目标检测-根据YOLO格式标签统计类别数量

#计算txt标签格式每个类别的数量
import os
from tqdm import tqdm
def get_every_class_num(txt_path):
    # 需修改，根据自己的类别，注意一一对应
    class_categories=['Cahua', 'Crazing', 'Patches', 'Inclusion', 'Uneven', 'Blowhole', 'Break', 'Crack', 'Yueyawan', 'Zhehen', 'Siban', 'Shuiban', 'Hanfeng', 'Yiwu', 'Youban', 'Yahen', 'Chongkong', 'Yaozhe', 'Pengshang', 'Pitted_Surface', 'Rolled-in_Scale', 'Scratches', 'Tufen']
    class_num = len(class_categories)  # 样本类别数
    class_list = [i for i in range(class_num)]
    class_num_list = [0 for i in range(class_num)]
    labels_list = os.listdir(txt_path)
    for i in tqdm(labels_list):
        file_path = os.path.join(txt_path, i)
        file = open(file_path, 'r')  # 打开文件
        file_data = file.readlines()  # 读取所有行
        for every_row in file_data:
            class_val = every_row.split(' ')[0]
            class_ind = class_list.index(int(class_val))
            class_num_list[class_ind] += 1
        file.close()
    # 输出每一类的数量以及总数
    result=dict(zip(class_categories,class_num_list))
    for name,num in result.items():
        print(name,":",num)
    print("-----------------------------------")
    print('total:', sum(class_num_list))
if __name__ == '__main__':
    # 需修改，txt文件所在路径
    txt_path = r'D:\desk\defect_dataset\labels\val'
    get_every_class_num(txt_path)

---

需要修改部分讲解

第5行

根据自己的类别进行修改，注意对应自己的类别

    # 需修改，根据自己的类别，注意一一对应
    class_categories=['Cahua', 'Crazing', 'Patches', 'Inclusion', 'Uneven', 'Blowhole', 'Break', 'Crack', 'Yueyawan', 'Zhehen', 'Siban', 'Shuiban', 'Hanfeng', 'Yiwu', 'Youban', 'Yahen', 'Chongkong', 'Yaozhe', 'Pengshang', 'Pitted_Surface', 'Rolled-in_Scale', 'Scratches', 'Tufen']

第27行

修改为自己的标签所在路径即可

    # 需修改，txt文件所在路径
    txt_path = r'D:\desk\defect_dataset\labels\val'

实验准备

YOLO格式标签若干张

运行结果

---

 附：利用VOC格式统计类别数

# -*- 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
import sys
np.set_printoptions(threshold=sys.maxsize)

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__':
    #需修改为自己的VOC标签路径
    xml_path = 'D:\desk\defect_dataset\VOC/'
    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。')

运行此代码仅需修改

第29行即可运行

---

本文代码借鉴了：Python 统计YOLO（txt）格式标签中各类别样本数_yolo中如何查看标签中每个类别数量多少-CSDN博客
目标检测中计算数据集每一类别框的数量_目标检测预测结果可以知道预测框的数量吗-CSDN博客
 

---

代码仅供自己学习使用