Labelme标注的json数据转化为coco格式的数据

1. 转化方法一

import os
import json
import numpy as np
import glob
import shutil
import cv2
from sklearn.model_selection import train_test_split

np.random.seed(41)

classname_to_id = {
    "mouth": 0,  # 改成自己的类别
    "teeth": 1,
    "tongue": 2,
    "uvula": 3,
    "oropharynx": 4
}

class Lableme2CoCo:

    def __init__(self):
        self.images = []
        self.annotations = []
        self.categories = []
        self.img_id = 0
        self.ann_id = 0

    def save_coco_json(self, instance, save_path):
        json.dump(instance, open(save_path, 'w', encoding='utf-8'), ensure_ascii=False, indent=1)  # indent=2 更加美观显示

    # 由json文件构建COCO
    def to_coco(self, json_path_list):
        self._init_categories()
        for json_path in json_path_list:
            obj = self.read_jsonfile(json_path)
            self.images.append(self._image(obj, json_path))
            shapes = obj['shapes']
            for shape in shapes:
                annotation = self._annotation(shape)
                self.annotations.append(annotation)
                self.ann_id += 1
            self.img_id += 1
        instance = {}
        instance['info'] = 'spytensor created'
        instance['license'] = ['license']
        instance['images'] = self.images
        instance['annotations'] = self.annotations
        instance['categories'] = self.categories
        return instance

    # 构建类别
    def _init_categories(self):
        for k, v in classname_to_id.items():
            category = {}
            category['id'] = v
            category['name'] = k
            self.categories.append(category)

    # 构建COCO的image字段
    def _image(self, obj, path):
        image = {}
        from labelme import utils
        img_x = utils.img_b64_to_arr(obj['imageData'])
        h, w = img_x.shape[:-1]
        image['height'] = h
        image['width'] = w
        image['id'] = self.img_id
        image['file_name'] = os.path.basename(path).replace(".json", ".jpg")
        return image

    # 构建COCO的annotation字段
    def _annotation(self, shape):
        # print('shape', shape)
        label = shape['label']
        points = shape['points']
        annotation = {}
        annotation['id'] = self.ann_id
        annotation['image_id'] = self.img_id
        annotation['category_id'] = int(classname_to_id[label])
        annotation['segmentation'] = [np.asarray(points).flatten().tolist()]
        annotation['bbox'] = self._get_box(points)
        annotation['iscrowd'] = 0
        annotation['area'] = 1.0
        return annotation

    # 读取json文件，返回一个json对象
    def read_jsonfile(self, path):
        with open(path, "r", encoding='utf-8') as f:
            return json.load(f)

    # COCO的格式： [x1,y1,w,h] 对应COCO的bbox格式
    def _get_box(self, points):
        min_x = min_y = np.inf
        max_x = max_y = 0
        for x, y in points:
            min_x = min(min_x, x)
            min_y = min(min_y, y)
            max_x = max(max_x, x)
            max_y = max(max_y, y)
        return [min_x, min_y, max_x - min_x, max_y - min_y]


# 训练过程中，如果遇到Index put requires the source and destination dtypes match, got Long for the destination and Int for the source
# 参考：https://github.com/open-mmlab/mmdetection/issues/6706
if __name__ == '__main__':
    labelme_path = "./data/mouth/train"
    saved_coco_path = "./data/"
    print('reading...')
    # 创建文件
    if not os.path.exists("%scoco/annotations/" % saved_coco_path):
        os.makedirs("%scoco/annotations/" % saved_coco_path)
    if not os.path.exists("%scoco/images/train2017/" % saved_coco_path):
        os.makedirs("%scoco/images/train2017" % saved_coco_path)
    if not os.path.exists("%scoco/images/val2017/" % saved_coco_path):
        os.makedirs("%scoco/images/val2017" % saved_coco_path)
    # 获取images目录下所有的joson文件列表
    print(labelme_path + "/*.json")
    json_list_path = glob.glob(labelme_path + "/*.json")
    print('json_list_path: ', len(json_list_path))
    # 数据划分,这里没有区分val2017和tran2017目录，所有图片都放在images目录下
    train_path, val_path = train_test_split(json_list_path, test_size=0.0001, train_size=0.9999)
    print("train_n:", len(train_path), 'val_n:', len(val_path))

    # 把训练集转化为COCO的json格式
    l2c_train = Lableme2CoCo()
    train_instance = l2c_train.to_coco(train_path)
    l2c_train.save_coco_json(train_instance, '%scoco/annotations/instances_train2017.json' % saved_coco_path)
    for file in train_path:
        # shutil.copy(file.replace("json", "jpg"), "%scoco/images/train2017/" % saved_coco_path)
        img_name = file.replace('json', 'jpg')
        temp_img = cv2.imread(img_name)
        try:
            cv2.imwrite(
                "{}coco/images/train2017/{}".format(saved_coco_path, img_name.split('\\')[-1].replace('png', 'jpg')),
                temp_img)
        except Exception as e:
            print(e)
            print('Wrong Image:', img_name)
            continue
        print(img_name + '-->', img_name.replace('png', 'jpg'))

    for file in val_path:
        # shutil.copy(file.replace("json", "jpg"), "%scoco/images/val2017/" % saved_coco_path)
        img_name = file.replace('json', 'jpg')
        temp_img = cv2.imread(img_name)
        try:
            cv2.imwrite(
                "{}coco/images/val2017/{}".format(saved_coco_path, img_name.split('\\')[-1].replace('png', 'jpg')),
                temp_img)
        except Exception as e:
            print(e)
            print('Wrong Image:', img_name)
            continue
        print(img_name + '-->', img_name.replace('png', 'jpg'))

    # 把验证集转化为COCO的json格式
    l2c_val = Lableme2CoCo()
    val_instance = l2c_val.to_coco(val_path)
    l2c_val.save_coco_json(val_instance, '%scoco/annotations/instances_val2017.json' % saved_coco_path)

• 修改下面类别为自己的类别

classname_to_id = {
    "mouth": 0,  # 改成自己的类别
    "teeth": 1,
    "tongue": 2,
    "uvula": 3,
    "oropharynx": 4
}

• 修改原label位置和保存的新生成label位置。

    labelme_path = "./data/mouth/train"
    saved_coco_path = "./data/"

-划分训练集和测试集的比例

 train_path, val_path = train_test_split(json_list_path, test_size=0.0001, train_size=0.9999)

2. 转化方法二

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


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'):
        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))
                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):
        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
        # img = cv2.imread(data['imagePath'], 0)
        height, width = img.shape[:2]
        img = None
        image['height'] = height
        image['width'] = width
        image['id'] = num + 1
        image['file_name'] = data['imagePath'].split('/')[-1]

        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'] = str(self.getbbox(points)) # 使用list保存json文件时报错（不知道为什么）
        # list(map(int,a[1:-1].split(','))) a=annotation['bbox'] 使用该方式转成list
        annotation['bbox'] = list(map(float, self.getbbox(points)))
        annotation['area'] = annotation['bbox'][2] * annotation['bbox'][3]
        # annotation['category_id'] = self.getcatid(label)
        annotation['category_id'] = self.getcatid(label)  # 注意，源代码默认为1
        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):
        # img = np.zeros([self.height,self.width],np.uint8)
        # cv2.polylines(img, [np.asarray(points)], True, 1, lineType=cv2.LINE_AA)  # 画边界线
        # cv2.fillPoly(img, [np.asarray(points)], 1)  # 画多边形 内部像素值为1
        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）
        '''
        # np.where(mask==1)
        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_r,left_top_c),(right_bottom_r,right_bottom_c)]
        # return [(left_top_c, left_top_r), (right_bottom_c, right_bottom_r)]
        # return [left_top_c, left_top_r, right_bottom_c, right_bottom_r]  # [x1,y1,x2,y2]
        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)  # indent=4 更加美观显示

labelme_json = glob.glob('./data/mouth/train/*.json')
# labelme_json=['./1.json']

labelme2coco(labelme_json, './data/coco/annotations/instances_train2017.json')

• 修改原数据集的label文件位置

labelme_json = glob.glob('./data/mouth/train/*.json')

• 修改生成的新label文件的位置和名称

labelme2coco(labelme_json, './data/coco/annotations/instances_train2017.json')