VOC格式数据集转换YOLO格式

最新推荐文章于 2024-07-09 20:07:16 发布

小远披荆斩棘

最新推荐文章于 2024-07-09 20:07:16 发布

阅读量372

点赞数 8

文章标签： YOLO python 人工智能

本文链接：https://blog.csdn.net/qq_45232776/article/details/135613757

版权

本文介绍了如何使用Python脚本将VOC格式的XML对象检测标注转换为YOLO所需的标签格式，包括读取XML文件、解析boundingbox信息并进行坐标转换。

摘要由CSDN通过智能技术生成

import xml.etree.ElementTree as ET
import os

# VOC的类别列表，需要根据实际情况修改
classes = ["class1", "class2", "class3", ...]

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(voc_path, yolo_path, image_id):
    in_file = open(os.path.join(voc_path, 'Annotations', image_id + '.xml'))
    out_file = open(os.path.join(yolo_path, 'labels', image_id + '.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
        if cls not in classes or int(difficult) == 1:
            continue
        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')

voc_path = 'path/to/VOCdevkit/VOC2007'  # VOC数据集路径
yolo_path = 'path/to/yolo'              # YOLO格式的输出路径

# 创建YOLO格式的labels文件夹
if not os.path.exists(os.path.join(yolo_path, 'labels')):
    os.makedirs(os.path.join(yolo_path, 'labels'))

# 转换所有的XML文件
image_ids = os.listdir(os.path.join(voc_path, 'Annotations'))
for image_id in image_ids:
    image_id = image_id.replace('.xml', '')
    convert_annotation(voc_path, yolo_path, image_id)