当前位置:网站首页>10.CNN应用于手写数字识别
10.CNN应用于手写数字识别
2022-07-07 23:11:00 【booze-J】
代码运行平台为jupyter-notebook,文章中的代码块,也是按照jupyter-notebook中的划分顺序进行书写的,运行文章代码,直接分单元粘入到jupyter-notebook即可。整体代码给出的注释还是挺简单明了的。
1.导入第三方库
import numpy as np
from keras.datasets import mnist
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Dense,Dropout,Convolution2D,MaxPooling2D,Flatten
from tensorflow.keras.optimizers import Adam
2.加载数据及数据预处理
# 载入数据
(x_train,y_train),(x_test,y_test) = mnist.load_data()
# (60000, 28, 28)
print("x_shape:\n",x_train.shape)
# (60000,) 还未进行one-hot编码 需要后面自己操作
print("y_shape:\n",y_train.shape)
# (60000, 28, 28) -> (60000,28,28,1)=(图片数目,图片高度,图片宽度,图片的通道数) reshape()中参数填入-1的话可以自动计算出参数结果 除以255.0是为了归一化
# 归一化很关键哈,可以大大减少计算量
x_train = x_train.reshape(-1,28,28,1)/255.0
x_test = x_test.reshape(-1,28,28,1)/255.0
# 换one hot格式
y_train = np_utils.to_categorical(y_train,num_classes=10)
y_test = np_utils.to_categorical(y_test,num_classes=10)
3.训练模型
# 定义顺序模型
model = Sequential()
# 第一个卷积层 注意第一层要写输入图片的大小 后面的层可以忽略
# input_shape 输入平面
# filters 卷积核/滤波器个数
# kernel_size 卷积窗口大小
# strides 步长
# padding padding方式 same/valid
# activation 激活函数
model.add(Convolution2D(
input_shape=(28,28,1),
filters=32,
kernel_size=5,
strides=1,
padding="same",
activation="relu"
))
# 第一个池化层
model.add(MaxPooling2D(
pool_size=2,
strides=2,
padding="same"
))
# 第二个池化层
model.add(Convolution2D(filters=64,kernel_size=5,strides=1,padding="same",activation="relu"))
# 第二个池化层
model.add(MaxPooling2D(pool_size=2,strides=2,padding="same"))
# 把第二个池化层的输出扁平化为1维
model.add(Flatten())
# 第一个全连接层
model.add(Dense(units=1024,activation="relu"))
# Dropout 随机选用50%神经元进行训练
model.add(Dropout(0.5))
# 第二个全连接层
model.add(Dense(units=10,activation="softmax"))
# 定义优化器 设置学习率为1e-4
adam = Adam(lr=1e-4)
# 定义优化器,loss function,训练过程中计算准确率
model.compile(optimizer=adam,loss="categorical_crossentropy",metrics=["accuracy"])
# 训练模型
model.fit(x_train,y_train,batch_size=64,epochs=10)
# 评估模型
loss,accuracy=model.evaluate(x_test,y_test)
print("test loss:",loss)
print("test accuracy:",accuracy)
代码运行结果:
代码中需要注意的一些点,在代码注释中也给出了解释和提醒。
注意
- 搭建神经网络的第一层要写输入图片的大小 后面的层可以忽略
边栏推荐
- Service mesh introduction, istio overview
- Cascade-LSTM: A Tree-Structured Neural Classifier for Detecting Misinformation Cascades(KDD20)
- 基于微信小程序开发的我最在行的小游戏
- 【obs】Impossible to find entrance point CreateDirect3D11DeviceFromDXGIDevice
- Deep dive kotlin synergy (XXII): flow treatment
- Service Mesh介绍,Istio概述
- C # generics and performance comparison
- AI遮天传 ML-回归分析入门
- 华为交换机S5735S-L24T4S-QA2无法telnet远程访问
- DNS series (I): why does the updated DNS record not take effect?
猜你喜欢
Service Mesh介绍,Istio概述
Qt添加资源文件,为QAction添加图标,建立信号槽函数并实现
QT adds resource files, adds icons for qaction, establishes signal slot functions, and implements
Invalid V-for traversal element style
Course of causality, taught by Jonas Peters, University of Copenhagen
接口测试进阶接口脚本使用—apipost(预/后执行脚本)
新库上线 | CnOpenData中国星级酒店数据
5.过拟合,dropout,正则化
Reentrantlock fair lock source code Chapter 0
How to insert highlighted code blocks in WPS and word
随机推荐
语义分割模型库segmentation_models_pytorch的详细使用介绍
手写一个模拟的ReentrantLock
Basic types of 100 questions for basic grammar of Niuke
股票开户免费办理佣金最低的券商,手机上开户安全吗
AI遮天传 ML-初识决策树
What does interface testing test?
取消select的默认样式的向下箭头和设置select默认字样
NVIDIA Jetson测试安装yolox过程记录
Jemter distributed
51与蓝牙模块通讯,51驱动蓝牙APP点灯
[note] common combined filter circuit
The method of server defense against DDoS, Hangzhou advanced anti DDoS IP section 103.219.39 x
Qt不同类之间建立信号槽,并传递参数
Deep dive kotlin synergy (XXII): flow treatment
Where is the big data open source project, one-stop fully automated full life cycle operation and maintenance steward Chengying (background)?
51 communicates with the Bluetooth module, and 51 drives the Bluetooth app to light up
A network composed of three convolution layers completes the image classification task of cifar10 data set
New library online | information data of Chinese journalists
Qt添加资源文件,为QAction添加图标,建立信号槽函数并实现
3 years of experience, can't you get 20K for the interview and test post? Such a hole?