卷积神经网络

简介

卷积神经网络

专有名词释义

卷积层， 使用算子对图像进行卷积，感觉是对图像信息的一种压缩。

池化层， 分块提取信息

padding， 防止卷积的时候信息丢失

全连接层，图像信息都对对接

经典CNN模型

1. 参考经典的CNN结构搭建新模型
2. 使用经典的CNN模型结构对图像预处理，再建立MLP模型

经典的CNN模型

LeNet-5
AlexNet
VGG

VGG-16

输入图像 227$times\(227\)times$3 RGB图，3个通道
训练参数 约138000000个
特点：

1. 所有卷积层filter宽和高都是3，步长为1，padding都使用same convolution；
2. 所有池化层的filter宽和高都是2，步长都是2；
3. 相比alexnet，有更多的filter用于提取轮廓信息，具有更高的准确性。

快速基于大佬已经训练好的CNN模型，构建自己的模型

1. 加载经典的CNN模型，剥离其FC层，对图像进行预处理
2. 把预处理完成的数据作为输入，分类结果为输出，建立一个mlp模型
3. 模型训练

参考链接

https://github.com/samuelzhoudev/machinelearningNotebook/tree/2db57a03293b6a2aa81c15d005984d8143fb5b3c

code

# load the data
from tensorflow.keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(rescale=1./255) # 像素归一化
training_set = train_datagen.flow_from_directory('./train1',target_size=(50,50),batch_size=32, class_mode='binary')

# set up the cnn model
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPool2D, Flatten,Dense
model = Sequential()
# 卷积层
model.add(Conv2D(32,(3,3),input_shape=(50,50,3),activation='relu'))
# 池化层
model.add(MaxPool2D(pool_size=(2,2)))
# 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())
# FC layer
model.add(Dense(units=128,activation='relu'))
model.add(Dense(units=1,activation='sigmoid'))

# configure the model
model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])


model.summary()

# train the model
model.fit_generator(training_set,epochs=25)


# accuracy on the training data
accuracy_train = model.evaluate(training_set)
print(accuracy_train)


# 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(test_set)
print(accuracy_test)


# load single image
from tensorflow.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)


pic_cat = '7.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)

training_set.class_indices


# 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 tensorflow.keras.preprocessing.image import load_img
from tensorflow.keras.preprocessing.image import img_to_array
from tensorflow.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()

image

code2

结合VGG已经训练好的模型构建新的模型。

#load the data
from tensorflow.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)

from tensorflow.keras.applications.vgg16 import VGG16
from tensorflow.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)

# 特征提取
features= model_vgg.predict(x)
print(features.shape)

# flatten
features = features.reshape(1,7*7*512)
print(features.shape)


#visualize the data
%matplotlib inline
from matplotlib import pyplot as plt
fig = plt.figure(figsize=(5,5))
img = load_img(img_path,target_size=(244,224))
plt.imshow(img)


# load image and preprocess it with vgg16 structure
from tensorflow.keras.preprocessing.image import img_to_array, load_img
from tensorflow.keras.applications.vgg16 import VGG16
from tensorflow.keras.applications.vgg16 import preprocess_input
import numpy as np

model_vgg = VGG16(weights='imagenet', include_top=False)
#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
#list file names of the training datasets
import os
folder = './train2/cats'
dirs = os.listdir(folder)
#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]

#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 = './train2/dogs'
dirs = os.listdir(folder)
#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]

#preprocess multiple images
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

#label the result
print(features1.shape,features2.shape)
y1 = np.zeros(300)
y2 = np.ones(300)

#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)


# 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)


# set up the mlp model
from tensorflow.keras.models import Sequential
from tensorflow.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()


# configure the model
model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])
# train the model
model.fit(X_train,y_train,epochs=50)


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)


# 测试准确率
y_test_predict = model.predict_classes(X_test)
accuracy_test = accuracy_score(y_test,y_test_predict)
print(accuracy_test)


img_path='dog.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)


# 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 tensorflow.keras.preprocessing.image import load_img
from tensorflow.keras.preprocessing.image import img_to_array
from tensorflow.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_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()

image