使用labelme标注数据集并转化为CoCo数据集

Posted 2021-09-04 啊～小 l i

目录

• 使用labelme标注数据
• 将labelme数据集转化为CoCo数据集

使用labelme标注数据

1. 安装labelme
   pip install lebelme
2. 安装完成后使用labelme
   在命令窗口输入labelme
   
3. 导入需要标注的数据
   Open Dir -> 选择要导入的文件夹 -> 设置自动保存[左上角(File -> Save Automatically)]-> Create Polygons[左侧工具栏]
   
4. 对图片进行标注
   注意：

• 标注要准确，尽可能表的详细
• 标注物体时需要标注物体最大的范围
• 尽可能多的点去标记
  产生的json文件(与标注文件在同一目录)
  

将labelme数据集转化为CoCo数据集

• rename.py
  用于对数据集中图片以及json文件的重命名
• format.py
  用于替换json中不合法的imagePath
• checkClasses
  用于检测当前一共标注了多少class 并对检测结果进行输出
• labelme2coco.py
  用于生成coco形式的数据集
  使用
  rename.py文件

import os
this_dir_path = './'
json_index = 0 # 表示从那个序号开始更改.json文件名
png_index = 0  # 表示从那个序号开始更改.png文件名
for file in os.listdir(this_dir_path):
    file_path = os.path.join(this_dir_path, file)
    if os.path.splitext(file_path)[-1] == '.png':
        new_file_path = '.'+'/'.join((os.path.splitext(file_path)[0].split('\\\\'))[:-1]) + '/{:0>4}_Color.png'.format(png_index)
        png_index += 1
        print(file_path+'---->'+new_file_path)
        os.rename(file_path, new_file_path)
    elif os.path.splitext(file_path)[-1] == '.json':
        new_file_path = '.'+'/'.join((os.path.splitext(file_path)[0].split('\\\\'))[:-1]) + '/{:0>4}_Color.json'.format(json_index)
        json_index += 1
        print(file_path+'---->'+new_file_path)
        os.rename(file_path,new_file_path)

format.py文件

import os
import re
dir_path = './'
pattern = re.compile('"imagePath": "(.+?png)",')
for file in os.listdir(dir_path):
    if os.path.splitext(file)[-1] != '.json':
        continue
    with open(os.path.join(dir_path, file), encoding='utf-8') as f:
        content = f.read()
        imagePath = pattern.findall(content)[0]
        print('imagePath ',imagePath)
        new_content = content.replace(imagePath, os.path.splitext(file)[0]+'.png')
    with open(os.path.join(dir_path, file), 'w', encoding='utf-8') as nf:
        nf.write(new_content)

checkClasses.py文件

import os
import re

CLASS_NAMES = ['CA001', 'CA002', 'CA003', 'CA004',
               'CD001', 'CD002', 'CD003']
CLASS_REAL_NAMES = ['draw_paper', 'roll_paper', 'toothbrush',
 'tape','apple', 'pear', 'melon']
CLASS_NAME_DICT = {
    'CA001': 'draw_paper',
    'CA002': 'roll_paper',
    'CA003': 'toothbrush',
    'CA004': 'tape',
    'CD001': 'apple',
    'CD002': 'pear',
    'CD003': 'melon',
}

dir_path = './'
pattern = re.compile('"label": "([A-Z]{2}[0-9]{3}(?:.+)?)",')
class_ids = []
for file in os.listdir(dir_path):
    if os.path.splitext(file)[-1] != '.json':
        continue
    with open(os.path.join(dir_path, file), 'r+', encoding='utf-8') as f:
        content = f.read()
        image_class_ids = pattern.findall(content)
        for id in image_class_ids:
            if id not in class_ids:
                if len(id) > 5:
                    print("Find invalid id !!")
                    content = content.replace(id, id[:5])
                    with open(os.path.join(dir_path, file), 'w', encoding='utf-8') as f:
                        f.write(content)
                else:
                    class_ids.append(id)
print('一共有{}种class'.format(len(class_ids)))
print('分别是')
index = 1
for id in class_ids:
    print('"{}",'.format(id), end="")
    index += 1
print()
index = 1
for id in class_ids:
    print('"{}":{},'.format(id, index))
    index += 1

for id in class_ids:
    print("'{}',".format(CLASS_NAME_DICT[id]),end="")

可以不适用ID,直接使用真实名字来标注！

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)

# 0为背景
classname_to_id = {
    "CA002": 1, # 从1开始标注
    "CA004": 2,
    "CA003": 3,
    "CD006": 4,
    "CD002": 5,
    "CD001": 6,
    "ZA001": 7,
    "ZA003": 8,
    "ZA002": 9,
}


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]


if __name__ == '__main__':
    labelme_path = "../../../xianjin_data-3/"
    saved_coco_path = "../../../xianjin_data-3/"
    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=0.1, train_size=0.9)
    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', 'png')
        temp_img = cv2.imread(img_name)
        try:
            cv2.imwrite("{}coco/images/train2017/{}".format(saved_coco_path, img_name.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', 'png')
        temp_img = cv2.imread(img_name)
        try:
            cv2.imwrite("{}coco/images/val2017/{}".format(saved_coco_path, img_name.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)

将图片转化为JPG格式，并且自动生成CoCo数据集