将数据集的VOC格式转为yolo格式

将数据集的VOC格式转为yolo格式

# -*- coding: utf-8 -*-
import xml.etree.ElementTree as ET
import os
import shutil


def convert(size, box):
    dw = 1. / (size[0])
    dh = 1. / (size[1])
    x = (box[0] + box[1]) / 2.0 - 1
    y = (box[2] + box[3]) / 2.0 - 1
    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(image_set, image_id, voc_path):
    in_file = open(voc_path + '/Annotations/%s.xml' % (image_id), encoding='UTF-8')
    out_file = open('./labels/%s/%s.txt' % (image_set, image_id), '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
        # difficult = obj.find('Difficult').text
        cls = obj.find('name').text
        # if cls not in classes or int(difficult) == 1:
        if cls not in classes:
            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))
        b1, b2, b3, b4 = b
        # 标注越界修正
        if b2 > w:
            b2 = w
        if b4 > h:
            b4 = h
        b = (b1, b2, b3, b4)
        bb = convert((w, h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')


if __name__ == "__main__":
    sets = ['train', 'val', 'test']     # 对应voc中的数据集被划分的部分（在Main文件夹中）
    classes = ['hand']  # 改成自己的类别
    voc_path = "E:/study/object_detection/YOLO_series/datasets/VOC2007_hand"
    abs_path = os.getcwd()   # 当前根路径
    print(abs_path)

    for image_set in sets:
        if not os.path.exists('./labels/'+image_set) and image_set in ['train', 'val']:
            os.makedirs('./labels/'+image_set)
        if not os.path.exists('./images/'+image_set) and image_set in ['train', 'val']:
            os.makedirs('./images/'+image_set)

        image_ids = open(voc_path + '/ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
        list_file = open('./%s.txt' % (image_set), 'w')

        for image_id in image_ids:
            list_file.write('./images/%s/%s.jpg\n' % (image_set, image_id))   # 创建三个txt
            convert_annotation(image_set, image_id, voc_path)  # 创建train和val的每张图片的txt
            shutil.copy(voc_path + '/JPEGImages/%s.jpg' % (image_id), './images/%s/%s.jpg' % (image_set, image_id))   # 复制图片

        list_file.close()