Keras：使用预训练网络的bottleneck特征

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)  _________________________________________________________________ block2_pool (MaxPooling2D) (None, 56, 56, 128) 0 _________________________________________________________________ block3_conv1 (Conv2D) (None, 56, 56, 256)  _________________________________________________________________ block3_conv2 (Conv2D) (None, 56, 56, 256)  _________________________________________________________________ block3_conv3 (Conv2D) (None, 56, 56, 256)  _________________________________________________________________ block3_pool (MaxPooling2D) (None, 28, 28, 256) 0 _________________________________________________________________ block4_conv1 (Conv2D) (None, 28, 28, 512)  _________________________________________________________________ block4_conv2 (Conv2D) (None, 28, 28, 512)  _________________________________________________________________ block4_conv3 (Conv2D) (None, 28, 28, 512)  _________________________________________________________________ block4_pool (MaxPooling2D) (None, 14, 14, 512) 0 _________________________________________________________________ block5_conv1 (Conv2D) (None, 14, 14, 512)  _________________________________________________________________ block5_conv2 (Conv2D) (None, 14, 14, 512)  _________________________________________________________________ block5_conv3 (Conv2D) (None, 14, 14, 512)  _________________________________________________________________ block5_pool (MaxPooling2D) (None, 7, 7, 512) 0 _________________________________________________________________ flatten (Flatten) (None, 25088) 0 _________________________________________________________________ fc1 (Dense) (None, 4096)  _________________________________________________________________ fc2 (Dense) (None, 4096)  _________________________________________________________________ predictions (Dense) (None, 1000) ================================================================= 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')

train\  0\  1\ validation\  0\  1\

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:

#!/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')