本文参考如下:
Instant Recognition with Caffe
Extracting Features
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
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.html
import numpy as np
import matplotlib.pyplot as plt
import os
import caffe
import sys
import pickle
import struct
import sys,cv2
caffe_root = '../'
# 运行模型的prototxt
deployPrototxt = '/home/bids/caffe/caffe-master/changmiao/model/deploy.prototxt'
# 相应载入的modelfile
modelFile = '/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 imageList
if __name__ == "__main__":
net = initilize()
imageList = readImageList(imageListFile)
extractFeature(imageList, net)