dogs_vs_cats学习

Posted on | In | | Visitors:

参考

任务

  • 重新训练一个小网络
  • 使用预训练模型得到的特征

  • 微调预训练模型

  • fit_generator训练

  • ImageDataGenerator做实时的数据增强
  • layer freezing 和 模型 fine-tuning

目录设置和数据集划分

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
"""
data/
    train/
        dogs/
            dog001.jpg
            dog002.jpg
            ...
        cats/
            cat001.jpg
            cat002.jpg
            ...
    val/
        dogs/
            dog001.jpg
            dog002.jpg
            ...
        cats/
            cat001.jpg
            cat002.jpg
            ...
"""
import shutil
import os

path_list = ['./data/val','./data/train/dogs','./data/train/cats','./data/val/dogs','./data/val/cats']

def make_path(path):
    if not os.path.exists(path):
        os.mkdir(path)
for i in path_list:
    make_path(i)
    
filenames = os.listdir('./data/train/')
cats = []
dogs = []
for x in filenames:
    if x[:3]=='cat':
        cats.append(x)
    else:
        dogs.append(x)

train_cats = cats[:12000]
train_dogs = dogs[:12000]

val_cats = cats[12000:]
val_dogs = dogs[12000:]

def mv_img(file,old_folder,new_folder):
    for i in file:
        path = os.path.join(old_folder,i)
        shutil.move(path,new_folder)
        
file = [train_cats,train_dogs,val_cats,val_dogs]
old_folder = ['./data/train','./data/train','./data/train','./data/train']
new_folder = ['./data/train/cats/','./data/train/dogs/','./data/val/cats/','./data/val/dogs/']

folder =list(zip(file,old_folder,new_folder))
for f,o,n in folder:
    mv_img(f,o,n)

数据预处理和数据增强

keras.preprocessing.image.ImageDataGenerator class

  • 训练的时候可以标准化
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
keras.preprocessing.image.ImageDataGenerator(featurewise_center=False,
    samplewise_center=False,
    featurewise_std_normalization=False,
    samplewise_std_normalization=False,
    zca_whitening=False,
    zca_epsilon=1e-6,
    rotation_range=0.,
    width_shift_range=0.,
    height_shift_range=0.,
    shear_range=0.,
    zoom_range=0.,
    channel_shift_range=0.,
    fill_mode='nearest',
    cval=0.,
    horizontal_flip=False,
    vertical_flip=False,
    rescale=None,
    preprocessing_function=None,
    data_format=K.image_data_format())
  • featurewise_center：布尔值，使输入数据集去中心化（均值为0）, 按feature执行
  • samplewise_center：布尔值，使输入数据的每个样本均值为0
  • featurewise_std_normalization：布尔值，将输入除以数据集的标准差以完成标准化, 按feature执行
  • samplewise_std_normalization：布尔值，将输入的每个样本除以其自身的标准差
  • zca_whitening：布尔值，对输入数据施加ZCA白化
  • zca_epsilon: ZCA使用的eposilon，默认1e-6
  • rotation_range：整数，数据提升时图片随机转动的角度
  • width_shift_range：浮点数，图片宽度的某个比例，数据提升时图片水平偏移的幅度
  • height_shift_range：浮点数，图片高度的某个比例，数据提升时图片竖直偏移的幅度
  • shear_range：浮点数，剪切强度（逆时针方向的剪切变换角度）
  • zoom_range：浮点数或形如[lower,upper]的列表，随机缩放的幅度，若为浮点数，则相当于[lower,upper] = [1 - zoom_range, 1+zoom_range]
  • channel_shift_range：浮点数，随机通道偏移的幅度
  • fill_mode：；‘constant’，‘nearest’，‘reflect’或‘wrap’之一，当进行变换时超出边界的点将根据本参数给定的方法进行处理
  • cval：浮点数或整数，当fill_mode=constant时，指定要向超出边界的点填充的值
  • horizontal_flip：布尔值，进行随机水平翻转
  • vertical_flip：布尔值，进行随机竖直翻转
  • rescale: 重放缩因子,默认为None. 如果为None或0则不进行放缩,否则会将该数值乘到数据上(在应用其他变换之前)
  • preprocessing_function: 将被应用于每个输入的函数。该函数将在图片缩放和数据提升之后运行。该函数接受一个参数，为一张图片（秩为3的numpy array），并且输出一个具有相同shape的numpy array
  • data_format：字符串，“channel_first”或“channel_last”之一，代表图像的通道维的位置。该参数是Keras 1.x中的image_dim_ordering，“channel_last”对应原本的“tf”，“channel_first”对应原本的“th”。以128x128的RGB图像为例，“channel_first”应将数据组织为（3,128,128），而“channel_last”应将数据组织为（128,128,3）。该参数的默认值是~/.keras/keras.json中设置的值，若从未设置过，则为“channel_last”
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img

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

img = load_img('data/train/cats/cat.10.jpg')
x = img_to_array(img)
x = x.reshape((1,) + x.shape)  # this is a Numpy array with shape (1, 3, 150, 150)

# the .flow() command below generates batches of randomly transformed images
# and saves the results to the `preview/` directory
i = 0
for batch in datagen.flow(x, batch_size=1,
                          save_to_dir='preview', save_prefix='cat', save_format='jpeg'):
    i += 1
    if i > 20:
        break  # otherwise the generator would loop indefinitely

训练一个小的卷积神经网络

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K

# dimensions of our images.
img_width, img_height = 150, 150
if K.image_data_format() == 'channels_first':
    input_shape = (3, img_width, img_height)
else:
    input_shape = (img_width, img_height, 3)

model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))

model.compile(loss='binary_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])
model.summary()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
train_data_dir = 'data/train'
validation_data_dir = 'data/val'
nb_train_samples = 12000
nb_validation_samples = 500
epochs = 50
batch_size = 16

# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True)

# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1. / 255)

train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
    validation_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary')

model.fit_generator(
    train_generator,
    steps_per_epoch=nb_train_samples // batch_size,
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=nb_validation_samples // batch_size)

model.save_weights('first_try.h5')

权重

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
import numpy as np
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Dropout, Flatten, Dense
from keras import applications

# dimensions of our images.
img_width, img_height = 150, 150

top_model_weights_path = 'bottleneck_fc_model.h5'
train_data_dir = 'data/train'
validation_data_dir = 'data/validation'
nb_train_samples = 2000
nb_validation_samples = 800
epochs = 50
batch_size = 16


def save_bottlebeck_features():
    datagen = ImageDataGenerator(rescale=1. / 255)

    # build the VGG16 network
    model = applications.VGG16(include_top=False, weights='imagenet')

    generator = datagen.flow_from_directory(
        train_data_dir,
        target_size=(img_width, img_height),
        batch_size=batch_size,
        class_mode=None,
        shuffle=False)
    bottleneck_features_train = model.predict_generator(
        generator, nb_train_samples // batch_size)
    np.save(open('bottleneck_features_train.npy', 'w'),
            bottleneck_features_train)

    generator = datagen.flow_from_directory(
        validation_data_dir,
        target_size=(img_width, img_height),
        batch_size=batch_size,
        class_mode=None,
        shuffle=False)
    bottleneck_features_validation = model.predict_generator(
        generator, nb_validation_samples // batch_size)
    np.save(open('bottleneck_features_validation.npy', 'w'),
            bottleneck_features_validation)


def train_top_model():
    train_data = np.load(open('bottleneck_features_train.npy'))
    train_labels = np.array(
        [0] * (nb_train_samples / 2) + [1] * (nb_train_samples / 2))

    validation_data = np.load(open('bottleneck_features_validation.npy'))
    validation_labels = np.array(
        [0] * (nb_validation_samples / 2) + [1] * (nb_validation_samples / 2))

    model = Sequential()
    model.add(Flatten(input_shape=train_data.shape[1:]))
    model.add(Dense(256, activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(1, activation='sigmoid'))

    model.compile(optimizer='rmsprop',
                  loss='binary_crossentropy', metrics=['accuracy'])

    model.fit(train_data, train_labels,
              epochs=epochs,
              batch_size=batch_size,
              validation_data=(validation_data, validation_labels))
    model.save_weights(top_model_weights_path)


save_bottlebeck_features()
train_top_model()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
from keras import applications
from keras.preprocessing.image import ImageDataGenerator
from keras import optimizers
from keras.models import Sequential
from keras.layers import Dropout, Flatten, Dense

# path to the model weights files.
weights_path = '../keras/examples/vgg16_weights.h5'
top_model_weights_path = 'fc_model.h5'
# dimensions of our images.
img_width, img_height = 150, 150

train_data_dir = 'cats_and_dogs_small/train'
validation_data_dir = 'cats_and_dogs_small/validation'
nb_train_samples = 2000
nb_validation_samples = 800
epochs = 50
batch_size = 16

# build the VGG16 network
model = applications.VGG16(weights='imagenet', include_top=False)
print('Model loaded.')

# build a classifier model to put on top of the convolutional model
top_model = Sequential()
top_model.add(Flatten(input_shape=model.output_shape[1:]))
top_model.add(Dense(256, activation='relu'))
top_model.add(Dropout(0.5))
top_model.add(Dense(1, activation='sigmoid'))

# note that it is necessary to start with a fully-trained
# classifier, including the top classifier,
# in order to successfully do fine-tuning
top_model.load_weights(top_model_weights_path)

# add the model on top of the convolutional base
model.add(top_model)

# set the first 25 layers (up to the last conv block)
# to non-trainable (weights will not be updated)
for layer in model.layers[:25]:
    layer.trainable = False

# compile the model with a SGD/momentum optimizer
# and a very slow learning rate.
model.compile(loss='binary_crossentropy',
              optimizer=optimizers.SGD(lr=1e-4, momentum=0.9),
              metrics=['accuracy'])

# prepare data augmentation configuration
train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    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_data_dir,
    target_size=(img_height, img_width),
    batch_size=batch_size,
    class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
    validation_data_dir,
    target_size=(img_height, img_width),
    batch_size=batch_size,
    class_mode='binary')

# fine-tune the model
model.fit_generator(
    train_generator,
    samples_per_epoch=nb_train_samples,
    epochs=epochs,
    validation_data=validation_generator,
    nb_val_samples=nb_validation_samples)
坚持原创技术分享，您的支持将鼓励我继续创作！