标注文件：xml转json And json转coco数据集

.xml文件(VOC数据集)转换成.json文件(COCO数据集)，网上代码一大堆，靠谱的没几个(本文代码支持标签内多个object)（需注意:确保.xml文件所指定的图像路径是正确的！）

#xml2json
import xml.etree.ElementTree as ET
import os
import json
import cv2
from io import BytesIO
import base64
from PIL import Image


def makefile(path, content):
    with open(path, 'w') as f:
        f.write(content)


def toJson(imagePath, imageHeight, imageWidth, shape_type, objects):
    print(imagePath)

    coco = dict()
    coco['version'] = "5.0.0"
    coco['flags'] = dict()
    coco['shapes'] = []
    
    for obj in objects:
        label = obj.find('name').text
        points = [
            [int(obj.find('bndbox/xmin').text), int(obj.find('bndbox/ymin').text)],
            [int(obj.find('bndbox/xmax').text), int(obj.find('bndbox/ymax').text)]
        ]
        shape = {
            'label': label,
            'points': points,
            'group_id': None,
            'shape_type': shape_type,
            'flags': dict()
        }
        coco['shapes'].append(shape)

    coco['imagePath'] = imagePath

    img = cv2.imread(imagePath)
    if img is None:
        print(f"Failed to read image: {imagePath}")
        return

    pil_img = Image.fromarray(img)
    buff = BytesIO()
    pil_img.save(buff, format="JPEG")
    new_image_string = base64.b64encode(buff.getvalue()).decode("utf-8")
    coco['imageData'] = new_image_string

    coco['imageHeight'] = imageHeight
    coco['imageWidth'] = imageWidth

    makefile(imagePath[:-4] + ".json", json.dumps(coco, indent=4))


def parseXmlFiles(xml_path):
    for f in os.listdir(xml_path):
        if not f.endswith('.xml'):
            continue

        xml_file = os.path.join(xml_path, f)
        print(xml_file)

        tree = ET.parse(xml_file)
        root = tree.getroot()
        if root.tag != 'annotation':
            raise Exception('pascal voc xml root element should be annotation, rather than {}'.format(root.tag))

        imagePath = ""
        imageHeight = 0
        imageWidth = 0
        shape_type = "rectangle"
        objects = []
        for elem in root:
            if elem.tag == 'folder' or elem.tag == 'filename' or elem.tag == 'source' or elem.tag == 'segmented':
                continue
            elif elem.tag == 'path':
                imagePath = elem.text
            elif elem.tag == 'size':
                for subelem in elem:
                    if subelem.tag == 'width':
                        imageWidth = subelem.text
                    elif subelem.tag == 'height':
                        imageHeight = subelem.text
            elif elem.tag == 'object':
                objects.append(elem)
        
        toJson(imagePath, imageHeight, imageWidth, shape_type, objects, xml_path)


if __name__ == '__main__':
    xml_path = '/home/sjf/Downloads/annotation' # 这是xml文件所在的地址
    parseXmlFiles(xml_path)

 

#json2coco
import argparse
import json
import matplotlib.pyplot as plt
import skimage.io as io
import cv2
import labelme.utils as utils
import numpy as np
import glob
import PIL.Image
import os




class MyEncoder(json.JSONEncoder):
    def default(self, obj):
        if isinstance(obj, np.integer):
            return int(obj)
        elif isinstance(obj, np.floating):
            return float(obj)
        elif isinstance(obj, np.ndarray):
            return obj.tolist()
        else:
            return super(MyEncoder, self).default(obj)


class labelme2coco(object):
    def __init__(self, labelme_json=[], save_json_path='./tran.json'):
        '''
        :param labelme_json: 所有labelme的json文件路径组成的列表
        :param save_json_path: json保存位置
        '''
        self.labelme_json = labelme_json
        self.save_json_path = save_json_path
        self.images = []
        self.categories = []
        self.annotations = []
        # self.data_coco = {}
        self.label = []
        self.annID = 1
        self.height = 0
        self.width = 0

        self.save_json()

    def data_transfer(self):

        for num, json_file in enumerate(self.labelme_json):
            with open(json_file, 'r') as fp:
                data = json.load(fp)  # 加载json文件
                self.images.append(self.image(data, num, json_file))
                for shapes in data['shapes']:
                    label = shapes['label']
                    if label not in self.label:
                        self.categories.append(self.categorie(label))
                        self.label.append(label)
                    points = shapes['points']  # 这里的point是用rectangle标注得到的，只有两个点，需要转成四个点
                    points.append([points[0][0], points[1][1]])
                    points.append([points[1][0], points[0][1]])
                    self.annotations.append(self.annotation(points, label, num))
                    self.annID += 1

    def image(self, data, num, json_file):

        image = {}
        # img = utils.img_b64_to_arr(data['imageData'])  # 解析原图片数据
        # img=io.imread(data['imagePath']) # 通过图片路径打开图片
        print(json_file.replace("json", "png").replace("annotations", "images"))
        imgname = ""
        if os.path.exists(json_file.replace("json", "png").replace("annotations", "images")):
            img = cv2.imread(json_file.replace("json", "png").replace("annotations", "images"), 0)
            imgname = os.path.basename(json_file.replace("json", "png").replace("annotations", "images"))
        else:
            img = cv2.imread(json_file.replace("json", "jpg").replace("annotations", "images"), 0)
            imgname = os.path.basename(json_file.replace("json", "jpg").replace("annotations", "images"))

        # TODO：这里需要指定好输入图像的尺寸，我的图像一般都是同样大小的，所以我就只取一张图片的size
        # img = cv2.imread("/Users/surui/CRT/data/1.jpg", 0)
        height, width = img.shape[:2]

        image['height'] = height
        image['width'] = width
        image['id'] = num + 1
        image['file_name'] = imgname

        self.height = height
        self.width = width

        return image

    def categorie(self, label):
        categorie = {}
        categorie['supercategory'] = 'Cancer'
        categorie['id'] = len(self.label) + 1  # 0 默认为背景
        categorie['name'] = label
        return categorie

    def annotation(self, points, label, num):
        annotation = {}
        annotation['segmentation'] = [list(np.asarray(points).flatten())]
        annotation['iscrowd'] = 0
        annotation['image_id'] = num + 1
        annotation['bbox'] = list(map(float, self.getbbox(points)))
        annotation['area'] = annotation['bbox'][2] * annotation['bbox'][3]
        annotation['category_id'] = self.getcatid(label)  
        annotation['id'] = self.annID
        return annotation

    def getcatid(self, label):
        for categorie in self.categories:
            if label == categorie['name']:
                return categorie['id']
        return 1

    def getbbox(self, points):
       
        polygons = points

        mask = self.polygons_to_mask([self.height, self.width], polygons)
        return self.mask2box(mask)

    def mask2box(self, mask):
        '''从mask反算出其边框
        mask：[h,w]  0、1组成的图片
        1对应对象，只需计算1对应的行列号（左上角行列号，右下角行列号，就可以算出其边框）
        '''
       
        index = np.argwhere(mask == 1)
        rows = index[:, 0]
        clos = index[:, 1]
        # 解析左上角行列号
        left_top_r = np.min(rows)  # y
        left_top_c = np.min(clos)  # x

        # 解析右下角行列号
        right_bottom_r = np.max(rows)
        right_bottom_c = np.max(clos)

       
        return [left_top_c, left_top_r, right_bottom_c - left_top_c,
                right_bottom_r - left_top_r]  # [x1,y1,w,h] 对应COCO的bbox格式

    def polygons_to_mask(self, img_shape, polygons):
        mask = np.zeros(img_shape, dtype=np.uint8)
        mask = PIL.Image.fromarray(mask)
        xy = list(map(tuple, polygons))
        PIL.ImageDraw.Draw(mask).polygon(xy=xy, outline=1, fill=1)
        mask = np.array(mask, dtype=bool)
        return mask

    def data2coco(self):
        data_coco = {}
        data_coco['images'] = self.images
        data_coco['categories'] = self.categories
        data_coco['annotations'] = self.annotations
        return data_coco

    def save_json(self):
        self.data_transfer()
        self.data_coco = self.data2coco()
        # 保存json文件
        json.dump(self.data_coco, open(self.save_json_path, 'w'), indent=4, cls=MyEncoder) 


if __name__ == '__main__':
    labelme_json = glob.glob('～/*.json')  # .json文件夹
    labelme2coco(labelme_json, '～/val.json')  # 生成的.json文件