Python | 使用Keras实现秃头识别

一、选题的背景

如今脱发已经成为了热门话题，在朋友圈、微博等社交平台经常看到年轻人们的哀嚎：身上全是头发，地上全是头发，大风一吹空中可以飘着头发，唯独自己的头上没有头发。一颗心还在红尘，头发却已迫不及待的“出家”。人们每天都对着自己日益发亮的头顶担忧不已，头发已经成为了人们心中地地道道“烦恼丝”。所以，研究自己的头发已成现代年轻人的当务之急，我的选题背景也就随之而来。

二、机器学习案例设计方案

1.本次选题采用机器学习Bald Classification Dataset的数据集

据介绍，Bald Classification Dataset（秃头数据集）由 Ashish Jangra 于今年 5 月发布。

数据集中包含 20 万张光头人像的图像，分为测试集、训练集、验证集三个文件夹，每个文件夹也包括 Bald 和 NotBald 两种图像。

其中秃头人像数据集的来源，主要是欧美公众人物，包含政商界、娱乐圈、体育界人士。

Bald Classification Dataset

发布人员： Ashish Jangra

包含数量：20 万张秃头人像

数据格式：JPG

数据大小：1.3 G

发布时间：2020 年 5 月

下载地址：https://hyper.ai/datasets/12385

数据集作者：发量惊人的印度小哥

发布者 Ashish Jangra 也是个停不下来的人。他是一位 95 后，2016 年开始就读于 Lovely Professional University（印度拉夫里科技大学)的计算机专业。

2.采用的机器学习框架描述

本项目使用的卷积神经网络(Convolutional Neural Network, CNN)，卷积神经网络是深度学习技术中极具代表的网络结构之一， 在图像处理领域取得了很大的成功。

本项目的扩展可以使用Keras搭建部署一个简单易用的深度学习图像网页应用， 可以通过网页导入图片判断改图片任务是否秃头。

3.涉及到的技术难点与解决思路

首先，数据集作业处理的图片尺寸都是178*218，当要验证自己所导入的图片时要注意尺寸问题。此外由于带着帽子的图片会难以判断是否图片，这个问题暂没有很好的处理方式，只能在测试时尽量毕竟带着帽子的图片进行测试

三、机器学习实现步骤

#查看训练集和验证集中各有多少图片

　　

 1 import os
 2 train_path="work/Dataset/Train/"
 3 print(\'total training bald images:\', len(os.listdir(train_path+"Bald")))
 4 print(\'total training notbald images:\', len(os.listdir(train_path+"NotBald")))
 5 valid_path="work/Dataset/validation/"
 6 print(\'total validation bald images:\', len(os.listdir(valid_path+"Bald")))
 7 print(\'total validation notbald images:\', len(os.listdir(valid_path+"NotBald")))
 8 
 9 test_path="work/Dataset/Test/"
10 print(\'total test images:\', len(os.listdir(test_path)))

 

 

 

 

 #数据增强

 

 1 import keras
 2 
 3 from keras.preprocessing.image import ImageDataGenerator
 4 
 5 IMSIZE=224
 6 
 7 train_generator = ImageDataGenerator(
 8 
 9 rescale=1./255, #设置放缩因子为1/255，把像素值放缩到0和1之间
10 
11 shear_range=0.5, #拉伸变换
12 
13 rotation_range=30, #左右旋转
14 
15 zoom_range=0.2, #放大或缩小的比例
16 
17 width_shift_range=0.2, #水平方向上平移的尺度
18 
19 height_shift_range=0.2, #垂直方向上平移的尺度
20 
21 horizontal_flip=True).flow_from_directory(
22 
23 \'work/Dataset/Train/\',
24 
25 target_size=(IMSIZE, IMSIZE),
26 
27 batch_size=100,
28 
29 class_mode= \'categorical\')

 

 

#建立模型 

 

 1 from keras import layers
 2 from keras import models
 3 model = models.Sequential()
 4 model.add(layers.Conv2D(32,(3,3),activation = \'relu\',input_shape = (IMSIZE,IMSIZE,3)))
 5 model.add(layers.MaxPooling2D((2,2)))
 6 model.add(layers.Conv2D(64,(3,3),activation = \'relu\'))
 7 model.add(layers.MaxPooling2D((2,2)))
 8 model.add(layers.Conv2D(128,(3,3),activation = \'relu\'))
 9 model.add(layers.MaxPooling2D((2,2)))
10 model.add(layers.Conv2D(128,(3,3),activation = \'relu\'))
11 model.add(layers.MaxPooling2D((2,2)))
12 model.add(layers.Flatten())
13 model.add(layers.Dense(512,activation = \'relu\'))
14 model.add(layers.Dense(1,activation = \'sigmoid\'))

 

 

#查询记录

 

1 model.summary()

 

 

 

 #设置优化器，损失函数，准确率评判标准

 

1 from keras.optimizers import Adam
2 model.compile(loss=\'binary_crossentropy\',
3 optimizer=Adam(lr=0.001),
4 metrics=[\'accuracy\'])

 

#归一化图片，设置生成器，修改输入的训练集，验证集的图片的尺寸，并输出图片尺寸

 

 1 from keras.preprocessing.image import ImageDataGenerator
 2 train_datagen = ImageDataGenerator(rescale = 1./255)
 3 test_datagen = ImageDataGenerator(rescale = 1./255)
 4 train_dir = \'work/Dataset/Train\'   
 5 train_generator = train_datagen.flow_from_directory(
 6     train_dir,
 7     target_size = (IMSIZE,IMSIZE),
 8     batch_size = 20,
 9     class_mode = \'binary\')  
10 validation_dir = \'work/Dataset/Validation\'  
11 validation_generator = test_datagen.flow_from_directory(
12     validation_dir,
13     target_size = (IMSIZE,IMSIZE),
14     batch_size = 20,
15     class_mode = \'binary\')
16 for data_batch,labels_batch in train_generator:
17     print(\'data batch shape:\',data_batch.shape)
18     print(\'data batch shape:\',labels_batch.shape)
19     break 

 

 

 

 

 

#开始模型训练

 

1 history = model.fit_generator(train_generator,
2 steps_per_epoch = 100,
3 epochs = 20,
4 validation_data = validation_generator,
5 validation_steps = 50)
6 model.save(\'bald.h5\')

 

 

 

 训练集上准确率到达了98.41%，基本符合我的要求，开始验证

#处理图片尺寸，处理好后并进行显示

 

 1 import matplotlib.pyplot as plt
 2 from PIL import Image
 3 import os.path
 4 
 5 def convertjpg(jpgfile,outdir,width=IMSIZE,height=IMSIZE):
 6 img=Image.open(jpgfile)
 7 try:
 8 new_img=img.resize((width,height),Image.BILINEAR)
 9 new_img.save(os.path.join(outdir,os.path.basename(jpgfile)))
10 except Exception as e:
11 print(e)
12 
13 jpgfile = \'work/Dataset/data/a.jpg\'
14 convertjpg(jpgfile,"work/Dataset")
15 img_scale = plt.imread(\'work/Dataset/a.jpg\')
16 print(img_scale.shape)
17 plt.imshow(img_scale)

 

 

 

 

 图片尺寸已经修改为224*224

#开始验证

 

 1 from keras.models import load_model
 2 model = load_model(\'bald.h5\')
 3 img_scale = img_scale.reshape(1,IMSIZE,IMSIZE,3).astype(\'float32\')
 4 img_scale = img_scale/255
 5 result = model.predict(img_scale)
 6 print(result)
 7 if result>0.8:
 8 print(\'该图片人物秃头\')
 9 else:
10 print(\'该图片人物不秃头\')

 

 

 

 #接下来验证一下有头发的图片

 #修改尺寸并显示

 

 1 import matplotlib.pyplot as plt
 2 from PIL import Image
 3 import os.path
 4 
 5 def convertjpg(jpgfile1,outdir,width=IMSIZE,height=IMSIZE):
 6 img=Image.open(jpgfile1)
 7 try:
 8 new_img=img.resize((width,height),Image.BILINEAR)
 9 new_img.save(os.path.join(outdir,os.path.basename(jpgfile1)))
10 except Exception as e:
11 print(e)
12 
13 jpgfile1 = \'work/Dataset/data/b.jpg\'
14 convertjpg(jpgfile1,"work/Dataset")
15 img_scale1 = plt.imread(\'work/Dataset/b.jpg\')
16 print(img_scale1.shape)
17 plt.imshow(img_scale1)
18 
19 import matplotlib.pyplot as plt
20 from PIL import Image
21 import os.path
22 
23 def convertjpg(jpgfile1,outdir,width=IMSIZE,height=IMSIZE):
24 img=Image.open(jpgfile1)
25 try:
26 new_img=img.resize((width,height),Image.BILINEAR)
27 new_img.save(os.path.join(outdir,os.path.basename(jpgfile1)))
28 except Exception as e:
29 print(e)
30 
31 jpgfile1 = \'work/Dataset/data/b.jpg\'
32 convertjpg(jpgfile1,"work/Dataset")
33 img_scale1 = plt.imread(\'work/Dataset/b.jpg\')
34 print(img_scale1.shape)
35 plt.imshow(img_scale1)

 

 

 

 #验证

 

 1 from keras.models import load_model
 2 model = load_model(\'bald.h5\')
 3 img_scale1 = img_scale1.reshape(1,IMSIZE,IMSIZE,3).astype(\'float32\')
 4 img_scale1 = img_scale1/255 
 5 result1 = model.predict(img_scale1) 
 6 print(result1)
 7 if result1>0.8:
 8 print(\'该图片人物秃头\')
 9 else:
10 print(\'该图片人物不秃头\')

 

 

 

 #代码汇总

  1 import os
  2 train_path="work/Dataset/Train/"
  3 print(\'total training bald images:\', len(os.listdir(train_path+"Bald")))
  4 print(\'total training notbald images:\', len(os.listdir(train_path+"NotBald")))
  5 valid_path="work/Dataset/validation/"
  6 print(\'total validation bald images:\', len(os.listdir(valid_path+"Bald")))
  7 print(\'total validation notbald images:\', len(os.listdir(valid_path+"NotBald")))
  8 
  9 test_path="work/Dataset/Test/"
 10 print(\'total test images:\', len(os.listdir(test_path)))
 11 
 12 import keras
 13 
 14 from keras.preprocessing.image import ImageDataGenerator
 15 
 16 IMSIZE=224
 17 
 18 train_generator = ImageDataGenerator(
 19 
 20 rescale=1./255, #设置放缩因子为1/255，把像素值放缩到0和1之间
 21 
 22 shear_range=0.5, #拉伸变换
 23 
 24 rotation_range=30, #左右旋转
 25 
 26 zoom_range=0.2, #放大或缩小的比例
 27 
 28 width_shift_range=0.2, #水平方向上平移的尺度
 29 
 30 height_shift_range=0.2, #垂直方向上平移的尺度
 31 
 32 horizontal_flip=True).flow_from_directory(
 33 
 34 \'work/Dataset/Train/\',
 35 
 36 target_size=(IMSIZE, IMSIZE),
 37 
 38 batch_size=100,
 39 
 40 class_mode= \'categorical\')
 41 
 42 model.summary()
 43 
 44 from keras.optimizers import Adam
 45 model.compile(loss=\'binary_crossentropy\',
 46               optimizer=Adam(lr=0.001),
 47               metrics=[\'accuracy\'])
 48 
 49 from keras.preprocessing.image import ImageDataGenerator
 50 train_datagen = ImageDataGenerator(rescale = 1./255)
 51 test_datagen = ImageDataGenerator(rescale = 1./255)
 52 train_dir = \'work/Dataset/Train\'   
 53 train_generator = train_datagen.flow_from_directory(
 54     train_dir,
 55     target_size = (IMSIZE,IMSIZE),
 56     batch_size = 20,
 57     class_mode = \'binary\')  
 58 validation_dir = \'work/Dataset/Validation\'  
 59 validation_generator = test_datagen.flow_from_directory(
 60     validation_dir,
 61     target_size = (IMSIZE,IMSIZE),
 62     batch_size = 20,
 63     class_mode = \'binary\')
 64 for data_batch,labels_batch in train_generator:
 65     print(\'data batch shape:\',data_batch.shape)
 66     print(\'data batch shape:\',labels_batch.shape)
 67     break 
 68 
 69 history = model.fit_generator(train_generator,
 70                               steps_per_epoch = 100,
 71                               epochs = 20,
 72                               validation_data = validation_generator,
 73                               validation_steps = 50)
 74 model.save(\'bald.h5\')
 75 
 76 import matplotlib.pyplot as plt
 77 from PIL import Image
 78 import os.path
 79 
 80 def convertjpg(jpgfile,outdir,width=IMSIZE,height=IMSIZE):
 81     img=Image.open(jpgfile)
 82     try:
 83         new_img=img.resize((width,height),Image.BILINEAR)   
 84         new_img.save(os.path.join(outdir,os.path.basename(jpgfile)))
 85     except Exception as e:
 86         print(e)
 87         
 88 jpgfile = \'work/Dataset/data/a.jpg\'
 89 convertjpg(jpgfile,"work/Dataset")
 90 img_scale = plt.imread(\'work/Dataset/a.jpg\')
 91 print(img_scale.shape)
 92 plt.imshow(img_scale) 
 93 
 94 from keras.models import load_model
 95 model = load_model(\'bald.h5\')
 96 img_scale = img_scale.reshape(1,IMSIZE,IMSIZE,3).astype(\'float32\')
 97 img_scale = img_scale/255        
 98 result = model.predict(img_scale) 
 99 print(result)
100 if result>0.8:
101     print(\'该图片人物秃头\')
102 else:
103     print(\'该图片人物不秃头\')
104 
105 import matplotlib.pyplot as plt
106 from PIL import Image
107 import os.path
108 
109 def convertjpg(jpgfile1,outdir,width=IMSIZE,height=IMSIZE):
110     img=Image.open(jpgfile1)
111     try:
112         new_img=img.resize((width,height),Image.BILINEAR)   
113         new_img.save(os.path.join(outdir,os.path.basename(jpgfile1)))
114     except Exception as e:
115         print(e)
116         
117 jpgfile1 = \'work/Dataset/data/b.jpg\'
118 convertjpg(jpgfile1,"work/Dataset")
119 img_scale1 = plt.imread(\'work/Dataset/b.jpg\')
120 print(img_scale1.shape)
121 plt.imshow(img_scale1) 
122 
123 from keras.models import load_model
124 model = load_model(\'bald.h5\')
125 img_scale1 = img_scale1.reshape(1,IMSIZE,IMSIZE,3).astype(\'float32\')
126 img_scale1 = img_scale1/255        #归一化到0-1之间
127 result1 = model.predict(img_scale1) #取图片信息
128 print(result1)
129 if result1>0.8:
130     print(\'该图片人物秃头\')
131 else:
132     print(\'该图片人物不秃头\')

 

四、总结：

          通过本次机器学习过程实现，巩固了之前学习的知识，也对机器学习有了更深层次的理解。本次案例是为了实现对秃头的识别，总体来说，功能较为简易，但是也让我体会到了Python功能的强大。案例使用Keras架构，最终实现对秃头图片的识别。本次机器学习案例使我受益匪浅！！！