当前位置：首页 > news >正文

将YOLO格式的数据集转换为mmdetection格式

news 2025/6/8 14:02:48

引言：当前目标检测框架最火的就是YOLO和MMdetection，本文介绍从YOLO格式向MMdetection格式的转换，方便大家使用这两种框架进行模型对比验证。

官方文档参考：

自定义数据集 — MMDetection 3.3.0 文档https://mmdetection.readthedocs.io/zh-cn/latest/advanced_guides/customize_dataset.htmlYOLO格式的数据集文件夹格式如下：

在我这里训练和测试已经划分完毕，所以分开生成COCO格式的json文件，文件夹这样摆放：

这里的images文件夹对应YOLO数据集的images/train，labels文件夹对应YOLO数据集的labels/train

然后安装sklearn库：

pip install scikit-learn

并在数据集下写classes.txt，每一行代表一个类别：

在当前目录下新建yolo2coco.py，代码如下：

import os
import cv2
import json
from tqdm import tqdm
from sklearn.model_selection import train_test_split
import argparse# python yolo2coco.py --root_dir VisDrone2019-DET-train --save_path train.json
# python yolo2coco.py --root_dir VisDrone2019-DET-val --save_path val.json
# python yolo2coco.py --root_dir VisDrone2019-DET-test-dev --save_path test.jsonparser = argparse.ArgumentParser()
parser.add_argument('--root_dir', default='./dataset/valid',type=str, help="root path of images and labels, include ./images and ./labels and classes.txt")
parser.add_argument('--save_path', type=str,default='./valid.json', help="if not split the dataset, give a path to a json file")
parser.add_argument('--random_split', action='store_true', help="random split the dataset, default ratio is 8:1:1")
parser.add_argument('--split_by_file', action='store_true', help="define how to split the dataset, include ./train.txt ./val.txt ./test.txt ")arg = parser.parse_args()def train_test_val_split_random(img_paths,ratio_train=0.8,ratio_test=0.1,ratio_val=0.1):# 这里可以修改数据集划分的比例。assert int(ratio_train+ratio_test+ratio_val) == 1train_img, middle_img = train_test_split(img_paths,test_size=1-ratio_train, random_state=233)ratio=ratio_val/(1-ratio_train)val_img, test_img  =train_test_split(middle_img,test_size=ratio, random_state=233)print("NUMS of train:val:test = {}:{}:{}".format(len(train_img), len(val_img), len(test_img)))return train_img, val_img, test_imgdef train_test_val_split_by_files(img_paths, root_dir):# 根据文件 train.txt, val.txt, test.txt（里面写的都是对应集合的图片名字） 来定义训练集、验证集和测试集phases = ['train', 'val', 'test']img_split = []for p in phases:define_path = os.path.join(root_dir, f'{p}.txt')print(f'Read {p} dataset definition from {define_path}')assert os.path.exists(define_path)with open(define_path, 'r') as f:img_paths = f.readlines()# img_paths = [os.path.split(img_path.strip())[1] for img_path in img_paths]  # NOTE 取消这句备注可以读取绝对地址。img_split.append(img_paths)return img_split[0], img_split[1], img_split[2]def yolo2coco(arg):root_path = arg.root_dirprint("Loading data from ",root_path)assert os.path.exists(root_path)originLabelsDir = os.path.join(root_path, 'labels')                                        originImagesDir = os.path.join(root_path, 'images')with open(os.path.join(root_path, 'classes.txt')) as f:classes = f.read().strip().split()# images dir nameindexes = os.listdir(originImagesDir)if arg.random_split or arg.split_by_file:# 用于保存所有数据的图片信息和标注信息train_dataset = {'categories': [], 'annotations': [], 'images': []}val_dataset = {'categories': [], 'annotations': [], 'images': []}test_dataset = {'categories': [], 'annotations': [], 'images': []}# 建立类别标签和数字id的对应关系, 类别id从0开始。for i, cls in enumerate(classes, 0):train_dataset['categories'].append({'id': i, 'name': cls, 'supercategory': 'mark'})val_dataset['categories'].append({'id': i, 'name': cls, 'supercategory': 'mark'})test_dataset['categories'].append({'id': i, 'name': cls, 'supercategory': 'mark'})if arg.random_split:print("spliting mode: random split")train_img, val_img, test_img = train_test_val_split_random(indexes,0.8,0.1,0.1)elif arg.split_by_file:print("spliting mode: split by files")train_img, val_img, test_img = train_test_val_split_by_files(indexes, root_path)else:dataset = {'categories': [], 'annotations': [], 'images': []}for i, cls in enumerate(classes, 0):dataset['categories'].append({'id': i, 'name': cls, 'supercategory': 'mark'})# 标注的idann_id_cnt = 0for k, index in enumerate(tqdm(indexes)):# 支持 png jpg 格式的图片。txtFile = index.replace('images','txt').replace('.jpg','.txt').replace('.png','.txt')# 读取图像的宽和高im = cv2.imread(os.path.join(root_path, 'images/') + index)height, width, _ = im.shapeif arg.random_split or arg.split_by_file:# 切换dataset的引用对象，从而划分数据集if index in train_img:dataset = train_datasetelif index in val_img:dataset = val_datasetelif index in test_img:dataset = test_dataset# 添加图像的信息dataset['images'].append({'file_name': index,'id': k,'width': width,'height': height})if not os.path.exists(os.path.join(originLabelsDir, txtFile)):# 如没标签，跳过，只保留图片信息。continuewith open(os.path.join(originLabelsDir, txtFile), 'r') as fr:labelList = fr.readlines()for label in labelList:label = label.strip().split()x = float(label[1])y = float(label[2])w = float(label[3])h = float(label[4])# convert x,y,w,h to x1,y1,x2,y2H, W, _ = im.shapex1 = (x - w / 2) * Wy1 = (y - h / 2) * Hx2 = (x + w / 2) * Wy2 = (y + h / 2) * H# 标签序号从0开始计算, coco2017数据集标号混乱，不管它了。cls_id = int(label[0])   width = max(0, x2 - x1)height = max(0, y2 - y1)dataset['annotations'].append({'area': width * height,'bbox': [x1, y1, width, height],'category_id': cls_id,'id': ann_id_cnt,'image_id': k,'iscrowd': 0,# mask, 矩形是从左上角点按顺时针的四个顶点'segmentation': [[x1, y1, x2, y1, x2, y2, x1, y2]]})ann_id_cnt += 1# 保存结果folder = os.path.join(root_path, 'annotations')if not os.path.exists(folder):os.makedirs(folder)if arg.random_split or arg.split_by_file:for phase in ['train','val','test']:json_name = os.path.join(root_path, 'annotations/{}.json'.format(phase))with open(json_name, 'w') as f:if phase == 'train':json.dump(train_dataset, f)elif phase == 'val':json.dump(val_dataset, f)elif phase == 'test':json.dump(test_dataset, f)print('Save annotation to {}'.format(json_name))else:json_name = os.path.join(root_path, 'annotations/{}'.format(arg.save_path))with open(json_name, 'w') as f:json.dump(dataset, f)print('Save annotation to {}'.format(json_name))if __name__ == "__main__":yolo2coco(arg)

然后启用脚本进行标签格式转换：

python yolo2coco.py --root_dir /home/hary/ctc/mmdetection/Dataset_depth_YOLO --save_path train.json

这里root_dir是数据集文件夹路径，save_path指定了保存的json文件名称。

转换完成后，可以在原数据集文件夹下看到新建了一个annotations文件夹，里面就是转换好的json文件：

同理，我们把验证集的json文件也生成过来：

最后按以下方式合并摆放：

COCO_ROOT # 根目录
├── annotations # 存放json格式的标注
│ ├── instances_train2017.json
│ └── instances_val2017.json
└── train2017 # 存放图片文件
├── 000000000001.jpg
├── 000000000002.jpg
└── 000000000003.jpg
└── val2017
├── 000000000004.jpg
└── 000000000005.jpg