python计算xml中各类的数量

最新推荐文章于 2024-07-17 17:53:42 发布

我劲歌

最新推荐文章于 2024-07-17 17:53:42 发布

阅读量349

点赞数

文章标签：大数据 python xml

本文链接：https://blog.csdn.net/qq_34835428/article/details/125757649

版权

PASCAL VOC XML解析图像信息对象统计图像标注

关键词由CSDN通过智能技术生成

# -*- 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='voc/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。')