使用预训练网络的bottleneck特征
在规模较大的数据集上训练好的网络,一般都具有非常好的特征提取能力.以VGG16为例,其网络就是通过卷基层提取到图像特征后通过后面的全连接层进行分类.现在我们通过使用VGG16的卷基层对我们自己的图像数据集进行特征提取以提高
通过
from keras.applications.vgg16 import VGG16
from keras.utils import plot_model
model = VGG16(include_top=True, weights='imagenet')
model.summary()
plot_model(model, to_file='VGG16.png')可以看到VGG16的网络结构为:
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) (None, 224, 224, 3) 0
_________________________________________________________________
block1_conv1 (Conv2D) (None, 224, 224, 64) 1792
_________________________________________________________________
block1_conv2 (Conv2D) (None, 224, 224, 64) 36928
_________________________________________________________________
block1_pool (MaxPooling2D) (None, 112, 112, 64) 0
_________________________________________________________________
block2_conv1 (Conv2D) (None, 112, 112, 128) 73856
_________________________________________________________________
block2_conv2 (Conv2D) (None, 112, 112, 128) 147584
_________________________________________________________________
block2_pool (MaxPooling2D) (None, 56, 56, 128) 0
_________________________________________________________________
block3_conv1 (Conv2D) (None, 56, 56, 256) 295168
_________________________________________________________________
block3_conv2 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_conv3 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_pool (MaxPooling2D) (None, 28, 28, 256) 0
_________________________________________________________________
block4_conv1 (Conv2D) (None, 28, 28, 512) 1180160
_________________________________________________________________
block4_conv2 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
block4_conv3 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
block4_pool (MaxPooling2D) (None, 14, 14, 512) 0
_________________________________________________________________
block5_conv1 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_conv2 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_conv3 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_pool (MaxPooling2D) (None, 7, 7, 512) 0
_________________________________________________________________
flatten (Flatten) (None, 25088) 0
_________________________________________________________________
fc1 (Dense) (None, 4096) 102764544
_________________________________________________________________
fc2 (Dense) (None, 4096) 16781312
_________________________________________________________________
predictions (Dense) (None, 1000) 4097000
=================================================================
Total params: 138,357,544
Trainable params: 138,357,544
Non-trainable params: 0
_________________________________________________________________
当我们需要使用VGG16的卷积部分时,我们将全连接以上的部分抛掉.即另
VGG16(include_top=True, weights='imagenet')中的include_top=False.
此时,网络仅仅保留了卷基层部分,如图:
这样使用.flow_from_directory()从图片中产生数据,利用网络的卷基层部分得到训练集和测试集的bottleneck特征,将得到的特征记录在numpy array里.
这里使用的数据量很小,每个文件夹下仅30幅图像.存放结构为:
train\
0\
1\
validation\
0\
1\在生成训练集与验证集的bottleneck特征数据时,steps分别选了200和80,这样得到的bottleneck特征的shape分别为(6000, 4, 4, 512)与(2400, 4, 4, 512).(即200*30=6000,80*30=2400)
关于bottleneck特征的shape查看可用:
import numpy as np
test = np.load('bottleneck_features_train.npy')
print (test.shape)生成训练集与验证集的bottleneck特征数据:
#!/usr/bin/python
# coding:utf8
from keras.preprocessing.image import ImageDataGenerator
import numpy as np
from keras.applications.vgg16 import VGG16
# include_top：是否保留顶层的3个全连接网络
# 'imagenet'代表加载预训练权重
model = VGG16(include_top=False, weights='imagenet')
# 加载pre-model的权重
model.load_weights('vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5')
datagen = ImageDataGenerator(rescale=1./255)
# 训练集图像生成器,以文件夹路径为参数,生成经过数据提升/归一化后的数据
train_generator = datagen.flow_from_directory('train',
target_size=(150, 150),
batch_size=32,
class_mode=None,
shuffle=False)
# 验证集图像生成器
validation_generator = datagen.flow_from_directory('validation',
target_size=(150, 150),
batch_size=32,
class_mode=None,
shuffle=False)
# 得到bottleneck feature
# 使用一个生成器作为数据源预测模型，生成器应返回与test_on_batch的输入数据相同类型的数据
bottleneck_features_train = model.predict_generator(train_generator, steps=200)
print (bottleneck_features_train)
# steps是生成器要返回数据的轮数
# 将得到的特征记录在numpy array里
np.save(open('bottleneck_features_train.npy', 'w'), bottleneck_features_train)
bottleneck_features_validation = model.predict_generator(validation_generator, steps=80)
# 一个epoch有800张图片,验证集
np.save(open('bottleneck_features_validation.npy', 'w'), bottleneck_features_validation)然后训练我们的全连接网络,这里由于之前我们得到的训练集与测试集的bottleneck特征分别有200*30=6000,80*30=2400组,因此对应labels分别设为:
train_labels = np.array([0]*3000 + [1]*3000)validation_labels = np.array([0]*1200 + [1]*1200)然后将得到的数据载入,开始训练全连接网络:
扫描二维码关注公众号，回复：
1590327 查看本文章
#!/usr/bin/python
# coding:utf8
# fine-tune网络的后面几层.Fine-tune以一个预训练好的网络为基础,在新的数据集上重新训练一小部分权重
from keras.models import Sequential
from keras.layers import Dropout, Flatten, Dense
import numpy as np
train_data = np.load(open('bottleneck_features_train.npy'))
train_labels = np.array([0]*3000 + [1]*3000)
print (train_labels)
validation_data = np.load(open('bottleneck_features_validation.npy'))
validation_labels = np.array([0]*1200 + [1]*1200)
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=5, batch_size=32, validation_data=(validation_data,validation_labels))
model.save_weights('bottleneck_fc_model.h5')