 0.0134 - val_acc: 0.9952

Epoch 31/40

378s - loss: 0.0270 - acc: 0.9922 - val_loss: 0.0128 - val_acc: 0.9957

Epoch 32/40

372s - loss: 0.0237 - acc: 0.9930 - val_loss: 0.0133 - val_acc: 0.9957

Epoch 33/40

375s - loss: 0.0237 - acc: 0.9931 - val_loss: 0.0138 - val_acc: 0.9955

Epoch 34/40

371s - loss: 0.0276 - acc: 0.9920 - val_loss: 0.0135 - val_acc: 0.9962

Epoch 35/40

373s - loss: 0.0259 - acc: 0.9920 - val_loss: 0.0136 - val_acc: 0.9952

Epoch 36/40

369s - loss: 0.0249 - acc: 0.9924 - val_loss: 0.0126 - val_acc: 0.9952

Epoch 37/40

370s - loss: 0.0257 - acc: 0.9923 - val_loss: 0.0130 - val_acc: 0.9960

Epoch 38/40

Epoch 00037: reducing learning rate to 3.12500014843e-05.

374s - loss: 0.0252 - acc: 0.9926 - val_loss: 0.0136 - val_acc: 0.9950

Epoch 39/40

372s - loss: 0.0246 - acc: 0.9927 - val_loss: 0.0134 - val_acc: 0.9957

Epoch 40/40

371s - loss: 0.0247 - acc: 0.9929 - val_loss: 0.0139 - val_acc: 0.9950

在训练过程当中，有几次触发学习效率衰减的条件，每当val_acc连续３轮没有增长，就会把学习效率调整为当前的一半，调整之后，val_acc都有明显的增长，但是在最后几轮,模型可能已经收敛．

# learning curves

fig,ax = plt.subplots(2,1,figsize=(10,10))

ax[0].plot(history.history['loss'], color='r', label='Training Loss')

ax[0].plot(history.history['val_loss'], color='g', label='Validation Loss')

ax[0].legend(loc='best',shadow=True)

ax[0].grid(True)

ax[1].plot(history.history['acc'], color='r', label='Training Accuracy')

ax[1].plot(history.history['val_acc'], color='g', label='Validation Accuracy')

ax[1].legend(loc='best',shadow=True)

ax[1].grid(True)

# 混淆矩阵

def plot_sonfusion_matrix(cm, classes, normalize=False, title='Confusion matrix',cmap=plt.cm.Blues):

plt.imshow(cm, interpolation='nearest', cmap=cmap)

plt.title(title)

plt.colorbar()

tick_marks = np.arange(len(classes))

plt.xticks(tick_marks, classes, rotation=45)

plt.yticks(tick_marks, classes)

if normalize:

cm = cm.astype('float')/cm.sum(axis=1)[:,np.newaxis]

thresh = cm.max()/2.0

for i,j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):

plt.text(j,i,cm[i,j], horizontalalignment='center',color='white' if cm[i,j] > thresh else 'black')

plt.tight_layout()

plt.ylabel('True label')

plt.xlabel('Predict label')

验证数据的混淆举证

pred_y = model.predict(val_x)

pred_label = np.argmax(pred_y, axis=1)

true_label = np.argmax(val_y, axis=1)

confusion_mat = confusion_matrix(true_label, pred_label)

plot_sonfusion_matrix(confusion_mat, classes = range(10))

以上就是本文的案例，如果大家对本篇文章技术点一知半解，不能透彻理解，您可能需要从机器学习的基础学起。