当前位置:网站首页>6.Dropout应用
6.Dropout应用
2022-07-07 23:12:00 【booze-J】
一、未使用Dropout的正常情况下
在4.交叉熵的代码的网络模型构建中添加一些隐藏层,并且输出训练集的损失和准确率。
将4.交叉熵中的
# 创建模型 输入784个神经元,输出10个神经元
model = Sequential([
# 定义输出是10 输入是784,设置偏置为1,添加softmax激活函数
Dense(units=10,input_dim=784,bias_initializer='one',activation="softmax"),
])
添加隐藏层修改为:
# 创建模型 输入784个神经元,输出10个神经元
model = Sequential([
# 定义输出是200 输入是784,设置偏置为1,添加softmax激活函数 第一个隐藏层有200个神经元
Dense(units=200,input_dim=784,bias_initializer='one',activation="tanh"),
# 第二个隐藏层有 100个神经元
Dense(units=100,bias_initializer='one',activation="tanh"),
Dense(units=10,bias_initializer='one',activation="softmax")
])
代码运行结果:
对比4.交叉熵的运行结果,可以发现添加更多隐藏层之后,模型测试的准确率大大提高,但是却出现了轻微的过拟合现象。
二、使用Dropout
在模型构建中添加Dropout:
# 创建模型 输入784个神经元,输出10个神经元
model = Sequential([
# 定义输出是200 输入是784,设置偏置为1,添加softmax激活函数 第一个隐藏层有200个神经元
Dense(units=200,input_dim=784,bias_initializer='one',activation="tanh"),
# 让40%的神经元不工作
Dropout(0.4),
# 第二个隐藏层有 100个神经元
Dense(units=100,bias_initializer='one',activation="tanh"),
# 让40%的神经元不工作
Dropout(0.4),
Dense(units=10,bias_initializer='one',activation="softmax")
])
使用Dropout之前需要先导入from keras.layers import Dropout
运行结果:
在这个例子中并不是说使用dropout会得到更好的效果,但是有些情况下,使用dropout是可以得到更好的效果。
但是使用dropout之后,测试准确率和训练准确率还是比较接近的,过拟合现象不是很明显。从训练结果中可以看到,训练过程中的准确率都低于最终模型测试训练集的准确率,这是因为使用dropout之后,每次训练都只是使用部分神经元进行训练,然后模型训练完之后,最后测试的时候,是使用所有神经元进行测试的,所以效果会更好。
完整代码
1.未使用Dropout情况的完整代码
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。
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
from tensorflow.keras.optimizers import SGD
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) -> (60000,784) 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
x_train = x_train.reshape(x_train.shape[0],-1)/255.0
x_test = x_test.reshape(x_test.shape[0],-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
# 创建模型 输入784个神经元,输出10个神经元
model = Sequential([
# 定义输出是200 输入是784,设置偏置为1,添加softmax激活函数 第一个隐藏层有200个神经元
Dense(units=200,input_dim=784,bias_initializer='one',activation="tanh"),
# 第二个隐藏层有 100个神经元
Dense(units=100,bias_initializer='one',activation="tanh"),
Dense(units=10,bias_initializer='one',activation="softmax")
])
# 定义优化器
sgd = SGD(lr=0.2)
# 定义优化器,loss_function,训练过程中计算准确率
model.compile(
optimizer=sgd,
loss="categorical_crossentropy",
metrics=['accuracy']
)
# 训练模型
model.fit(x_train,y_train,batch_size=32,epochs=10)
# 评估模型
# 测试集的loss和准确率
loss,accuracy = model.evaluate(x_test,y_test)
print("\ntest loss",loss)
print("test_accuracy:",accuracy)
# 训练集的loss和准确率
loss,accuracy = model.evaluate(x_train,y_train)
print("\ntrain loss",loss)
print("train_accuracy:",accuracy)
2.使用Dropout的完整代码
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。
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
from tensorflow.keras.optimizers import SGD
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) -> (60000,784) 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
x_train = x_train.reshape(x_train.shape[0],-1)/255.0
x_test = x_test.reshape(x_test.shape[0],-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
# 创建模型 输入784个神经元,输出10个神经元
model = Sequential([
# 定义输出是200 输入是784,设置偏置为1,添加softmax激活函数 第一个隐藏层有200个神经元
Dense(units=200,input_dim=784,bias_initializer='one',activation="tanh"),
# 让40%的神经元不工作
Dropout(0.4),
# 第二个隐藏层有 100个神经元
Dense(units=100,bias_initializer='one',activation="tanh"),
# 让40%的神经元不工作
Dropout(0.4),
Dense(units=10,bias_initializer='one',activation="softmax")
])
# 定义优化器
sgd = SGD(lr=0.2)
# 定义优化器,loss_function,训练过程中计算准确率
model.compile(
optimizer=sgd,
loss="categorical_crossentropy",
metrics=['accuracy']
)
# 训练模型
model.fit(x_train,y_train,batch_size=32,epochs=10)
# 评估模型
# 测试集的loss和准确率
loss,accuracy = model.evaluate(x_test,y_test)
print("\ntest loss",loss)
print("test_accuracy:",accuracy)
# 训练集的loss和准确率
loss,accuracy = model.evaluate(x_train,y_train)
print("\ntrain loss",loss)
print("train_accuracy:",accuracy)
边栏推荐
- 华为交换机S5735S-L24T4S-QA2无法telnet远程访问
- Solution to the problem of unserialize3 in the advanced web area of the attack and defense world
- Interface test advanced interface script use - apipost (pre / post execution script)
- 韦东山第三期课程内容概要
- Course of causality, taught by Jonas Peters, University of Copenhagen
- STL--String类的常用功能复写
- RPA cloud computer, let RPA out of the box with unlimited computing power?
- "An excellent programmer is worth five ordinary programmers", and the gap lies in these seven key points
- 5g NR system messages
- 22年秋招心得
猜你喜欢

国外众测之密码找回漏洞

New library online | cnopendata China Star Hotel data

SDNU_ ACM_ ICPC_ 2022_ Summer_ Practice(1~2)

英雄联盟胜负预测--简易肯德基上校

SDNU_ACM_ICPC_2022_Summer_Practice(1~2)

基于卷积神经网络的恶意软件检测方法

赞!idea 如何单窗口打开多个项目?

新库上线 | CnOpenData中华老字号企业名录

FOFA-攻防挑战记录

QT adds resource files, adds icons for qaction, establishes signal slot functions, and implements
随机推荐
接口测试进阶接口脚本使用—apipost(预/后执行脚本)
13.模型的保存和载入
Basic types of 100 questions for basic grammar of Niuke
LeetCode刷题
【愚公系列】2022年7月 Go教学课程 006-自动推导类型和输入输出
玩轉Sonar
ABAP ALV LVC template
SDNU_ ACM_ ICPC_ 2022_ Summer_ Practice(1~2)
After going to ByteDance, I learned that there are so many test engineers with an annual salary of 40W?
3 years of experience, can't you get 20K for the interview and test post? Such a hole?
What if the testing process is not perfect and the development is not active?
Reentrantlock fair lock source code Chapter 0
Introduction to paddle - using lenet to realize image classification method I in MNIST
jemter分布式
ThinkPHP kernel work order system source code commercial open source version multi user + multi customer service + SMS + email notification
Cause analysis and solution of too laggy page of [test interview questions]
【笔记】常见组合滤波电路
What does interface testing test?
Is it safe to speculate in stocks on mobile phones?
2022-07-07: the original array is a monotonic array with numbers greater than 0 and less than or equal to K. there may be equal numbers in it, and the overall trend is increasing. However, the number