深度学习（二）卷积神经网络CNN

 '''

    
 基于dataset\training_set数据，根据提供的结构，建立CNN模型，识别图片中的猫/狗，计算预测准确率
    
 '''
    
 # 1. load the data
    
 from keras.preprocessing.image import ImageDataGenerator
    
 train_datagen = ImageDataGenerator(rescale=1./255)# 1./255：归一化，图像的灰度值都除以255
    
  
    
 training_set = train_datagen.flow_from_directory('./dataset/training_set',target_size=(50,50),batch_size=32,class_mode='binary') # flow_from_directory 文件路径
    
 # batch_size：每次选32张图片进行反向梯度搜索来求解cnn，size越小，损失函数越不稳定
    
 # class_mode：模式为二分类
    
  
    
 # 2. 确认输入数据标签
    
 training_set.class_indices
    
  
    
 #3. 建立CNN模型 set up the cnn model
    
 from keras.models import Sequential
    
 from keras.layers import Conv2D, MaxPool2D, Flatten, Dense
    
 #创建顺序模型的实例
    
 model = Sequential()
    
 #卷积层
    
 model.add(Conv2D(32,(3,3),input_shape=(50,50,3),activation='relu')) # 32个filters，每个3*3，输入像素为50*50*3通道
    
 #池化层
    
 model.add(MaxPool2D(pool_size=(2,2))) # 默认s=1
    
 #卷积层
    
 model.add(Conv2D(32,(3,3),activation='relu'))
    
 #池化层
    
 model.add(MaxPool2D(pool_size=(2,2)))
    
 #flattening layer
    
 model.add(Flatten()) # 将（m行*n列）转换成（m*n行1列）
    
 #FC layer
    
 model.add(Dense(units=128,activation='relu'))
    
 #输出层
    
 model.add(Dense(units=1,activation='sigmoid'))
    
  
    
 # 4. 配置模型参数 configure the model
    
 model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy']) # 每次训练完后用accuracy进行评估
    
  
    
 # 5. 查看模型每层的结构，及多少参数
    
 model.summary()
    
  
    
 # 6. 训练模型 train the model
    
 model.fit_generator(training_set,epochs=20) # 因为是通过keras中的ImageGenerator生成图像的，所以训练时要用fit_generator
    
  
    
 # 7. 计算训练数据集的准确率，用evaluate_generator方法 accuracy on the training data
    
 accuracy_train = model.evaluate_generator(training_set)
    
 print(accuracy_train)
    
  
    
 # 8. 计算测试数据集的准确率 accuracy on the test data
    
 test_set = train_datagen.flow_from_directory('./dataset/test_set',target_size=(50,50),batch_size=32,class_mode='binary')
    
  
    
 accuracy_test = model.evaluate_generator(test_set)
    
 print(accuracy_test)
    
    
    
    
    AI助手

 '''

    
 从网站下载猫/狗图片，对其进行预测
    
 '''
    
 # 9. 加载单个狗图片，对其进行归一化，维度转换，及预测
    
 from keras.preprocessing.image import load_img, img_to_array
    
 pic_dog = 'dog.jpg'
    
 pic_dog = load_img(pic_dog,target_size=(50,50))
    
 pic_dog = img_to_array(pic_dog)
    
 pic_dog = pic_dog/255
    
 pic_dog = pic_dog.reshape(1,50,50,3)
    
 result = model.predict_classes(pic_dog)
    
 print(result) # 结果为[[1]]
    
  
    
 # 10. 加载单个猫图片，对其进行归一化，维度转换，及预测
    
 pic_cat = 'cat1.jpg'
    
 pic_cat = load_img(pic_cat,target_size=(50,50))
    
 pic_cat = img_to_array(pic_cat)
    
 pic_cat = pic_cat/255
    
 pic_cat = pic_cat.reshape(1,50,50,3)
    
 result = model.predict_classes(pic_cat)
    
 print(result) # 结果为[[0]]
    
  
    
 # 11. 获取类别序列
    
 training_set.class_indices # {'cats': 0, 'dogs': 1}
    
  
    
 # 12. 在多张图中预测其类别 make prediction on multiple images
    
 import matplotlib as mlp
    
 font2 = {'family' : 'SimHei',
    
 'weight' : 'normal',
    
 'size'   : 20,
    
 }
    
 mlp.rcParams['font.family'] = 'SimHei'
    
 mlp.rcParams['axes.unicode_minus'] = False
    
 from matplotlib import pyplot as plt
    
 from matplotlib.image import imread
    
 from keras.preprocessing.image import load_img
    
 from keras.preprocessing.image import img_to_array
    
 from keras.models import load_model
    
 a = [i for i in range(1,10)]
    
 fig = plt.figure(figsize=(10,10))
    
 for i in a:
    
     img_name = str(i)+'.jpg'
    
     img_ori = load_img(img_name, target_size=(50, 50))
    
     img = img_to_array(img_ori)
    
     img = img.astype('float32')/255
    
     img = img.reshape(1,50,50,3)
    
     result = model.predict_classes(img)
    
     img_ori = load_img(img_name, target_size=(250, 250))
    
     plt.subplot(3,3,i)
    
     plt.imshow(img_ori)
    
     plt.title('预测为：狗狗' if result[0][0] == 1 else '预测为：猫咪')
    
 plt.show()
    
    
    
    
    AI助手

 '''

    
 单个图像预处理，使用VGG16结构提取图像特征
    
 '''
    
 # 1. load the data
    
 from keras.preprocessing.image import load_img,img_to_array
    
  
    
 img_path = '1.jpg'
    
 img = load_img(img_path,target_size=(224,224))
    
 img = img_to_array(img)
    
 type(img)
    
  
    
 # 2. 加载VGG-16模型结构
    
 from keras.applications.vgg16 import VGG16
    
 from keras.applications.vgg16 import preprocess_input
    
 import numpy as np
    
 model_vgg = VGG16(weights='imagenet',include_top=False)
    
 x = np.expand_dims(img,axis=0)
    
 x = preprocess_input(x)
    
 print(x.shape)
    
  
    
 # 3. 使用vgg模型提取图像特征
    
 features = model_vgg.predict(x)
    
 print(features.shape)
    
  
    
 #4. 建立全连接层flatten
    
 features = features.reshape(1,7*7*512)
    
 print(features.shape)
    
  
    
 # 5. 可视化数据 visualize the data
    
 %matplotlib inline
    
 from matplotlib import pyplot as plt
    
 fig = plt.figure(figsize=(5,5))
    
 img = load_img(img_path,target_size=(224,224))
    
 plt.imshow(img)
    
    
    
    
    AI助手

 '''

    
 任务1：批量图片预处理，用VGG16的结构提取批量图像特征
    
 '''
    
 # 1. 导入库
    
 from keras.preprocessing.image import img_to_array,load_img
    
 from keras.applications.vgg16 import VGG16
    
 from keras.applications.vgg16 import preprocess_input
    
 import numpy as np
    
  
    
 # 2. 创建vgg16模型实例
    
 model_vgg = VGG16(weights='imagenet', include_top=False)
    
  
    
 # 3. 定义一个图片加载方法 define a method to load and preprocess the image
    
 def modelProcess(img_path,model):
    
     img = load_img(img_path, target_size=(224, 224))
    
     img = img_to_array(img)
    
     x = np.expand_dims(img,axis=0)
    
     x = preprocess_input(x)
    
     x_vgg = model.predict(x)
    
     x_vgg = x_vgg.reshape(1,25088)
    
     return x_vgg
    
  
    
 # 4. 查看指定文件夹包含的文件名列表 list file names of the training datasets
    
 import os
    
 folder = "dataset/data_vgg/cats"
    
 dirs = os.listdir(folder)
    
  
    
 # 5. 生成各个图片路径 generate path for the images
    
 img_path = []
    
 for i in dirs:                             
    
     if os.path.splitext(i)[1] == ".jpg":   
    
     img_path.append(i)
    
 img_path = [folder+"//"+i for i in img_path]
    
  
    
 # 6. 多图像预处理 preprocess multiple images
    
 features1 = np.zeros([len(img_path),25088])
    
 for i in range(len(img_path)):
    
     feature_i = modelProcess(img_path[i],model_vgg)
    
     print('preprocessed:',img_path[i])
    
     features1[i] = feature_i
    
     
    
 folder = "dataset/data_vgg/dogs"
    
 dirs = os.listdir(folder)
    
 img_path = []
    
 for i in dirs:                             
    
     if os.path.splitext(i)[1] == ".jpg":   
    
     img_path.append(i)
    
 img_path = [folder+"//"+i for i in img_path]
    
 features2 = np.zeros([len(img_path),25088])
    
 for i in range(len(img_path)):
    
     feature_i = modelProcess(img_path[i],model_vgg)
    
     print('preprocessed:',img_path[i])
    
     features2[i] = feature_i
    
     
    
 # 7. 结果标签 label the results
    
 print(features1.shape,features2.shape)
    
 y1 = np.zeros(300)
    
 y2 = np.ones(300)
    
  
    
 # 8. 生成训练数据集 generate the training data
    
 X = np.concatenate((features1,features2),axis=0)
    
 y = np.concatenate((y1,y2),axis=0)
    
 y = y.reshape(-1,1)
    
 print(X.shape,y.shape)
    
    
    
    
    AI助手

 '''

    
 任务2：根据任务1提取的图像特征建立MLP模型，对数据进行分离、计算测试数据预测准确率（mlp模型一个隐藏层，10个神经元）
    
 '''
    
 # 1. split the training and test data
    
 from sklearn.model_selection import train_test_split
    
 X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.3,random_state=50)
    
 print(X_train.shape,X_test.shape,X.shape)
    
  
    
 # 2. 建立MLP模型set up the mlp model
    
 from keras.models import Sequential
    
 from keras.layers import Dense
    
 model = Sequential()
    
 model.add(Dense(units=10,activation='relu',input_dim=25088))
    
 model.add(Dense(units=1,activation='sigmoid'))
    
 model.summary()
    
  
    
 # 3. configure the model
    
 model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])
    
  
    
 # 4. train the model
    
 model.fit(X_train,y_train,epochs=50)
    
  
    
 # 5. 计算训练数据集的预测准确率
    
 from sklearn.metrics import accuracy_score
    
 y_train_predict = model.predict_classes(X_train)
    
 accuracy_train = accuracy_score(y_train,y_train_predict)
    
 print(accuracy_train) # 0.98
    
  
    
 # 6. 计算测试数据集的准确率
    
 y_test_predict = model.predict_classes(X_test)
    
 accuracy_test = accuracy_score(y_test,y_test_predict)
    
 print(accuracy_test) # 0.97
    
    
    
    
    AI助手

 '''

    
 任务3：从网站下载猫/狗图片，对其进行预测
    
 '''
    
 # 加载新图片
    
 img_path = 'cat1.jpg'
    
 img = load_img(img_path,target_size=(224,224))
    
 img = img_to_array(img)
    
 x = np.expand_dims(img,axis=0)
    
 x = preprocess_input(x)
    
 features = model_vgg.predict(x)
    
 features = features.reshape(1,7*7*512)
    
 result = model.predict_classes(features)
    
 print(result)
    
  
    
 # coding:utf-8
    
 import matplotlib as mlp
    
 font2 = {'family' : 'SimHei',
    
 'weight' : 'normal',
    
 'size'   : 20,
    
 }
    
 mlp.rcParams['font.family'] = 'SimHei'
    
 mlp.rcParams['axes.unicode_minus'] = False
    
 from matplotlib import pyplot as plt
    
 from matplotlib.image import imread
    
 from keras.preprocessing.image import load_img
    
 from keras.preprocessing.image import img_to_array
    
 from keras.models import load_model
    
 #from cv2 import load_img
    
 a = [i for i in range(1,10)]
    
 fig = plt.figure(figsize=(10,10))
    
 for i in a:
    
     img_name = str(i)+'.jpg'
    
     img_path = img_name
    
     img = load_img(img_path, target_size=(224, 224))
    
     img = img_to_array(img)
    
     x = np.expand_dims(img,axis=0)
    
     x = preprocess_input(x)
    
     x_vgg = model_vgg.predict(x)
    
     x_vgg = x_vgg.reshape(1,25088)
    
     result = model.predict_classes(x_vgg)
    
     img_ori = load_img(img_name, target_size=(250, 250))
    
     plt.subplot(3,3,i)
    
     plt.imshow(img_ori)
    
     plt.title('预测为：狗狗' if result[0][0] == 1 else '预测为：猫咪')
    
 plt.show()
    
    
    
    
    AI助手