VGG16的猫狗识别

简单步骤

加载一张照片
维度转换为224*224
转换为array

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)

numpy.ndarray

获取vgg16 主要卷积层 不要后面的全连接层 （自己写）
改变输入数据的维度
图像预处理

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)

(1, 224, 224, 3)

#特征提取
features = model_vgg.predict(x)`在这里插入代码片`
print(features.shape)

(1, 7, 7, 512)

#全连接层准备   改变数据维度 
features = features.reshape(1,7*7*512)
print(features.shape)

(1, 25088)

整体处理

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
# 数据预处理和模型加载
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 = "dataset/data_vgg/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 = "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
    
#label the results
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)

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)

from keras.models import Sequential
from keras.layers import Dense
# 构建模型 两个全连接层 25088-10 10-1 （1就是二分类）
model = Sequential()
model.add(Dense(units=10,activation='relu',input_dim=25088))
model.add(Dense(units=1,activation='sigmoid'))
model.summary()
#定义loss opt acc基本参数
odel.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])
#train the model
model.fit(X_train,y_train,epochs=50)

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

# 找个网图测试
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)

可视化测试  找10个图片名字是1-10
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()

结果如图