数据集格式转换——yolo和voc互转

1.yolo转voc

import argparse
import os
import sys
import shutil

import cv2
from lxml import etree, objectify

# 将标签信息写入xml
from tqdm import tqdm

images_nums = 0
category_nums = 0
bbox_nums = 0


def save_anno_to_xml(filename, size, objs, save_path):
    E = objectify.ElementMaker(annotate=False)
    anno_tree = E.annotation(
        E.folder("DATA"),
        E.filename(filename),
        E.source(
            E.database("The VOC Database"),
            E.annotation("PASCAL VOC"),
            E.image("flickr")
        ),
        E.size(
            E.width(size[1]),
            E.height(size[0]),
            E.depth(size[2])
        ),
        E.segmented(0)
    )
    for obj in objs:
        E2 = objectify.ElementMaker(annotate=False)
        anno_tree2 = E2.object(
            E.name(obj[0]),
            E.pose("Unspecified"),
            E.truncated(0),
            E.difficult(0),
            E.bndbox(
                E.xmin(obj[1][0]),
                E.ymin(obj[1][1]),
                E.xmax(obj[1][2]),
                E.ymax(obj[1][3])
            )
        )
        anno_tree.append(anno_tree2)
    anno_path = os.path.join(save_path, filename[:-3] + "xml")
    etree.ElementTree(anno_tree).write(anno_path, pretty_print=True)


def xywhn2xyxy(bbox, size):
    bbox = list(map(float, bbox))
    size = list(map(float, size))
    xmin = (bbox[0] - bbox[2] / 2.) * size[1]
    ymin = (bbox[1] - bbox[3] / 2.) * size[0]
    xmax = (bbox[0] + bbox[2] / 2.) * size[1]
    ymax = (bbox[1] + bbox[3] / 2.) * size[0]
    box = [xmin, ymin, xmax, ymax]
    return list(map(int, box))


def parseXmlFilse(image_path, anno_path, save_path):
    global images_nums, category_nums, bbox_nums
    assert os.path.exists(image_path), "ERROR {} dose not exists".format(image_path)
    assert os.path.exists(anno_path), "ERROR {} dose not exists".format(anno_path)
    if os.path.exists(save_path):
        shutil.rmtree(save_path)
    os.makedirs(save_path)

    category_set = []
    with open(anno_path + '/classes.txt', 'r') as f:
        for i in f.readlines():
            category_set.append(i.strip())
    category_nums = len(category_set)
    category_id = dict((k, v) for k, v in enumerate(category_set))

    images = [os.path.join(image_path, i) for i in os.listdir(image_path)]
    files = [os.path.join(anno_path, i) for i in os.listdir(anno_path)]
    images_index = dict((v.split(os.sep)[-1][:-4], k) for k, v in enumerate(images))
    images_nums = len(images)

    for file in tqdm(files):
        if os.path.splitext(file)[-1] != '.txt' or 'classes' in file.split(os.sep)[-1]:
            continue
        if file.split(os.sep)[-1][:-4] in images_index:
            index = images_index[file.split(os.sep)[-1][:-4]]
            img = cv2.imread(images[index])
            shape = img.shape
            filename = images[index].split(os.sep)[-1]
        else:
            continue
        objects = []
        with open(file, 'r') as fid:
            for i in fid.readlines():
                i = i.strip().split()
                category = int(i[0])
                category_name = category_id[category]
                bbox = xywhn2xyxy((i[1], i[2], i[3], i[4]), shape)
                obj = [category_name, bbox]
                objects.append(obj)
        bbox_nums += len(objects)
        save_anno_to_xml(filename, shape, objects, save_path)


if __name__ == '__main__':
    """
    脚本说明：
        本脚本用于将yolo格式的标注文件.txt转换为voc格式的标注文件.xml
    参数说明：
        anno_path:标注文件txt存储路径
        save_path:json文件输出的文件夹
        image_path:图片路径
    """
    parser = argparse.ArgumentParser()
    parser.add_argument('-ap', '--anno-path', type=str, default='./data/labels/yolo', help='yolo txt path')
    parser.add_argument('-s', '--save-path', type=str, default='./data/convert/voc', help='xml save path')
    parser.add_argument('--image-path', default='./data/images')

    opt = parser.parse_args()
    if len(sys.argv) > 1:
        print(opt)
        parseXmlFilse(**vars(opt))
        print("image nums: {}".format(images_nums))
        print("category nums: {}".format(category_nums))
        print("bbox nums: {}".format(bbox_nums))
    else:
        anno_path = './data/labels/yolo'
        save_path = './data/convert/voc1'
        image_path = './data/images'
        parseXmlFilse(image_path, anno_path, save_path)
        print("image nums: {}".format(images_nums))
        print("category nums: {}".format(category_nums))
        print("bbox nums: {}".format(bbox_nums))

2.voc转yolo

import os
import json
import argparse
import sys
import shutil
from lxml import etree
from tqdm import tqdm

category_set = set()
image_set = set()
bbox_nums = 0


def parse_xml_to_dict(xml):
    """
    将xml文件解析成字典形式，参考tensorflow的recursive_parse_xml_to_dict
    Args:
        xml: xml tree obtained by parsing XML file contents using lxml.etree

    Returns:
        Python dictionary holding XML contents.
    """
    if len(xml) == 0:  # 遍历到底层，直接返回tag对应的信息
        return {xml.tag: xml.text}

    result = {}
    for child in xml:
        child_result = parse_xml_to_dict(child)  # 递归遍历标签信息
        if child.tag != 'object':
            result[child.tag] = child_result[child.tag]
        else:
            if child.tag not in result:  # 因为object可能有多个，所以需要放入列表里
                result[child.tag] = []
            result[child.tag].append(child_result[child.tag])
    return {xml.tag: result}


def write_classIndices(category_set):
    class_indices = dict((k, v) for v, k in enumerate(category_set))
    json_str = json.dumps(dict((val, key) for key, val in class_indices.items()), indent=4)
    with open('class_indices.json', 'w') as json_file:
        json_file.write(json_str)


def xyxy2xywhn(bbox, size):
    bbox = list(map(float, bbox))
    size = list(map(float, size))
    xc = (bbox[0] + (bbox[2] - bbox[0]) / 2.) / size[0]
    yc = (bbox[1] + (bbox[3] - bbox[1]) / 2.) / size[1]
    wn = (bbox[2] - bbox[0]) / size[0]
    hn = (bbox[3] - bbox[1]) / size[1]
    return (xc, yc, wn, hn)


def parser_info(info: dict, only_cat=True, class_indices=None):
    filename = info['annotation']['filename']
    image_set.add(filename)
    objects = []
    width = int(info['annotation']['size']['width'])
    height = int(info['annotation']['size']['height'])
    for obj in info['annotation']['object']:
        obj_name = obj['name']
        category_set.add(obj_name)
        if only_cat:
            continue
        xmin = int(obj['bndbox']['xmin'])
        ymin = int(obj['bndbox']['ymin'])
        xmax = int(obj['bndbox']['xmax'])
        ymax = int(obj['bndbox']['ymax'])
        bbox = xyxy2xywhn((xmin, ymin, xmax, ymax), (width, height))
        if class_indices is not None:
            obj_category = class_indices[obj_name]
            object = [obj_category, bbox]
            objects.append(object)

    return filename, objects


def parseXmlFilse(voc_dir, save_dir):
    assert os.path.exists(voc_dir), "ERROR {} does not exists".format(voc_dir)
    if os.path.exists(save_dir):
        shutil.rmtree(save_dir)
    os.makedirs(save_dir)

    xml_files = [os.path.join(voc_dir, i) for i in os.listdir(voc_dir) if os.path.splitext(i)[-1] == '.xml']
    for xml_file in xml_files:
        with open(xml_file) as fid:
            xml_str = fid.read()
        xml = etree.fromstring(xml_str)
        info_dict = parse_xml_to_dict(xml)
        parser_info(info_dict, only_cat=True)

    with open(save_dir + "/classes.txt", 'w') as classes_file:
        for cat in sorted(category_set):
            classes_file.write("{}\n".format(cat))

    class_indices = dict((v, k) for k, v in enumerate(sorted(category_set)))

    xml_files = tqdm(xml_files)
    for xml_file in xml_files:
        with open(xml_file) as fid:
            xml_str = fid.read()
        xml = etree.fromstring(xml_str)
        info_dict = parse_xml_to_dict(xml)
        filename, objects = parser_info(info_dict, only_cat=False, class_indices=class_indices)
        if len(objects) != 0:
            global bbox_nums
            bbox_nums += len(objects)
            with open(save_dir + "/" + filename.split(".")[0] + ".txt", 'w') as f:
                for obj in objects:
                    f.write(
                        "{} {:.5f} {:.5f} {:.5f} {:.5f}\n".format(obj[0], obj[1][0], obj[1][1], obj[1][2], obj[1][3]))


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--voc-dir', type=str, default='./data/labels/voc')
    parser.add_argument('--save-dir', type=str, default='./data/convert/yolo')
    opt = parser.parse_args()
    if len(sys.argv) > 1:
        print(opt)
        parseXmlFilse(**vars(opt))
        print("image nums: {}".format(len(image_set)))
        print("category nums: {}".format(len(category_set)))
        print("bbox nums: {}".format(bbox_nums))
    else:
        voc_dir = './data/labels/voc'
        save_dir = './data/convert/yolo'
        parseXmlFilse(voc_dir, save_dir)
        print("image nums: {}".format(len(image_set)))
        print("category nums: {}".format(len(category_set)))
        print("bbox nums: {}".format(bbox_nums))