keras用vgg16预训练的参数训练自己数据集

1.下载vgg16模型预训练权重，将之放到~/.keras/model/下面，这样在keras导入vgg16的时候就不会联网下载，因为某些原因国内下载不了。。

2.通过vgg16来提取特征，不用输出层

通过vgg获取数据集特征，提取离线处理之后后面直接用，数据集和上次一样的车辆数据集一样，前面博文有说

import kerasfrom keras.applications.vgg16 import VGG16from keras.preprocessing import imagefrom keras.applications.vgg16 import preprocess_inputfrom keras.preprocessing.image import ImageDataGeneratorimport numpy as npmodel = VGG16(weights='imagenet', include_top=False)# img_path = '17.png'# img = image.load_img(img_path)# x = image.img_to_array(img)# x = np.expand_dims(x, axis=0)# x = preprocess_input(x)# features = model.predict(x)# print features# dimensions of our images.img_width, img_height = 64, 64train_data_dir = 'data/train'validation_data_dir = 'data/validation'nb_train_samples = 4000  #4000nb_validation_samples = 2000  #2000batch_size = 1datagen = ImageDataGenerator()generator = datagen.flow_from_directory(        'data/train',        target_size=(img_width, img_height),        batch_size=batch_size,        class_mode=None,  # this means our generator will only yield batches of data, no labels        shuffle=False)  # our data will be in order, so all first 1000 images will be cats, then 1000 dogs# the predict_generator method returns the output of a model, given# a generator that yields batches of numpy dataprint "train begin\n"bottleneck_features_train = model.predict_generator(generator, nb_train_samples)# save the output as a Numpy arraynp.save(open('bottleneck_features_train.npy', 'w'), bottleneck_features_train)print "train over\n"generator = datagen.flow_from_directory(        'data/validation',        target_size=(img_width, img_height),        batch_size=batch_size,        class_mode=None,  # this means our generator will only yield batches of data, no labels        shuffle=False)bottleneck_features_validation = model.predict_generator(generator, nb_validation_samples)np.save(open('bottleneck_features_validation.npy', 'w'), bottleneck_features_validation)

训练输出层部分

from keras.preprocessing.image import ImageDataGeneratorfrom keras.models import Sequentialfrom keras.layers import Conv2D, MaxPooling2Dfrom keras.layers import Activation, Dropout, Flatten, Densefrom keras import backend as Kimport h5pyimport numpy as nptrain_data = np.load(open('bottleneck_features_train.npy'))# the features were saved in order, so recreating the labels is easytrain_labels = np.array([0] * 2000 + [1] * 2000)print train_data.shape[1:]validation_data = np.load(open('bottleneck_features_validation.npy'))validation_labels = np.array([0] * 1000 + [1] * 1000)print validation_data.shapemodel = Sequential()model.add(Flatten(input_shape=train_data.shape[1:]))model.add(Dense(1024, activation='relu'))model.add(Dropout(0.5))model.add(Dense(256, activation='relu'))model.add(Dropout(0.5))model.add(Dense(1, activation='sigmoid'))# 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,          nb_epoch=50, batch_size=32,          validation_data=(validation_data, validation_labels) )#model.save_weights('bottleneck_fc_model.h5')model.save('My_vgg.h5')

测试数据

import kerasfrom keras.models import load_modelfrom keras.models import Sequentialfrom keras.applications.vgg16 import VGG16from keras.preprocessing import imagefrom keras.applications.vgg16 import preprocess_inputfrom keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_imgfrom keras import backend as K#import cv2import numpy as npimport h5pyimport os#model = Sequential()modelVGG = VGG16(weights='imagenet', include_top=False)modelMY = load_model('My_vgg.h5')num_test=44count=0for i in range(num_test):    #path='pic/'+str(i)+'.png';    #path='17.png'    #path='data/validation/veh/'+str(i)+'.png'    path='pic/'+str(i)+'.png'    img = load_img(path)  # this is a PIL image    x = img_to_array(img)  # this is a Numpy array with shape (3, 150, 150)    x = np.expand_dims(x, axis=0)    x = preprocess_input(x)    features = modelVGG.predict(x)    # print i    #print i,modelMY.predict_proba(features)    if (modelMY.predict_proba(features) > 0.7 ):        print iprint count*1.0/num_test    # print '\n'