代码
import xml.etree.ElementTree as ET import pickle import os from os import listdir, getcwd from os.path import join classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"] # 换上你标签 # 改变坐标格式 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) xml_path = "D:/2022.11/MetaPruning-master/VOCdevkit/VOC2007/Annotations/" txt_path = "D:/2022.11/MetaPruning-master/VOCdevkit/VOC2007/AnnotationsTXT/" def convert_annotation(xml_path, txt_path): if not os.path.exists(txt_path): os.mkdir(txt_path) for image_id in os.listdir(xml_path): # print(xml_path+image_id) xml_file = open(xml_path + image_id) txt_file = open(txt_path + image_id[:-3] + "txt", "a") tree = ET.parse(xml_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 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) txt_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n') convert_annotation(xml_path, txt_path) 输出
//2007_000346.txt
15 0.274000 0.208000 0.994000 1.000000
15 0.178000 0.538667 0.258000 0.658667
15 0.144000 0.557333 0.222000 0.690667
5 0.248000 0.285333 0.460000 0.914667
核心代码参考
使用python将voc类型标注xml文件对图片进行目标还原,以及批量裁剪特定类_三寸光阴___的博客-CSDN博客_剪切voc标注图像