将CoCo数据集Json格式转成训练Yolov8-detect检测的txt格式

最近在训练Yolov8-detect时遇到一个问题，就是如何将CoCo数据Json文件转化成可用于Yolov8-detect训练的txt文件，并且是自己想要训练的类别，CoCo数据有80类，我只需要其中的某几类，例如person、cat、dog等。

Yolov8-detect训练数据目录结构如下：images存放训练集和验证集图片，labels存放训练集和验证集txt

mydata
______images
____________train
_________________001.jpg
____________val
_________________002.jpg
______labels
____________train
_________________001.txt
____________val
_________________002.txt   

具体代码如下：

utils.py

import glob
import os
import shutil
from pathlib import Path

import numpy as np
from PIL import ExifTags
from tqdm import tqdm

# Parameters
img_formats = ['bmp', 'jpg', 'jpeg', 'png', 'tif', 'tiff', 'dng']  # acceptable image suffixes
vid_formats = ['mov', 'avi', 'mp4', 'mpg', 'mpeg', 'm4v', 'wmv', 'mkv']  # acceptable video suffixes

# Get orientation exif tag
for orientation in ExifTags.TAGS.keys():
    if ExifTags.TAGS[orientation] == 'Orientation':
        break


def exif_size(img):
    # Returns exif-corrected PIL size
    s = img.size  # (width, height)
    try:
        rotation = dict(img._getexif().items())[orientation]
        if rotation in [6, 8]:  # rotation 270
            s = (s[1], s[0])
    except:
        pass

    return s


def split_rows_simple(file='../data/sm4/out.txt'):  # from utils import *; split_rows_simple()
    # splits one textfile into 3 smaller ones based upon train, test, val ratios
    with open(file) as f:
        lines = f.readlines()

    s = Path(file).suffix
    lines = sorted(list(filter(lambda x: len(x) > 0, lines)))
    i, j, k = split_indices(lines, train=0.9, test=0.1, validate=0.0)
    for k, v in {'train': i, 'test': j, 'val': k}.items():  # key, value pairs
        if v.any():
            new_file = file.replace(s, f'_{k}{s}')
            with open(new_file, 'w') as f:
                f.writelines([lines[i] for i in v])


def split_files(out_path, file_name, prefix_path=''):  # split training data
    file_name = list(filter(lambda x: len(x) > 0, file_name))
    file_name = sorted(file_name)
    i, j, k = split_indices(file_name, train=0.9, test=0.1, validate=0.0)
    datasets = {'train': i, 'test': j, 'val': k}
    for key, item in datasets.items():
        if item.any():
            with open(f'{out_path}_{key}.txt', 'a') as file:
                for i in item:
                    file.write('%s%s\n' % (prefix_path, file_name[i]))


def split_indices(x, train=0.9, test=0.1, validate=0.0, shuffle=True):  # split training data
    n = len(x)
    v = np.arange(n)
    if shuffle:
        np.random.shuffle(v)

    i = round(n * train)  # train
    j = round(n * test) + i  # test
    k = round(n * validate) + j  # validate
    return v[:i], v[i:j], v[j:k]  # return indices


def make_dirs(dir='new_dir/'):
    # Create folders
    dir = Path(dir)
    if dir.exists():
        shutil.rmtree(dir)  # delete dir
    for p in dir, dir / 'labels', dir / 'images':
        p.mkdir(parents=True, exist_ok=True)  # make dir
    return dir


def write_data_data(fname='data.data', nc=80):
    # write darknet *.data file
    lines = ['classes = %g\n' % nc,
             'train =../out/data_train.txt\n',
             'valid =../out/data_test.txt\n',
             'names =../out/data.names\n',
             'backup = backup/\n',
             'eval = coco\n']

    with open(fname, 'a') as f:
        f.writelines(lines)


def image_folder2file(folder='images/'):  # from utils import *; image_folder2file()
    # write a txt file listing all imaged in folder
    s = glob.glob(f'{folder}*.*')
    with open(f'{folder[:-1]}.txt', 'w') as file:
        for l in s:
            file.write(l + '\n')  # write image list


def add_coco_background(path='../data/sm4/', n=1000):  # from utils import *; add_coco_background()
    # add coco background to sm4 in outb.txt
    p = f'{path}background'
    if os.path.exists(p):
        shutil.rmtree(p)  # delete output folder
    os.makedirs(p)  # make new output folder

    # copy images
    for image in glob.glob('../coco/images/train2014/*.*')[:n]:
        os.system(f'cp {image} {p}')

    # add to outb.txt and make train, test.txt files
    f = f'{path}out.txt'
    fb = f'{path}outb.txt'
    os.system(f'cp {f} {fb}')
    with open(fb, 'a') as file:
        file.writelines(i + '\n' for i in glob.glob(f'{p}/*.*'))
    split_rows_simple(file=fb)


def create_single_class_dataset(path='../data/sm3'):  # from utils import *; create_single_class_dataset('../data/sm3/')
    # creates a single-class version of an existing dataset
    os.system(f'mkdir {path}_1cls')


def flatten_recursive_folders(path='../../Downloads/data/sm4/'):  # from utils import *; flatten_recursive_folders()
    # flattens nested folders in path/images and path/JSON into single folders
    idir, jdir = f'{path}images/', f'{path}json/'
    nidir, njdir = Path(f'{path}images_flat/'), Path(f'{path}json_flat/')
    n = 0

    # Create output folders
    for p in [nidir, njdir]:
        if os.path.exists(p):
            shutil.rmtree(p)  # delete output folder
        os.makedirs(p)  # make new output folder

    for parent, dirs, files in os.walk(idir):
        for f in tqdm(files, desc=parent):
            f = Path(f)
            stem, suffix = f.stem, f.suffix
            if suffix.lower()[1:] in img_formats:
                n += 1
                stem_new = '%g_' % n + stem
                image_new = nidir / (stem_new + suffix)  # converts all formats to *.jpg
                json_new = njdir / f'{stem_new}.json'

                image = parent / f
                json = Path(parent.replace('images', 'json')) / str(f).replace(suffix, '.json')

                os.system("cp '%s' '%s'" % (json, json_new))
                os.system("cp '%s' '%s'" % (image, image_new))
                # cv2.imwrite(str(image_new), cv2.imread(str(image)))

    print('Flattening complete: %g jsons and images' % n)


def coco91_to_coco80_class():  # converts 80-index (val2014) to 91-index (paper)
    # https://tech.amikelive.com/node-718/what-object-categories-labels-are-in-coco-dataset/
    x = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, None, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, None, 24, 25, None,
         None, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, None, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50,
         51, 52, 53, 54, 55, 56, 57, 58, 59, None, 60, None, None, 61, None, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72,
         None, 73, 74, 75, 76, 77, 78, 79, None]
    return x

cocojson2bboxtxt.py

import contextlib
import json

import cv2
import pandas as pd
from PIL import Image
from collections import defaultdict

from utils import *

classname = {0: 'person', 1: 'bicycle', 2: 'car', 3: 'motorcycle', 4: 'airplane', 5: 'bus', 6: 'train',
             7: 'truck', 8: 'boat', 9: 'traffic light', 10: 'fire hydrant', 11: 'stop sign',
             12: 'parking meter', 13: 'bench', 14: 'bird', 15: 'cat', 16: 'dog', 17: 'horse',
             18: 'sheep', 19: 'cow', 20: 'elephant', 21: 'bear', 22: 'zebra', 23: 'giraffe',
             24: 'backpack', 25: 'umbrella', 26: 'handbag', 27: 'tie', 28: 'suitcase', 29: 'frisbee',
             30: 'skis', 31: 'snowboard', 32: 'sports ball', 33: 'kite', 34: 'baseball bat',
             35: 'baseball glove', 36: 'skateboard', 37: 'surfboard', 38: 'tennis racket', 39: 'bottle',
             40: 'wine glass', 41: 'cup', 42: 'fork', 43: 'knife', 44: 'spoon', 45: 'bowl', 46: 'banana',
             47: 'apple', 48: 'sandwich', 49: 'orange', 50: 'broccoli', 51: 'carrot', 52: 'hot dog',
             53: 'pizza', 54: 'donut', 55: 'cake', 56: 'chair', 57: 'couch', 58: 'potted plant',
             59: 'bed', 60: 'dining table', 61: 'toilet', 62: 'tv', 63: 'laptop', 64: 'mouse',
             65: 'remote', 66: 'keyboard', 67: 'cell phone', 68: 'microwave', 69: 'oven', 70: 'toaster',
             71: 'sink', 72: 'refrigerator', 73: 'book', 74: 'clock', 75: 'vase', 76: 'scissors',
             77: 'teddy bear', 78: 'hair drier', 79: 'toothbrush'}



def convert_coco_json(json_dir,savepath,selfclasses, cls91to80=False):
    save_dir = make_dirs(savepath)  # output directory
    coco80 = coco91_to_coco80_class()
    # print('coco80',coco80)

    # Import json
    for json_file in sorted(Path(json_dir).resolve().glob('*.json')):
        fn = Path(save_dir) / 'labels' / json_file.stem.replace('instances_', '')  # folder name
        fn.mkdir()
        with open(json_file) as f:
            data = json.load(f)

        # Create image dict
        images = {'%g' % x['id']: x for x in data['images']}

        # Create image-annotations dict
        imgToAnns = defaultdict(list)
        for ann in data['annotations']:
            # print(ann)
            imgToAnns[ann['image_id']].append(ann)

        # Write labels file
        for img_id, anns in tqdm(imgToAnns.items(), desc=f'Annotations {json_file}'):
            img = images['%g' % img_id]
            h, w, f = img['height'], img['width'], img['file_name']

            bboxes = []
            segments = []
            for ann in anns:
                if ann['iscrowd']:
                    continue
                # The COCO box format is [top left x, top left y, width, height]
                box = np.array(ann['bbox'], dtype=np.float64)

                box[:2] += box[2:] / 2  # xy top-left corner to center
                box[[0, 2]] /= w  # normalize x
                box[[1, 3]] /= h  # normalize y
                if box[2] <= 0 or box[3] <= 0:  # if w <= 0 and h <= 0
                    continue
                cls = coco80[ann['category_id'] - 1] if cls91to80 else ann['category_id'] - 1  # class
                clsname = classname[cls]

                if clsname in selfclasses:
                    if clsname == 'person':
                        cls = 0
                    if clsname == 'cat':
                        cls = 1
                    if clsname == 'dog':
                        cls = 2
                    box = [cls] + box.tolist()
                    if box not in bboxes:
                        bboxes.append(box)
                    # print(clsname,box)
            # Write
            if len(bboxes) > 0:
                with open((fn / f).with_suffix('.txt'), 'a') as file:
                    for i in range(len(bboxes)):
                        line = *(bboxes[i]),  # cls, box or segments
                        file.write(('%g ' * len(line)).rstrip() % line + '\n')


if __name__ == '__main__':
    source = 'COCO'
    cocojsonpath = r'G:\XRW\Data\yolodata\json'
    savepath = r'G:\XRW\Data\yolodata\save'
    selfclasses = ['person', 'cat', 'dog']
    if source == 'COCO':
        convert_coco_json(cocojsonpath,  # directory with *.json
                          savepath,
                          selfclasses,
                          cls91to80=True)

• cocojsonpath：CoCo数据集json文件存放路径
• savepath：生成的txt存放路径
• selfclasses：自己想要训练的类别

运行cocojson2bboxtxt.py

运行完成后得到的txt要少于上图显示的，因为这些txt只包含person、cat、dog类别

txt存放的数据格式如下（与官方一致）：

分别代表：类别、框的中心点xy坐标以及框的宽高（进行了归一化处理）

注意：我这里将person、cat、dog3类分别对应成0、1、2，可自行修改

以上步骤完成后只生成了txt，需要再将对应的图片copy到对应路径中。

import glob
import os
import shutil
imgpath = r'G:\CoCoData\val2017'
txtpath = r'G:\Yolov8\ultralytics-main\datasets\mysegdata\labels\val2017'
savepath = r'G:\Yolov8\ultralytics-main\datasets\mysegdata\images\val2017'

imglist = glob.glob(os.path.join(imgpath,'*.jpg'))
txtlist = glob.glob(os.path.join(txtpath,'*.txt'))

for img in imglist:
    name = txtpath + '\\'+img.split('\\')[-1].split('.')[0]+'.txt'
    if name in txtlist:
        shutil.copy(img,savepath)

• imgpath CoCo数据集图片路径
• txtpath 生成的人猫狗txt路径
• savepath 保存图片的路径

CoCo数据

人猫狗类别的txt

人猫狗类别的图片

这样CoCo数据集的人猫狗类别的Yolov8检测数据集就制作完成了。