VOC格式标签转换为yolo格式的标签

VOC格式标签转换为yolo格式的标签

xml -> txt

# _*_ coding:utf-8 _*_
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
"""已知标签名,xml -> txt"""

imgs_path = './images_fire/'   #图片路径
anns_path = './labels_fire/'  #xml标签路径
ann_save_path = './labels/'   #txt标签保存路径

if not os.path.exists(ann_save_path):
    os.makedirs(ann_save_path)
anns = os.listdir(anns_path)

# classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
classes = ["fire"]      #类别名,顺序随便,需要更改为自己的


def convert(size, box):
    dw = 1. / size[0]
    dh = 1. / size[1]
    x = (box[0] + box[1]) / 2.0
    y = (box[2] + box[3]) / 2.0
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x * dw
    w = w * dw
    y = y * dh
    h = h * dh
    return (x, y, w, h)


def convert_annotation(ann, totle_name):
    # in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml' % (year, image_id), encoding='UTF-8')
    # out_file = open('VOCdevkit/VOC%s/labels/%s.txt' % (year, image_id), 'w')
    in_file = open(anns_path+ann,'r')
    out_file = open(ann_save_path+totle_name+'.txt','w')

    tree = ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)
    for obj in root.iter('object'):
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        # print(count)
        if cls not in classes or int(difficult) == 1:
            continue
        # elif str(cls) == 'quandin':
        #   cls = 'quanding'
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
             float(xmlbox.find('ymax').text))
        bb = convert((w, h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')


# wd = getcwd()


num = 0
for ann in anns:
    ann = ann.split('.')
    totle_name = ann[0]
    ann =str.join('.' ,ann)
    convert_annotation(ann, totle_name)
    num+=1
    print('num----------------------------',num)

版权声明:本文为CSDN博主「AI余小晖」的原创文章,遵循CC 4.0 BY-SA版权协议,转载请附上原文出处链接及本声明。
原文链接:https://blog.csdn.net/weixin_51154380/article/details/121914731

AI余小晖

我还没有学会写个人说明!

暂无评论

发表评论

相关推荐

弱监督目标检测与半监督目标检测

一、监督学习分类 根据数据集的标注情况,分为:监督学习、弱监督学习、弱半监督学习和半监督学习。 监督学习:数据集为带实例级标注的标签,包含坐标和类别信息 弱监督学习:数据

YOLOV1论文详解

YOLOV1 1. Introduction YOLO非常简单:对于一张完整的图像,通过一个单一的卷积网络可以同时预测多个bounding boxes的回归参数和这些boxes的类别概率,并直接优化检

【darknet】1、yolov4模型训练之数据处理

本文主要写了使用yolov4进行模型训练前的数据准备。darknet框架使用的数据格式是yolo格式,但我们常见的目标检测数据格式是COCO和VOC.所以本文将以车辆检测为例,将coco2017和voc2007及vo