猫狗大战---自制模型

猫狗大战

• 自制模型

---

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)


---

### 构建模型

#定义一个包含dropout层的新卷积网络
model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu',input_shape=(150, 150, 3)))
model.add(layers.MaxPooling2D(2, 2))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D(2, 2))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D(2 ,2))
model.add(layers.Flatten())
model.add(layers.Dropout(0.5))
model.add(layers.Dense(512, activation='relu'))
model.add(layers.Dense(1,activation='sigmoid'))

model.compile(loss='binary_crossentropy',
             optimizer=optimizers.RMSprop(lr=1e-4),
             metrics=['acc'])

---

数据预处理

使用数据增强

datagen = ImageDataGenerator(
    rotation_range = 40,#随机旋转角度值
    width_shift_range = 0.2,#平移水平的相对范围
    height_shift_range = 0.2,#平移高度的相对范围
    shear_range = 0.2,#随机交错变换的角度
    zoom_range = 0.2,#图像随机缩放的范围
    horizontal_flip = True,#随机将一半的图像水平翻转
    fill_mode = 'nearest'#用于填充创建像素的方法，这些新像素可能来自旋转或宽度/高度平移
)

#增强预览
from keras .preprocessing import image

fnames = [os.path.join(train_cats_dir, fname) for fname in os.listdir(train_cats_dir)]
img_path = fnames[50]#选一张图片进行增强

img = image.load_img(img_path, target_size=(150, 150))#读取图像并且调整大小

x = image.img_to_array(img)#将其形状变成形状为(150,150,3)的Numpy数组

x = x.reshape((1,) + x.shape)#将其形状改变成为(1,150,150,3)

i = 0
for batch in datagen.flow(x, batch_size=1):
    plt.figure()
    imgplot = plt.imshow(image.array_to_img(batch[0]))
    i += 1
    if i % 4 ==0:
        break

plt.show()

使用ImageDataGenerator从目录中读取图像

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,
)

test_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
    train_dir,
    target_size=(150, 150),
    batch_size=32,
    class_mode='binary',#因为使用了binary_crossentropy损失，所以需要用二进制标签
)

validation_generator = test_datagen.flow_from_directory(
    validation_dir,
    target_size=(150, 150),
    batch_size=32,
    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=100,
    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_small_2.h5’)