猫狗大战 ---使用预训练模型②

猫狗大战—使用预训练模型VGG16①

• 法①: 将输出保存成Numpy数组作为独立的密集连接分类器的输入，速度快代价低，但不能使用数据增强
• 法②: 在顶部添加Dense层来扩展已有模型（即conv_base）,并在输入数据上端到端的运行整个模型，可以使用数据增强。
• 本篇现将法②

---

数据导入

将图像复制到训练，验证和测试目录

import os
import shutil

TRAIN_DIR = 'D:\\Jupyter\\dogs-vs-cats\\'
BASE_DIR = 'E:\\BaiduNetdiskDownload\\kaggle\\train\\'

#举一个train文件夹的例子
train_dir = os.path.join(TRAIN_DIR, 'train')
#os.mkdir(train_dir)

train_cats_dir = os.path.join(train_dir, 'cats')
#os.mkdir(train_cats_dir)
train_dogs_dir = os.path.join(train_dir, 'dogs')
#os.mkdir(train_dogs_dir)

#举一个复制图片里猫猫的例子
fnames = ['cat.{}.jpg'.format(i) for i in range(1000)]
for fname in fnames:
    src = os.path.join(BASE_DIR, fname)
    dst = os.path.join(train_cats_dir, fname)
    shutil.copyfile(src, dst)

fnames = ['cat.{}.jpg'.format(i) for i in range(1000,1500)]
for fname in fnames:
    src = os.path.join(BASE_DIR, fname)
    dst = os.path.join(validation_cats_dir, fname)
    shutil.copyfile(src, dst)

fnames = ['cat.{}.jpg'.format(i) for i in range(1500,2000)]
for fname in fnames:
    src = os.path.join(BASE_DIR, fname)
    dst = os.path.join(test_cats_dir, fname)
    shutil.copyfile(src, dst)

#如果以上步骤之前做过，则
#import os
#base_dir = 'D:\\Jupyter\\dogs-vs-cats\\'
#train_dir = os.path.join(base_dir, 'train')
#validation_dir = os.path.join(base_dir, 'validation')
#test_dir = os.path.join(base_dir, 'test')


---

### 构建模型

from keras.applications import VGG16
#导入VGG16
conv_base = VGG16(weights='imagenet',#指向模型初始化的权重检查点
                  include_top=False,#指定模型是否包含密集连接分类器
                  input_shape=(150, 150, 3)#输入到网络的张量形状
                 )

from keras import models
from keras import layers

#编译之前“冻结”
conv_base.trainable = False

model = models.Sequential()
model.add(conv_base)
model.add(layers.Flatten())
model.add(layers.Dense(256, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))
#编译
model.compile(optimizer=optimizers.RMSprop(lr=2e-5),
             loss='binary_crossentropy',
             metrics=['acc'])

---

数据预处理

不使用数据增强

from keras.preprocessing.image import ImageDataGenerator
from keras import optimizers

train_datagen = ImageDataGenerator(
    rescale = 1./255,
    rotation_range = 40,
    width_shift_range = 0.2,
    height_shift_range = 0.2,
    shear_range = 0.2,
    zoom_range = 0.2,
    horizontal_flip = True,
    fill_mode = 'nearest'
)

test_datagen = ImageDataGenerator(rescale = 1./255)

使用ImageDataGenerator从目录中读取图像

train_generator = train_datagen.flow_from_directory(
    train_dir,
    target_size = (150, 150),
    batch_size = 20,
    class_mode = 'binary',#因为使用binary_crossentropy，所以得使用binary二进制标签
)

validation_generator = test_datagen.flow_from_directory(
    validation_dir,
    target_size = (150,150),
    batch_size = 20,
    class_mode = 'binary',
)

利用批量生成器拟合模型

history = model.fit_generator(
    train_generator,
    steps_per_epoch=100,
    epochs=30,
    validation_data = validation_generator,
    validation_steps=50
)

绘制训练过程中的损失曲线和精度曲线

import matplotlib.pyplot as plt

acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']

epochs = range(1, len(acc)+1)

plt.plot(epochs, acc, 'bo', label='Training acc')
plt.plot(epochs, val_acc, 'b', label='Validaton acc')
plt.title('Training and Validation accuracy')
plt.legend()

plt.figure()

plt.plot(epochs, loss, 'bo', label='Training loss')
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title('Training and Validation loss')
plt.legend()

plt.show()

---

保存模型

model.save(‘cats_and_dogs_VGG16_motehod2.h5’)