猫狗图像分类

1.搜狗图片爬取

import requests
import time
import os
# 请求头,伪装成浏览器
headers = {
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.116 Safari/537.36'}
keyword = '纯种黄土狗' # 关键字
max_page = 10 # 爬取页数
i=7273 # 记录图片数
for page in range(0,5):
    print(page)
    page = page*30
    # 网址
url = 'https://image.baidu.com/search/acjson?tn=resultjson_com&ipn=rj&ct=201326592&is=&fp=result&queryWord='\+keyword+'&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=-1&z=&ic=0&hd=&latest=&copyright=&word='\
+keyword+'&s=&se=&tab=&width=&height=&face=0&istype=2&qc=&nc=1&fr=&expermode=&force=&cg=wallpaper&pn='\+str(page)+'&rn=30&gsm=1e&1596899786625='
    # 请求响应
    response = requests.get(url=url,headers=headers)
    # 得到相应的json数据
    json = response.json()
    if json.get('data'):
        for item in json.get('data')[:30]:
            # 图片地址
            img_url = item.get('thumbURL')
            # 获取图片
            image = requests.get(url=img_url)
            # 下载图片
            with open('狗图片/dog.%d.jpg' %i,'wb') as f:
                f.write(image.content) # 图片二进制数据
            time.sleep(1) # 等待1s
            print('第%d张%s图片下载完成...'%(i,keyword))
            i+=1
print('End!')

我们构建的CNN模型网络的输入图片大小为(150,150,3)，我们要对首先对训练和测试图片做预处理。

# 定义图片生成器
train_datagen = ImageDataGenerator(
    rotation_range = 40,     # 随机旋转度数
    width_shift_range = 0.2, # 随机水平平移
    height_shift_range = 0.2,# 随机竖直平移
    rescale = 1/255,         # 数据归一化
    shear_range = 20,       # 随机错切变换
    zoom_range = 0.2,        # 随机放大
    horizontal_flip = True,  # 水平翻转
    fill_mode = 'nearest',   # 填充方式
) 
test_datagen = ImageDataGenerator(
    rescale = 1/255,         # 数据归一化
) 
batch_size = 32
# 生成训练数据
train_generator = train_datagen.flow_from_directory('image/train/', target_size=(150,150), batch_size=batch_size)
# 测试数据
test_generator = train_datagen.flow_from_directory('image/test/', target_size=(150,150), batch_size=batch_size)
# Found 400 images belonging to 2 classes.
# Found 200 images belonging to 2 classes.

train_generator.class_indices
# {'cat': 0, 'dog': 1}

卷积神经网络模型构建(CNN)

from keras.models import Sequential
from keras.layers import Dense, Conv2D, MaxPool2D, Activation, Dropout, Flatten
from keras.optimizers import Adam
from keras.preprocessing.image import ImageDataGenerator, img_to_array, load_img
from keras.utils.vis_utils import plot_model
import matplotlib.pyplot as plt

# 定义模型
model = Sequential()
model.add(Conv2D(input_shape=(150,150,3),filters=32, kernel_size=3, padding='same', activation='relu'))
model.add(Conv2D(filters=32, kernel_size=3, padding='same', activation='relu'))
model.add(MaxPool2D(pool_size=2, strides=2))

model.add(Conv2D(filters=64, kernel_size=3, padding='same', activation='relu'))
model.add(Conv2D(filters=64, kernel_size=3, padding='same', activation='relu'))
model.add(MaxPool2D(pool_size=2, strides=2))

model.add(Conv2D(filters=128, kernel_size=3, padding='same', activation='relu'))
model.add(Conv2D(filters=128, kernel_size=3, padding='same', activation='relu'))
model.add(MaxPool2D(pool_size=2, strides=2))

model.add(Flatten())
model.add(Dense(units=64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(2, activation='softmax'))

# 定义优化器
adam = Adam(lr=1e-4)

# 定义优化器，代价函数，训练过程中的准确率
model.compile(optimizer=adam, loss='categorical_crossentropy', metrics=['accuracy'])
model.summary()

# 进行训练
model.fit_generator(
    train_generator, 
    steps_per_epoch=len(train_generator), 
    epochs=30, 
    validation_data=test_generator, 
    validation_steps=len(test_generator))
# 模型保存
model.save('model_cnn.h5')
# 部分输出结果：
# Epoch 1/30
# 13/13 [==============================] - 13s 962ms/step - loss: 0.6986 - acc: 0.5171 - val_loss: 0.6936 - val_acc: 0.5000
# Epoch 2/30

from keras.models import load_model
import numpy as np
label = np.array(['cat','dog'])
# 载入模型
model = load_model('model_cnn.h5')
# 导入图片
image = load_img('image/test/cat/cat.1002.jpg')
# 对测试图片预处理
image = image.resize((150,150))
image = img_to_array(image)
image = image/255
image = np.expand_dims(image,0)
image.shape
# (1, 150, 150, 3)
# 预测结果：
print(label[model.predict_classes(image)])
# ['cat']

附：
vgg16模型，准确率更好

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Conv2D, MaxPool2D, Activation, Dropout, Flatten
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.preprocessing.image import ImageDataGenerator, img_to_array, load_img
from keras.utils.vis_utils import plot_model
import matplotlib.pyplot as plt
from tensorflow.keras.applications import VGG16


base_model=VGG16(weights="imagenet",include_top=False,input_shape=(150,150,3))
model = Sequential()
model.add(base_model)

model.add(Flatten())
model.add(Dense(units=64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(2, activation='softmax'))

adam = Adam(lr=1e-4)

model.compile(optimizer=adam, loss='categorical_crossentropy', metrics=['accuracy'])
model.summary()