Python 统计数据集标签的类别及数目操作

看了大神统计voc数据集标签框后，针对自己标注数据集，灵活应用，感谢！

看代码吧~

import re
import os
import xml.etree.ElementTree as ET
class1 = \'answer\'
class2 = \'hand\'
class3 = \'write\'
class4 = \'music\'
class5 = \'phone\'
\'\'\'class6 = \'bus\'
class7 = \'car\'
class8 = \'cat\'
class9 = \'chair\'
class10 = \'cow\'
class11 = \'diningtable\'
class12 = \'dog\'
class13 = \'horse\'
class14 = \'motorbike\'
class15 = \'person\'
class16 = \'pottedplant\'
class17 = \'sheep\'
class18 = \'sofa\'
class19 = \'train\'
class20 = \'tvmonitor\'
\'\'\'
annotation_folder = \'/home/.../train/\'		#改为自己标签文件夹的路径
#annotation_folder = \'/home/.../VOC2007/Annotations/\'
list = os.listdir(annotation_folder)
  
def file_name(file_dir):
	L = []
	for root, dirs, files in os.walk(file_dir):
		for file in files:
			if os.path.splitext(file)[1] == \'.xml\':
				L.append(os.path.join(root, file))
	return L
  
total_number1 = 0
total_number2 = 0
total_number3 = 0
total_number4 = 0
total_number5 = 0
\'\'\'total_number6 = 0
total_number7 = 0
total_number8 = 0
total_number9 = 0
total_number10 = 0
total_number11 = 0
total_number12 = 0
total_number13 = 0
total_number14 = 0
total_number15 = 0
total_number16 = 0
total_number17 = 0
total_number18 = 0
total_number19 = 0
total_number20 = 0\'\'\'
total = 0
total_pic=0
 
pic_num1 = 0
pic_num2 = 0
pic_num3 = 0
pic_num4 = 0
pic_num5 = 0
\'\'\'pic_num6 = 0
pic_num7 = 0
pic_num8 = 0
pic_num9 = 0
pic_num10 = 0
pic_num11 = 0
pic_num12 = 0
pic_num13 = 0
pic_num14 = 0
pic_num15 = 0
pic_num16 = 0
pic_num17 = 0
pic_num18 = 0
pic_num19 = 0
pic_num20 = 0\'\'\'
 
flag1 = 0
flag2 = 0
flag3 = 0
flag4 = 0
flag5 = 0
\'\'\'flag6 = 0
flag7 = 0
flag8 = 0
flag9 = 0
flag10 = 0
flag11 = 0
flag12 = 0
flag13 = 0
flag14 = 0
flag15= 0
flag16 = 0
flag17 = 0
flag18 = 0
flag19 = 0
flag20 = 0\'\'\'
 
xml_dirs = file_name(annotation_folder) 
for i in range(0, len(xml_dirs)):
	print(xml_dirs[i])
	#path = os.path.join(annotation_folder,list[i])
	#print(path)
 
	annotation_file = open(xml_dirs[i]).read()
 
	root = ET.fromstring(annotation_file)
	#tree = ET.parse(annotation_file)
	#root = tree.getroot()
 
	total_pic = total_pic + 1
	for obj in root.findall(\'object\'):
		label = obj.find(\'name\').text
		if label == class1:
			total_number1=total_number1+1
			flag1=1
			total = total + 1
			#print(\"bounding box number:\", total_number1)
		if label == class2:
			total_number2=total_number2+1
			flag2=1
			total = total + 1
		if label == class3:
			total_number3=total_number3+1
			flag3=1
			total = total + 1
		if label == class4:
			total_number4=total_number4+1
			flag4=1
			total = total + 1
		if label == class5:
			total_number5=total_number5+1
			flag5=1
			total = total + 1
		\'\'\'if label == class6:
			total_number6=total_number6+1
			flag6=1
			total = total + 1
		if label == class7:
			total_number7=total_number7+1
			flag7=1
			total = total + 1
		if label == class8:
			total_number8=total_number8+1
			flag8=1
			total = total + 1
		if label == class9:
			total_number9=total_number9+1
			flag9=1
			total = total + 1
		if label == class10:
			total_number10=total_number10+1
			flag10=1
			total = total + 1
		if label == class11:
			total_number11=total_number11+1
			flag11=1
			total = total + 1
		if label == class12:
			total_number12=total_number12+1
			flag12=1
			total = total + 1
		if label == class13:
			total_number13=total_number13+1
			flag13=1
			total = total + 1
		if label == class14:
			total_number14=total_number14+1
			flag14=1
			total = total + 1
		if label == class15:
			total_number15=total_number15+1
			flag15=1
			total = total + 1
		if label == class16:
			total_number16=total_number16+1
			flag16=1
			total = total + 1
		if label == class17:
			total_number17=total_number17+1
			flag17=1
			total = total + 1
		if label == class18:
			total_number18=total_number18+1
			flag18=1
			total = total + 1
		if label == class19:
			total_number19=total_number19+1
			flag19=1
			total = total + 1
		if label == class20:
			total_number20=total_number20+1
			flag20=1
			total = total + 1\'\'\'
 
	if flag1==1:
		pic_num1=pic_num1+1
		#print(\"pic number:\", pic_num1)
		flag1=0
	if flag2==1:
		pic_num2=pic_num2+1
		flag2=0
	if flag3==1:
		pic_num3=pic_num3+1
		flag3=0
	if flag4==1:
		pic_num4=pic_num4+1
		flag4=0
	if flag5==1:
		pic_num5=pic_num5+1
		flag5=0
	\'\'\'if flag6==1:
		pic_num6=pic_num6+1
		flag6=0
	if flag7==1:
		pic_num7=pic_num7+1
		flag7=0
	if flag8==1:
		pic_num8=pic_num8+1
		flag8=0
	if flag9==1:
		pic_num9=pic_num9+1
		flag9=0
	if flag10==1:
		pic_num10=pic_num10+1
		flag10=0
	if flag11==1:
		pic_num11=pic_num11+1
		flag11=0
	if flag12==1:
		pic_num12=pic_num12+1
		flag12=0
	if flag13==1:
		pic_num13=pic_num13+1
		flag13=0
	if flag14==1:
		pic_num14=pic_num14+1
		flag14=0
	if flag15==1:
		pic_num15=pic_num15+1
		flag15=0
	if flag16==1:
		pic_num16=pic_num16+1
		flag16=0
	if flag17==1:
		pic_num17=pic_num17+1
		flag17=0
	if flag18==1:
		pic_num18=pic_num18+1
		flag18=0
	if flag19==1:
		pic_num19=pic_num19+1
		flag19=0
	if flag20==1:
		pic_num20=pic_num20+1
		flag20=0\'\'\'
  
print(class1,pic_num1,total_number1)
print(class2,pic_num2,total_number2)
print(class3,pic_num3, total_number3)
print(class4,pic_num4, total_number4)
print(class5,pic_num5, total_number5)
\'\'\'print(class6,pic_num6, total_number6)
print(class7,pic_num7, total_number7)
print(class8,pic_num8, total_number8)
print(class9,pic_num9, total_number9)
print(class10,pic_num10, total_number10)
print(class11,pic_num11,total_number11)
print(class12,pic_num12,total_number12)
print(class13,pic_num13, total_number13)
print(class14,pic_num14, total_number14)
print(class15,pic_num15, total_number15)
print(class16,pic_num16, total_number16)
print(class17,pic_num17, total_number17)
print(class18,pic_num18, total_number18)
print(class19,pic_num19, total_number19)
print(class20,pic_num20, total_number20)\'\'\'
 
print(\"total\", total_pic, total)

补充：【数据集处理】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)