[人工智能]标注转yolo格式

# !/usr/bin/env python
# -*- coding: utf-8 -*-




import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from imutils import paths
import cv2
from tqdm import tqdm

classes = []

def raad_voc_names(txt_path):
    with open(txt_path, 'r') as f:
        for line in f.readlines():
            line = line.strip()
            classes.append(line)



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(xml_root, anno_txt_root, image_id, Image_root):
    in_file = open(os.path.join(xml_root, '{}.xml'.format(image_id)))
    out_file = open(os.path.join(anno_txt_root, '{}.txt'.format(image_id)), 'w')
    tree = ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')  # 根据不同的xml标注习惯修改
    if size:
        w = int(size.find('width').text)
        h = int(size.find('height').text)
    else:
        jpg_img_patch = Image_root + image_id + '.jpg'
        jpg_img = cv2.imread(jpg_img_patch)
        h, w, _ = jpg_img.shape  # cv2读取的图片大小格式是w,h

    for obj in root.iter('object'):
        difficult = obj.find('difficult')
        if difficult:
            difficult = obj.find('difficult').text
        else:
            difficult = 0
        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')


if __name__ == '__main__':

    wd = getcwd()
    print(wd)
    voc_names = os.path.join(wd, 'voc.names')
    raad_voc_names(voc_names)

    Image_root = r'D:\data\voc\VOCdevkit\VOC2007\JPEGImages'
    xml_root = r'D:\data\voc\VOCdevkit\VOC2007\Annotations'
    yolo_anno = r'D:\data\voc\VOCdevkit\VOC2007\yolo_anno'

    fileList = os.listdir(Image_root)
    for path in tqdm(fileList):
        image_ids = path.split(".")
        image_id = image_ids[0]
        convert_annotation(xml_root, yolo_anno, image_id, Image_root)

Reference:

https://blog.csdn.net/jiugeshao/article/details/116084611