把faster-rcnn检测出来的结果保存成txt,再转成xml

利用faster-rcnn检测图片，先把结果保存成txt，就像下面这样



利用下面这段代码就可以做到，把这段代码保存成XX.py，再运行。代码里需要改的地方都注释了，不知道怎么上传源码的，将就着用

#!/usr/bin/env python
# -*- coding: UTF-8 -*-
# --------------------------------------------------------
# Faster R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick
# --------------------------------------------------------

"""
Demo script showing detections in sample images.

See README.md for installation instructions before running.
"""

import _init_paths
from fast_rcnn.config import cfg
from fast_rcnn.test import im_detect
from fast_rcnn.nms_wrapper import nms
from utils.timer import Timer
import matplotlib.pyplot as plt
import numpy as np
import scipy.io as sio
import caffe, os, sys, cv2
import argparse

CLASSES = ('__background__',
'aeroplane', 'bicycle', 'bird', 'boat',
'bottle', 'bus', 'car', 'cat', 'chair',
'cow', 'diningtable', 'dog', 'horse',
'motorbike', 'person', 'pottedplant',
'sheep', 'sofa', 'train', 'tvmonitor')                                     #改成你的类别

NETS = {'vgg16': ('VGG16',
'VGG16_faster_rcnn_final.caffemodel'),
'zf': ('ZF',
'ZF_faster_rcnn_final.caffemodel')}

def vis_detections(image_name, class_name, dets, thresh=0.5):
"""Draw detected bounding boxes."""
inds = np.where(dets[:, -1] >= thresh)[0]
if len(inds) == 0:
return

for i in inds:
bbox = dets[i, :4]
score = dets[i, -1]
if(class_name == '__background__'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')                                                             #最终的txt保存在这个路径下，下面的都改
fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')

#                    图片名                 标签名                          四个坐标
fw.close()
elif(class_name == 'aeroplane'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
fw.close()
elif(class_name == 'bicycle'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
fw.write(str(image_name)+' '+'n02835271'+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')  #双人自行车
fw.close()
elif(class_name == 'bird'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
fw.write(str(image_name)+' '+'n01833805'+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')   #蜂鸟
fw.close()
elif(class_name == 'boat'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
fw.write(str(image_name)+' '+'n04273569'+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')    #快艇
fw.close()
elif(class_name == 'bottle'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
fw.write(str(image_name)+' '+'n04557648'+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')    #水瓶
fw.close()
elif(class_name == 'bus'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
fw.write(str(image_name)+' '+'n03769881'+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')    #小巴
fw.close()
elif(class_name == 'car'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
fw.write(str(image_name)+' '+'n04461696'+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')   #拖车
fw.close()
elif(class_name == 'cat'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
fw.write(str(image_name)+' '+'n02123045'+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')   #大花猫
fw.close()
elif(class_name == 'chair'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
fw.write(str(image_name)+' '+'n02791124'+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')    #理发椅
fw.close()
elif(class_name == 'cow'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
fw.close()
elif(class_name == 'diningtable'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
fw.close()
elif(class_name == 'dog'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
fw.write(str(image_name)+' '+'n0211673'+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')     #非洲猎犬，土狼狗，普猎犬，红腹锦鸡森林狼
fw.close()
elif(class_name == 'horse'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
fw.write(str(image_name)+' '+'n12768682'+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
fw.close()
elif(class_name == 'motorbike'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
fw.close()
elif(class_name == 'person'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
fw.close()
elif(class_name == 'pottedplant'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
fw.close()
elif(class_name == 'sheep'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
fw.write(str(image_name)+' '+'n02415577'+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')   #大角羊
fw.close()
elif(class_name == 'sofa'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
fw.close()
elif(class_name == 'train'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
fw.write(str(image_name)+' '+'n02917067'+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')  #子弹头列车
fw.close()
elif(class_name == 'tvmonitor'):
fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
fw.write(str(image_name)+' '+class_name+' '+str(int(bbox[0]))+' '+str(int(bbox[1]))+' '+str(int(bbox[2]))+' '+str(int(bbox[3]))+'\n')
fw.close()

def demo(net, image_name):
"""Detect object classes in an image using pre-computed object proposals."""

# Load the demo image
#im_file = os.path.join(cfg.DATA_DIR, 'demo', image_name)
im_file = os.path.join('/','media','zc','A','Imagenet2012','img_train','n01440764',image_name)                  #改成你图片的位置
im = cv2.imread(im_file)

# Detect all object classes and regress object bounds
timer = Timer()
timer.tic()
scores, boxes = im_detect(net, im)
timer.toc()
print ('Detection took {:.3f}s for '
'{:d} object proposals').format(timer.total_time, boxes.shape[0])

# Visualize detections for each class
CONF_THRESH = 0.8
NMS_THRESH = 0.3

#fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
#fw.write(str(image_name)+'\t')
#fw.close()

for cls_ind, cls in enumerate(CLASSES[1:]):
cls_ind += 1 # because we skipped background
cls_boxes = boxes[:, 4*cls_ind:4*(cls_ind + 1)]
cls_scores = scores[:, cls_ind]
dets = np.hstack((cls_boxes,
cls_scores[:, np.newaxis])).astype(np.float32)
keep = nms(dets, NMS_THRESH)
dets = dets[keep, :]
vis_detections(image_name, cls, dets, thresh=CONF_THRESH)
#fw = open('/media/zc/A/Imagenet2012/img_train/n01440764/result.txt','a')
#fw.write('\n')
#fw.close()

def parse_args():
"""Parse input arguments."""
parser = argparse.ArgumentParser(description='Faster R-CNN demo')
parser.add_argument('--gpu', dest='gpu_id', help='GPU device id to use [0]',
default=0, type=int)
parser.add_argument('--cpu', dest='cpu_mode',
help='Use CPU mode (overrides --gpu)',
action='store_true')
parser.add_argument('--net', dest='demo_net', help='Network to use [vgg16]',
choices=NETS.keys(), default='vgg16')

args = parser.parse_args()

return args

if __name__ == '__main__':
cfg.TEST.HAS_RPN = True  # Use RPN for proposals

args = parse_args()

prototxt = os.path.join(cfg.MODELS_DIR, NETS[args.demo_net][0],
'faster_rcnn_alt_opt', 'faster_rcnn_test.pt')
caffemodel = os.path.join(cfg.DATA_DIR, 'faster_rcnn_models',
NETS[args.demo_net][1])

if not os.path.isfile(caffemodel):
raise IOError(('{:s} not found.\nDid you run ./data/script/'
'fetch_faster_rcnn_models.sh?').format(caffemodel))

if args.cpu_mode:
caffe.set_mode_cpu()
else:
caffe.set_mode_gpu()
caffe.set_device(args.gpu_id)
cfg.GPU_ID = args.gpu_id
net = caffe.Net(prototxt, caffemodel, caffe.TEST)

print '\n\nLoaded network {:s}'.format(caffemodel)

# Warmup on a dummy image
im = 128 * np.ones((300, 500, 3), dtype=np.uint8)
for i in xrange(2):
_, _= im_detect(net, im)

#im_names = ['000456.jpg', '000542.jpg', '001150.jpg',
#            '001763.jpg', '004545.jpg']

fr = open('/media/zc/A/Imagenet2012/img_train/n01440764/temp.txt','r')          #这个txt里面保存的是图片的名字，一行一个
for im_name in fr:
im_name = im_name.strip('\n')
print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
print 'Demo for data/demo/{}'.format(im_name)

demo(net, im_name)

plt.show()
fr.close

再用一个matlab代码，就可以把txt转化成xml,感谢小咸鱼的分享，如果你的图片是jpg，只要修改四个变量就能用，十分方便，如果是JPEG,下面还要修改两个地方，我注释了

%%
%该代码可以做voc2007数据集中的xml文件，
%txt文件每行格式为：000002.jpg dog 44 28 132 121
%即每行由图片名、目标类型、包围框坐标组成，空格隔开
%如果一张图片有多个目标，则格式如下：（比如两个目标）
%000002.jpg dog 44 28 132 121
%000002.jpg car 50 27 140 110
%包围框坐标为左上角和右下角
%作者：小咸鱼_
%CSDN:http://blog.csdn.net/sinat_30071459
%%
clc;
clear;
%注意修改下面四个变量
imgpath='img\';%图像存放文件夹
txtpath='img\output.txt';%txt文件
xmlpath_new='Annotations/';%修改后的xml保存文件夹
foldername='VOC2007';%xml的folder字段名

fidin=fopen(txtpath,'r');
lastname='begin';

while ~feof(fidin)
tline=fgetl(fidin);
str = regexp(tline, ' ','split');
filepath=[imgpath,str{1}];
img=imread(filepath);
[h,w,d]=size(img);
imshow(img);
rectangle('Position',[str2double(str{3}),str2double(str{4}),str2double(str{5})-str2double(str{3}),str2double(str{6})-str2double(str{4})],'LineWidth',4,'EdgeColor','r');
pause(0.1);

if strcmp(str{1},lastname)%如果文件名相等，只需增加object
object_node=Createnode.createElement('object');
Root.appendChild(object_node);
node=Createnode.createElement('name');
node.appendChild(Createnode.createTextNode(sprintf('%s',str{2})));
object_node.appendChild(node);

node=Createnode.createElement('pose');
node.appendChild(Createnode.createTextNode(sprintf('%s','Unspecified')));
object_node.appendChild(node);

node=Createnode.createElement('truncated');
node.appendChild(Createnode.createTextNode(sprintf('%s','0')));
object_node.appendChild(node);

node=Createnode.createElement('difficult');
node.appendChild(Createnode.createTextNode(sprintf('%s','0')));
object_node.appendChild(node);

bndbox_node=Createnode.createElement('bndbox');
object_node.appendChild(bndbox_node);

node=Createnode.createElement('xmin');
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(str{3}))));
bndbox_node.appendChild(node);

node=Createnode.createElement('ymin');
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(str{4}))));
bndbox_node.appendChild(node);

node=Createnode.createElement('xmax');
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(str{5}))));
bndbox_node.appendChild(node);

node=Createnode.createElement('ymax');
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(str{6}))));
bndbox_node.appendChild(node);
else %如果文件名不等，则需要新建xml
copyfile(filepath, 'JPEGImages');
%先保存上一次的xml
if exist('Createnode','var')
tempname=lastname;
tempname=strrep(tempname,'.jpg','.xml');                                                                          %你的图片是JPEG,这里就要把jpg改成JPEG
xmlwrite(tempname,Createnode);
end

Createnode=com.mathworks.xml.XMLUtils.createDocument('annotation');
Root=Createnode.getDocumentElement;%根节点
node=Createnode.createElement('folder');
node.appendChild(Createnode.createTextNode(sprintf('%s',foldername)));
Root.appendChild(node);
node=Createnode.createElement('filename');
node.appendChild(Createnode.createTextNode(sprintf('%s',str{1})));
Root.appendChild(node);
source_node=Createnode.createElement('source');
Root.appendChild(source_node);
node=Createnode.createElement('database');
node.appendChild(Createnode.createTextNode(sprintf('My Database')));
source_node.appendChild(node);
node=Createnode.createElement('annotation');
node.appendChild(Createnode.createTextNode(sprintf('VOC2007')));
source_node.appendChild(node);

node=Createnode.createElement('image');
node.appendChild(Createnode.createTextNode(sprintf('flickr')));
source_node.appendChild(node);

node=Createnode.createElement('flickrid');
node.appendChild(Createnode.createTextNode(sprintf('NULL')));
source_node.appendChild(node);
owner_node=Createnode.createElement('owner');
Root.appendChild(owner_node);
node=Createnode.createElement('flickrid');
node.appendChild(Createnode.createTextNode(sprintf('NULL')));
owner_node.appendChild(node);

node=Createnode.createElement('name');
node.appendChild(Createnode.createTextNode(sprintf('xiaoxianyu')));
owner_node.appendChild(node);
size_node=Createnode.createElement('size');
Root.appendChild(size_node);

node=Createnode.createElement('width');
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(w))));
size_node.appendChild(node);

node=Createnode.createElement('height');
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(h))));
size_node.appendChild(node);

node=Createnode.createElement('depth');
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(d))));
size_node.appendChild(node);

node=Createnode.createElement('segmented');
node.appendChild(Createnode.createTextNode(sprintf('%s','0')));
Root.appendChild(node);
object_node=Createnode.createElement('object');
Root.appendChild(object_node);
node=Createnode.createElement('name');
node.appendChild(Createnode.createTextNode(sprintf('%s',str{2})));
object_node.appendChild(node);

node=Createnode.createElement('pose');
node.appendChild(Createnode.createTextNode(sprintf('%s','Unspecified')));
object_node.appendChild(node);

node=Createnode.createElement('truncated');
node.appendChild(Createnode.createTextNode(sprintf('%s','0')));
object_node.appendChild(node);

node=Createnode.createElement('difficult');
node.appendChild(Createnode.createTextNode(sprintf('%s','0')));
object_node.appendChild(node);

bndbox_node=Createnode.createElement('bndbox');
object_node.appendChild(bndbox_node);

node=Createnode.createElement('xmin');
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(str{3}))));
bndbox_node.appendChild(node);

node=Createnode.createElement('ymin');
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(str{4}))));
bndbox_node.appendChild(node);

node=Createnode.createElement('xmax');
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(str{5}))));
bndbox_node.appendChild(node);

node=Createnode.createElement('ymax');
node.appendChild(Createnode.createTextNode(sprintf('%s',num2str(str{6}))));
bndbox_node.appendChild(node);

lastname=str{1};
end
%处理最后一行
if feof(fidin)
tempname=lastname;
tempname=strrep(tempname,'.jpg','.xml');                                                         %你的图片是JPEG,这里就要把jpg改成JPEG
xmlwrite(tempname,Createnode);
end
end
fclose(fidin);

file=dir(pwd);
for i=1:length(file)
if length(file(i).name)>=4 && strcmp(file(i).name(end-3:end),'.xml')
fold=fopen(file(i).name,'r');
fnew=fopen([xmlpath_new file(i).name],'w');
line=1;
while ~feof(fold)
tline=fgetl(fold);
if line==1
line=2;
continue;
end
expression = '   ';
replace=char(9);
newStr=regexprep(tline,expression,replace);
fprintf(fnew,'%s\n',newStr);
end
fprintf('已处理%s\n',file(i).name);
fclose(fold);
fclose(fnew);
delete(file(i).name);
end
end