批量提取 caffe 特征 （python, C++, Matlab）（待续）

本文参考如下：

Instant Recognition with Caffe
Extracting Features

Caffe Python特征提取

caffe 练习4 —-利用python批量抽取caffe计算得到的特征——by 香蕉麦乐迪
caffe 练习3 用caffe提供的C++函数批量抽取图像特征——by 香蕉麦乐迪

caffe python批量抽取图像特征
caffe python 批量抽取图像特征—续篇
caffe c++ 抽取图片特征

shicai C++ Caffe提取特征

caffe源码修改：抽取任意一张图片的特征

matlab 批量提取CNN特征

关于如何批量提取特征，本文的框架如下：
１. 准备数据及相应准备工作
２. 初始化网络
３.读取图像列表
４.提取图像特征，并保存为特定格式

Python方法一
主要有三个函数：
initialize () 初始化网络的相关
readlist() 读取抽取图像列表
extractFeatre() 抽取图像的特征，保存为指定的格式

其中在transformer那里需要根据自己的需求设定

#encoding:utf-8#详情请查看http://www.cnblogs.com/louyihang-loves-baiyan/p/5078746.htmlimport numpy as npimport matplotlib.pyplot as pltimport osimport caffeimport sysimport pickleimport structimport sys,cv2caffe_root = '../'  # 运行模型的prototxtdeployPrototxt =  '/home/bids/caffe/caffe-master/changmiao/model/deploy.prototxt'# 相应载入的modelfilemodelFile = '/home/bids/caffe/caffe-master/changmiao/model/bvlc_reference_caffenet.caffemodel'# meanfile 也可以用自己生成的meanFile = 'python/caffe/imagenet/ilsvrc_2012_mean.npy'# 需要提取的图像列表imageListFile = '/home/bids/caffe/caffe-master/changmiao/data/temp.txt'imageBasePath = '/home/bids/caffe/caffe-master/changmiao/data/cat'#gpuID = 4　＃根据你自己电脑的ＧＰＵ情况而定postfix = '.classify_allCar1716_fc6'# 初始化函数的相关操作def initilize():    print 'initilize ... '    sys.path.insert(0, caffe_root + 'python')    caffe.set_mode_gpu()#    caffe.set_device(gpuID)    net = caffe.Net(deployPrototxt, modelFile,caffe.TEST)    return net  # 提取特征并保存为相应地文件def extractFeature(imageList, net):    # 对输入数据做相应地调整如通道、尺寸等等    transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})    transformer.set_transpose('data', (2,0,1))    transformer.set_mean('data', np.load(caffe_root + meanFile).mean(1).mean(1)) # mean pixel    transformer.set_raw_scale('data', 255)      transformer.set_channel_swap('data', (2,1,0))      # set net to batch size of 1 如果图片较多就设置合适的batchsize     net.blobs['data'].reshape(1,3,227,227)      #这里根据需要设定，如果网络中不一致，需要调整    num=0#imageList = os.listdir(imageBasePath)    for imagefile in imageList:        imagefile_abs = os.path.join(imageBasePath, imagefile)        print imagefile_abs        net.blobs['data'].data[...] = transformer.preprocess('data', caffe.io.load_image(imagefile_abs))        out = net.forward()        fea_file = imagefile_abs.replace('.jpg',postfix)        num +=1        print 'Num ',num,' extract feature ',fea_file        with  open(fea_file,'wb') as f:            for x in xrange(0, net.blobs['fc6'].data.shape[0]):                for y in xrange(0, net.blobs['fc6'].data.shape[1]):                    f.write(struct.pack('f', net.blobs['fc6'].data[x,y]))# 读取文件列表def readImageList(imageListFile):    imageList = []    with open(imageListFile,'r') as fi:        while(True):            line = fi.readline().strip().split()# every line is a image file name            if not line:                break            imageList.append(line[0])     print 'read imageList done image num ', len(imageList)    return imageListif __name__ == "__main__":    net = initilize()    imageList = readImageList(imageListFile)     extractFeature(imageList, net)