机器学习(二)深度学习实战-使用Kera预测人物年龄问题描述引入所需要模块加载数据集创建模型编译模型优化optimize1 使用卷积神经网络optimize2 增加神经网络的层数输出结果结果
问题描述
我们的任务是从一个人的面部特征来预测他的年龄(用“Young”“Middle ”“Old”表示),我们训练的数据集大约有19906多张照片及其每张图片对应的年龄(全是阿三的头像。。。),测试集有6636张图片,首先我们加载数据集,然后我们通过深度学习框架Keras建立、编译、训练模型,预测出6636张人物头像对应的年龄
引入所需要模块
import os
import random
import pandas as pd
import numpy as np
from PIL import Image
加载数据集
root_dir=os.path.abspath('E:/data/age')
train=pd.read_csv(os.path.join(root_dir,'train.csv'))
test=pd.read_csv(os.path.join(root_dir,'test.csv'))
print(train.head())
print(test.head())
ID Class
0 377.jpg MIDDLE
1 17814.jpg YOUNG
2 21283.jpg MIDDLE
3 16496.jpg YOUNG
4 4487.jpg MIDDLE
ID
0 25321.jpg
1 989.jpg
2 19277.jpg
3 13093.jpg
4 5367.jpg
随机读取一张图片试下(☺)
i=random.choice(train.index)
img_name=train.ID[i]
print(img_name)
img=Image.open(os.path.join(root_dir,'Train',img_name))
img.show()
print(train.Class[i])
20188.jpg
MIDDLE
难点
我们随机打开几张图片之后,可以发现图片之间的差别比较大。大家感受下:
- 质量好的图片:
- Middle:
**Middle**
- Young:
**Young**
- Old:
**Old**
- 质量差的:
- Middle:
**Middle**
下面是我们需要面临的问题:
- 图片的尺寸差别:有的图片的尺寸是66x46,而另一张图片尺寸为102x87
- 人物面貌角度不同:
- 侧脸:
- 正脸:
- 图片质量不一(直接上图):
插图
- 亮度和对比度的差异
亮度
对比度 现在,我们只专注下图片尺寸处理,将每一张图片尺寸重置为32x32
格式化图片尺寸和将图片转换成numpy数组
temp=[]
for img_name in train.ID:
img_path=os.path.join(root_dir,'Train',img_name)
img=Image.open(img_path)
img=img.resize((32,32))
array=np.array(img)
temp.append(array.astype('float32'))
train_x=np.stack(temp)
print(train_x.shape)
print(train_x.ndim)
(19906, 32, 32, 3)
4
temp=[]
for img_name in test.ID:
img_path=os.path.join(root_dir,'Test',img_name)
img=Image.open(img_path)
img=img.resize((32,32))
array=np.array(img)
temp.append(array.astype('float32'))
test_x=np.stack(temp)
print(test_x.shape)
(6636, 32, 32, 3)
另外我们再归一化图像,这样会使模型训练的更快
train_x = train_x / 255.
test_x = test_x / 255.
我们看下图片年龄大致分布
train.Class.value_counts(normalize=True)
MIDDLE 0.542751
YOUNG 0.336883
OLD 0.120366
Name: Class, dtype: float64
test['Class'] = 'MIDDLE'
test.to_csv('sub01.csv', index=False)
将目标变量处理虚拟列,能够使模型更容易接受识别它
import keras
from sklearn.preprocessing import LabelEncoder
lb=LabelEncoder()
train_y=lb.fit_transform(train.Class)
print(train_y)
train_y=keras.utils.np_utils.to_categorical(train_y)
print(train_y)
print(train_y.shape)
[0 2 0 ..., 0 0 0]
[[ 1. 0. 0.]
[ 0. 0. 1.]
[ 1. 0. 0.]
...,
[ 1. 0. 0.]
[ 1. 0. 0.]
[ 1. 0. 0.]]
(19906, 3)
创建模型
#构建神经网络
input_num_units=(32,32,3)
hidden_num_units=500
output_num_units=3
epochs=5
batch_size=128
from keras.models import Sequential
from keras.layers import Dense,Flatten,InputLayer
model=Sequential({
InputLayer(input_shape=input_num_units),
Flatten(),
Dense(units=hidden_num_units,activation='relu'),
Dense(input_shape=(32,32,3),units=output_num_units,activation='softmax')
})
model.summary()
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_23 (InputLayer) (None, 32, 32, 3) 0
_________________________________________________________________
flatten_23 (Flatten) (None, 3072) 0
_________________________________________________________________
dense_45 (Dense) (None, 500) 1536500
_________________________________________________________________
dense_46 (Dense) (None, 3) 1503
=================================================================
Total params: 1,538,003
Trainable params: 1,538,003
Non-trainable params: 0
_________________________________________________________________
编译模型
# model.compile(optimizer='sgd',loss='categorical_crossentropy',metrics=['accuracy'])
model.compile(optimizer='sgd',loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(train_x,train_y,batch_size=batch_size,epochs=epochs,verbose=1)
Epoch 1/5
19906/19906 [==============================] - 4s - loss: 0.8878 - acc: 0.5809
Epoch 2/5
19906/19906 [==============================] - 4s - loss: 0.8420 - acc: 0.6077
Epoch 3/5
19906/19906 [==============================] - 4s - loss: 0.8210 - acc: 0.6214
Epoch 4/5
19906/19906 [==============================] - 4s - loss: 0.8149 - acc: 0.6194
Epoch 5/5
19906/19906 [==============================] - 4s - loss: 0.8042 - acc: 0.6305
<keras.callbacks.History at 0x1d3803e6278>
model.fit(train_x, train_y, batch_size=batch_size,epochs=epochs,verbose=1, validation_split=0.2)
Train on 15924 samples, validate on 3982 samples
Epoch 1/5
15924/15924 [==============================] - 3s - loss: 0.7970 - acc: 0.6375 - val_loss: 0.7854 - val_acc: 0.6396
Epoch 2/5
15924/15924 [==============================] - 3s - loss: 0.7919 - acc: 0.6378 - val_loss: 0.7767 - val_acc: 0.6519
Epoch 3/5
15924/15924 [==============================] - 3s - loss: 0.7870 - acc: 0.6404 - val_loss: 0.7754 - val_acc: 0.6534
Epoch 4/5
15924/15924 [==============================] - 3s - loss: 0.7806 - acc: 0.6439 - val_loss: 0.7715 - val_acc: 0.6524
Epoch 5/5
15924/15924 [==============================] - 3s - loss: 0.7755 - acc: 0.6519 - val_loss: 0.7970 - val_acc: 0.6346
<keras.callbacks.History at 0x1d3800a4eb8>
优化
我们使用最基本的模型来处理这个年龄预测结果,并且最终的预测结果为0.6375。接下来,从以下角度尝试优化:
- 使用更好的神经网络模型
- 增加训练次数
- 将图片进行灰度处理(因为对于本问题而言,图片颜色不是一个特别重要的特征。)
optimize1 使用卷积神经网络
添加卷积层之后,预测准确率有所上涨,从6.3到6.7;最开始epochs轮数是5,训练轮数增加到10,此时准确率为6.87;然后将训练轮数增加到20,结果没有发生变化。
Conv2D层
keras.layers.convolutional.Conv2D(filters, kernel_size, strides=(1, 1), padding='valid', data_format=None, dilation_rate=(1, 1), activation=None, use_bias=True, kernel_initializer='glorot_uniform', bias_initializer='zeros', kernel_regularizer=None, bias_regularizer=None, activity_regularizer=None, kernel_constraint=None, bias_constraint=None)
- filters:输出的维度
- strides:卷积的步长
更多关于Conv2D的介绍请看Keras文档Conv2D层
#参数初始化
filters=10
filtersize=(5,5)
epochs =10
batchsize=128
input_shape=(32,32,3)
from keras.models import Sequential
model = Sequential()
model.add(keras.layers.InputLayer(input_shape=input_shape))
model.add(keras.layers.convolutional.Conv2D(filters, filtersize, strides=(1, 1), padding='valid', data_format="channels_last", activation='relu'))
model.add(keras.layers.MaxPooling2D(pool_size=(2, 2)))
model.add(keras.layers.Flatten())
model.add(keras.layers.Dense(units=3, input_dim=50,activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(train_x, train_y, epochs=epochs, batch_size=batchsize,validation_split=0.3)
model.summary()
Train on 13934 samples, validate on 5972 samples
Epoch 1/10
13934/13934 [==============================] - 9s - loss: 0.8986 - acc: 0.5884 - val_loss: 0.8352 - val_acc: 0.6271
Epoch 2/10
13934/13934 [==============================] - 9s - loss: 0.8141 - acc: 0.6281 - val_loss: 0.7886 - val_acc: 0.6474
Epoch 3/10
13934/13934 [==============================] - 9s - loss: 0.7788 - acc: 0.6504 - val_loss: 0.7706 - val_acc: 0.6551
Epoch 4/10
13934/13934 [==============================] - 9s - loss: 0.7638 - acc: 0.6577 - val_loss: 0.7559 - val_acc: 0.6626
Epoch 5/10
13934/13934 [==============================] - 9s - loss: 0.7484 - acc: 0.6679 - val_loss: 0.7457 - val_acc: 0.6710
Epoch 6/10
13934/13934 [==============================] - 9s - loss: 0.7346 - acc: 0.6723 - val_loss: 0.7490 - val_acc: 0.6780
Epoch 7/10
13934/13934 [==============================] - 9s - loss: 0.7217 - acc: 0.6804 - val_loss: 0.7298 - val_acc: 0.6795
Epoch 8/10
13934/13934 [==============================] - 9s - loss: 0.7162 - acc: 0.6826 - val_loss: 0.7248 - val_acc: 0.6792
Epoch 9/10
13934/13934 [==============================] - 9s - loss: 0.7082 - acc: 0.6892 - val_loss: 0.7202 - val_acc: 0.6890
Epoch 10/10
13934/13934 [==============================] - 9s - loss: 0.7001 - acc: 0.6940 - val_loss: 0.7226 - val_acc: 0.6885
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_6 (InputLayer) (None, 32, 32, 3) 0
_________________________________________________________________
conv2d_6 (Conv2D) (None, 28, 28, 10) 760
_________________________________________________________________
max_pooling2d_6 (MaxPooling2 (None, 14, 14, 10) 0
_________________________________________________________________
flatten_6 (Flatten) (None, 1960) 0
_________________________________________________________________
dense_6 (Dense) (None, 3) 5883
=================================================================
Total params: 6,643
Trainable params: 6,643
Non-trainable params: 0
_________________________________________________________________
optimize2 增加神经网络的层数
我们在模型中多添加几层并且提高卷几层的输出维度,这次结果得到显著提升:0.750904
#参数初始化
filters1=50
filters2=100
filters3=100
filtersize=(5,5)
epochs =10
batchsize=128
input_shape=(32,32,3)
from keras.models import Sequential
model = Sequential()
model.add(keras.layers.InputLayer(input_shape=input_shape))
model.add(keras.layers.convolutional.Conv2D(filters1, filtersize, strides=(1, 1), padding='valid', data_format="channels_last", activation='relu'))
model.add(keras.layers.MaxPooling2D(pool_size=(2, 2)))
model.add(keras.layers.convolutional.Conv2D(filters2, filtersize, strides=(1, 1), padding='valid', data_format="channels_last", activation='relu'))
model.add(keras.layers.MaxPooling2D(pool_size=(2, 2)))
model.add(keras.layers.convolutional.Conv2D(filters3, filtersize, strides=(1, 1), padding='valid', data_format="channels_last", activation='relu'))
model.add(keras.layers.Flatten())
model.add(keras.layers.Dense(units=3, input_dim=50,activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(train_x, train_y, epochs=epochs, batch_size=batchsize,validation_split=0.3)
model.summary()
Train on 13934 samples, validate on 5972 samples
Epoch 1/10
13934/13934 [==============================] - 44s - loss: 0.8613 - acc: 0.5985 - val_loss: 0.7778 - val_acc: 0.6586
Epoch 2/10
13934/13934 [==============================] - 44s - loss: 0.7493 - acc: 0.6697 - val_loss: 0.7545 - val_acc: 0.6808
Epoch 3/10
13934/13934 [==============================] - 43s - loss: 0.7079 - acc: 0.6877 - val_loss: 0.7150 - val_acc: 0.6947
Epoch 4/10
13934/13934 [==============================] - 43s - loss: 0.6694 - acc: 0.7061 - val_loss: 0.6496 - val_acc: 0.7261
Epoch 5/10
13934/13934 [==============================] - 43s - loss: 0.6274 - acc: 0.7295 - val_loss: 0.6683 - val_acc: 0.7125
Epoch 6/10
13934/13934 [==============================] - 43s - loss: 0.5950 - acc: 0.7462 - val_loss: 0.6194 - val_acc: 0.7400
Epoch 7/10
13934/13934 [==============================] - 43s - loss: 0.5562 - acc: 0.7655 - val_loss: 0.5981 - val_acc: 0.7465
Epoch 8/10
13934/13934 [==============================] - 43s - loss: 0.5165 - acc: 0.7852 - val_loss: 0.6458 - val_acc: 0.7354
Epoch 9/10
13934/13934 [==============================] - 46s - loss: 0.4826 - acc: 0.7986 - val_loss: 0.6206 - val_acc: 0.7467
Epoch 10/10
13934/13934 [==============================] - 45s - loss: 0.4530 - acc: 0.8130 - val_loss: 0.5984 - val_acc: 0.7569
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_15 (InputLayer) (None, 32, 32, 3) 0
_________________________________________________________________
conv2d_31 (Conv2D) (None, 28, 28, 50) 3800
_________________________________________________________________
max_pooling2d_23 (MaxPooling (None, 14, 14, 50) 0
_________________________________________________________________
conv2d_32 (Conv2D) (None, 10, 10, 100) 125100
_________________________________________________________________
max_pooling2d_24 (MaxPooling (None, 5, 5, 100) 0
_________________________________________________________________
conv2d_33 (Conv2D) (None, 1, 1, 100) 250100
_________________________________________________________________
flatten_15 (Flatten) (None, 100) 0
_________________________________________________________________
dense_7 (Dense) (None, 3) 303
=================================================================
Total params: 379,303
Trainable params: 379,303
Non-trainable params: 0
_________________________________________________________________
输出结果
pred=model.predict_classes(test_x)
pred=lb.inverse_transform(pred)
print(pred)
test['Class']=pred
test.to_csv('sub02.csv',index=False)
6636/6636 [==============================] - 7s
['MIDDLE' 'YOUNG' 'MIDDLE' ..., 'MIDDLE' 'MIDDLE' 'YOUNG']
i = random.choice(train.index)
img_name = train.ID[i]
img=Image.open(os.path.join(root_dir,'Train',img_name))
img.show()
pred = model.predict_classes(train_x)
print('Original:', train.Class[i], 'Predicted:', lb.inverse_transform(pred[i]))
19872/19906 [============================>.] - ETA: 0sOriginal: MIDDLE Predicted: MIDDLE
结果
image.png
还可以优化,继续探讨
- Linux下用户及用户权限管理
- Oracle数据库项目——MC服务器管理系统
- ASP.NET MVC项目开发笔记
- .NET Core 实战笔记3 ASP.NET Core
- HTML页面中的lang属性
- JSP Cheat Sheet - JavaWeb基础学习速查表
- 把网站改成APP吧-Xamarin WebView
- 数据库E-R模型关系图
- 修改Visual Studio类模板添加版权注释信息
- Oracle 11g 安装教程
- ASP.NET MVC学习笔记07数据表和模型添加新字段
- 以太坊·电影院场景区块链应用探索
- 最全爬虫攻略:微博、APP、公众号一个不能少!
- 注册中心 Eureka 源码解析 —— Eureka-Client 初始化(一)之 EurekaInstanceConfig
- JavaScript 教程
- JavaScript 编辑工具
- JavaScript 与HTML
- JavaScript 与Java
- JavaScript 数据结构
- JavaScript 基本数据类型
- JavaScript 特殊数据类型
- JavaScript 运算符
- JavaScript typeof 运算符
- JavaScript 表达式
- JavaScript 类型转换
- JavaScript 基本语法
- JavaScript 注释
- Javascript 基本处理流程
- Javascript 选择结构
- Javascript if 语句
- Javascript if 语句的嵌套
- Javascript switch 语句
- Javascript 循环结构
- Javascript 循环结构实例
- Javascript 跳转语句
- Javascript 控制语句总结
- Javascript 函数介绍
- Javascript 函数的定义
- Javascript 函数调用
- Javascript 几种特殊的函数
- JavaScript 内置函数简介
- Javascript eval() 函数
- Javascript isFinite() 函数
- Javascript isNaN() 函数
- parseInt() 与 parseFloat()
- escape() 与 unescape()
- Javascript 字符串介绍
- Javascript length属性
- javascript 字符串函数
- Javascript 日期对象简介
- Javascript 日期对象用途
- Date 对象属性和方法
- Javascript 数组是什么
- Javascript 创建数组
- Javascript 数组赋值与取值
- Javascript 数组属性和方法
- Java——泛型基本总结(通配符、泛型接口、泛型方法)
- Java——类图、时序图、用例图
- Java——四种访问控制权限及Java命名规范
- Java——static关键字总结(含义、定义属性或方法、使用时机)
- Java——try catch finally异常的捕获及处理逻辑实例详解大全
- Java——String类使用详解(实例化、字符串比较、匿名对象、两种实例化方法的区别)
- Java——数组的定义与使用(基本概念、引用分析、初始化方式、二维数组、对象数组)
- Java——单例设计模式
- Java——包的定义及使用
- Java——Object类(基本概念、toString()方法、equals()方法、可以接收所有引用类型)
- JavaWeb——MyBatis框架之对数据库的增删改查操作CRUD实践及MyBatis参数的深入详解
- JavaWeb——MyBatis框架之入门总结及案例实战,常见坑处理:Failed to execute goal org.codehaus.mojo:exec-maven-plugin:3.0.0
- JavaWeb——MyBatis框架之执行过程原理与解析(通过自定义MyBatis查询所有操作的实现来观察整个过程)
- Java——抽象类(基本概念、使用原则、模板设计模式)
- Java——覆写(概念、覆写的意义、覆写的要求)