python:批量统计xml中各类目标的数量案例

之前写了一个matlab的，越用越觉得麻烦，如果不同数据集要改类别数目，而且运行速度慢。所以重新写了一个Python的，直接读取xml文件夹路径就可以，不用预先知道类别，直接能够检测出所有类别的目标名称及其对应的数量。

分享出来给大家。

代码如下：

# -*- coding:utf-8 -*-
import os
import xml.etree.ElementTree as ET
import numpy as np
np.set_printoptions(suppress=True, threshold=np.nan)
import matplotlib
from PIL import Image
 
def parse_obj(xml_path, filename):
 tree=ET.parse(xml_path+filename)
 objects=[]
 for obj in tree.findall(\'object\'):
 obj_struct={}
 obj_struct[\'name\']=obj.find(\'name\').text
 objects.append(obj_struct)
 return objects
 
 
def read_image(image_path, filename):
 im=Image.open(image_path+filename)
 W=im.size[0]
 H=im.size[1]
 area=W*H
 im_info=[W,H,area]
 return im_info
 
 
if __name__ == \'__main__\':
 xml_path=\'C:/Users/nansbas/Desktop/hebin/03/\'
 filenamess=os.listdir(xml_path)
 filenames=[]
 for name in filenamess:
 name=name.replace(\'.xml\',\'\')
 filenames.append(name)
 recs={}
 obs_shape={}
 classnames=[]
 num_objs={}
 obj_avg={}
 for i,name in enumerate(filenames):
 recs[name]=parse_obj(xml_path, name+ \'.xml\' )
 for name in filenames:
 for object in recs[name]:
 if object[\'name\'] not in num_objs.keys():
  num_objs[object[\'name\']]=1
 else:
  num_objs[object[\'name\']]+=1
 if object[\'name\'] not in classnames:
  classnames.append(object[\'name\'])
 for name in classnames:
 print(\'{}:{}个\'.format(name,num_objs[name]))
 print(\'信息统计算完毕。\')

补充知识：Python对目标检测数据集xml文件操作（统计目标种类、数量、面积、比例等&修改目标名字）

1. 根据xml文件统计目标种类以及数量

# -*- coding:utf-8 -*-
#根据xml文件统计目标种类以及数量
import os
import xml.etree.ElementTree as ET
import numpy as np
np.set_printoptions(suppress=True, threshold=np.nan)
import matplotlib
from PIL import Image
 
def parse_obj(xml_path, filename):
 tree=ET.parse(xml_path+filename)
 objects=[]
 for obj in tree.findall(\'object\'):
 obj_struct={}
 obj_struct[\'name\']=obj.find(\'name\').text
 objects.append(obj_struct)
 return objects
 
 
def read_image(image_path, filename):
 im=Image.open(image_path+filename)
 W=im.size[0]
 H=im.size[1]
 area=W*H
 im_info=[W,H,area]
 return im_info
 
 
if __name__ == \'__main__\':
 xml_path=\'/home/dlut/网络/make_database/数据集——合集/VOCdevkit/VOC2018/Annotations/\'
 filenamess=os.listdir(xml_path)
 filenames=[]
 for name in filenamess:
 name=name.replace(\'.xml\',\'\')
 filenames.append(name)
 recs={}
 obs_shape={}
 classnames=[]
 num_objs={}
 obj_avg={}
 for i,name in enumerate(filenames):
 recs[name]=parse_obj(xml_path, name+ \'.xml\' )
 for name in filenames:
 for object in recs[name]:
  if object[\'name\'] not in num_objs.keys():
   num_objs[object[\'name\']]=1
  else:
   num_objs[object[\'name\']]+=1
  if object[\'name\'] not in classnames:
   classnames.append(object[\'name\'])
 for name in classnames:
 print(\'{}:{}个\'.format(name,num_objs[name]))
 print(\'信息统计算完毕。\')

2.根据xml文件统计目标的平均长度、宽度、面积以及每一个目标在原图中的占比

# -*- coding:utf-8 -*-
#统计
# 计算每一个目标在原图中的占比
# 计算目标的平均长度、
# 计算平均宽度，
# 计算平均面积、
# 计算目标平均占比

import os
import xml.etree.ElementTree as ET
import numpy as np

#np.set_printoptions(suppress=True, threshold=np.nan) #10,000,000
np.set_printoptions(suppress=True, threshold=10000000) #10,000,000
import matplotlib
from PIL import Image


def parse_obj(xml_path, filename):
 tree = ET.parse(xml_path + filename)
 objects = []
 for obj in tree.findall(\'object\'):
  obj_struct = {}
  obj_struct[\'name\'] = obj.find(\'name\').text
  bbox = obj.find(\'bndbox\')
  obj_struct[\'bbox\'] = [int(bbox.find(\'xmin\').text),
        int(bbox.find(\'ymin\').text),
        int(bbox.find(\'xmax\').text),
        int(bbox.find(\'ymax\').text)]
  objects.append(obj_struct)
 return objects


def read_image(image_path, filename):
 im = Image.open(image_path + filename)
 W = im.size[0]
 H = im.size[1]
 area = W * H
 im_info = [W, H, area]
 return im_info


if __name__ == \'__main__\':
 image_path = \'/home/dlut/网络/make_database/数据集——合集/VOCdevkit/VOC2018/JPEGImages/\'
 xml_path = \'/home/dlut/网络/make_database/数据集——合集/VOCdevkit/VOC2018/Annotations/\'
 filenamess = os.listdir(xml_path)
 filenames = []
 for name in filenamess:
  name = name.replace(\'.xml\', \'\')
  filenames.append(name)
 print(filenames)
 recs = {}
 ims_info = {}
 obs_shape = {}
 classnames = []
 num_objs={}
 obj_avg = {}
 for i, name in enumerate(filenames):
  print(\'正在处理 {}.xml \'.format(name))
  recs[name] = parse_obj(xml_path, name + \'.xml\')
  print(\'正在处理 {}.jpg \'.format(name))
  ims_info[name] = read_image(image_path, name + \'.jpg\')
 print(\'所有信息收集完毕。\')
 print(\'正在处理信息......\')
 for name in filenames:
  im_w = ims_info[name][0]
  im_h = ims_info[name][1]
  im_area = ims_info[name][2]
  for object in recs[name]:
   if object[\'name\'] not in num_objs.keys():
    num_objs[object[\'name\']] = 1
   else:
    num_objs[object[\'name\']] += 1
   #num_objs += 1
   ob_w = object[\'bbox\'][2] - object[\'bbox\'][0]
   ob_h = object[\'bbox\'][3] - object[\'bbox\'][1]
   ob_area = ob_w * ob_h
   w_rate = ob_w / im_w
   h_rate = ob_h / im_h
   area_rate = ob_area / im_area
   if not object[\'name\'] in obs_shape.keys():
    obs_shape[object[\'name\']] = ([[ob_w,
            ob_h,
            ob_area,
            w_rate,
            h_rate,
            area_rate]])
   else:
    obs_shape[object[\'name\']].append([ob_w,
             ob_h,
             ob_area,
             w_rate,
             h_rate,
             area_rate])
  if object[\'name\'] not in classnames:
   classnames.append(object[\'name\']) # 求平均

 for name in classnames:
  obj_avg[name] = (np.array(obs_shape[name]).sum(axis=0)) / num_objs[name]
  print(\'{}的情况如下：*******\\n\'.format(name))
  print(\' 目标平均W={}\'.format(obj_avg[name][0]))
  print(\' 目标平均H={}\'.format(obj_avg[name][1]))
  print(\' 目标平均area={}\'.format(obj_avg[name][2]))
  print(\' 目标平均与原图的W比例={}\'.format(obj_avg[name][3]))
  print(\' 目标平均与原图的H比例={}\'.format(obj_avg[name][4]))
  print(\' 目标平均原图面积占比={}\\n\'.format(obj_avg[name][5]))
 print(\'信息统计计算完毕。\')

3.修改xml文件中某个目标的名字为另一个名字

#修改xml文件中的目标的名字，
import os, sys
import glob
from xml.etree import ElementTree as ET

# 批量读取Annotations下的xml文件
# per=ET.parse(r\'C:\\Users\\rockhuang\\Desktop\\Annotations\\000003.xml\')
xml_dir = r\'/home/dlut/网络/make_database/数据集——合集/VOCdevkit/VOC2018/Annotations\'
xml_list = glob.glob(xml_dir + \'/*.xml\')
for xml in xml_list:
 print(xml)
 per = ET.parse(xml)
 p = per.findall(\'/object\')

 for oneper in p: # 找出person节点
  child = oneper.getchildren()[0] # 找出person节点的子节点
  if child.text == \'PinNormal\': #需要修改的名字
   child.text = \'normal bolt\' #修改成什么名字
  if child.text == \'PinDefect\': #需要修改的名字
   child.text = \'defect bolt-1\' #修改成什么名字

 per.write(xml)
 print(child.tag, \':\', child.text)