当前位置：首页 > news >正文

将LabelMe工具目标检测标注生成的json文件转换成COCO json格式

news 2025/11/17 6:11:02

安装labelme2coco，执行如下命令：

pip install labelme2coco

将使用LabelMe生成的.json文件转换成coco支持的json文件，执行以下命令：

labelme2coco melon_detect/train --category_id_start 1 # 生成的dataset.json重命名为train.json
labelme2coco melon_detect/val --category_id_start 1 # 生成的dataset.json重命名为val.json

结果如下所示：

{
"images":[{"height":340,"width":437,"id":1,"file_name":"melon_detect\\val\\0940ff7f2754e74b5ad6d13495cd13e1_t.jpeg"},{"height":534,"width":800,"id":2,"file_name":"melon_detect\\val\\14896085.webp"},{"height":693,"width":1024,"id":3,"file_name":"melon_detect\\val\\21319742_204241990080_2.jpg"},{"height":410,"width":600,"id":4,"file_name":"melon_detect\\val\\213511.jpg"},{"height":1157,"width":1600,"id":5,"file_name":"melon_detect\\val\\222859661.webp"}],
"annotations":[{"iscrowd":0,"image_id":1,"bbox":[35.65817694369973,171.87667560321717,234.85254691689005,133.51206434316356],"segmentation":[],"category_id":1,"id":1,"area":31355},{"iscrowd":0,"image_id":1,"bbox":[168.36595174262735,32.46648793565684,250.40214477211802,259.51742627345845],"segmentation":[],"category_id":1,"id":2,"area":64983},{"iscrowd":0,"image_id":2,"bbox":[105.90717299578058,250.12236286919833,421.5189873417721,232.48945147679322],"segmentation":[],"category_id":1,"id":3,"area":97998},{"iscrowd":0,"image_id":2,"bbox":[266.2447257383966,39.99578059071733,385.65400843881855,355.27426160337546],"segmentation":[],"category_id":1,"id":4,"area":137012},{"iscrowd":0,"image_id":3,"bbox":[205.44262295081967,17.53825136612023,618.5792349726776,598.9071038251367],"segmentation":[],"category_id":1,"id":5,"area":370471}],
"categories":[{"id":1,"name":"watermelon","supercategory":"watermelon"},{"id":2,"name":"wintermelon","supercategory":"wintermelon"}]
}

注：

1.LabelMe的label索引是从0开始的，而COCO类别ID必须从1开始，所以必须要加：--category_id_start 1

2.LabelMe的bbox为{x1,y1,x2,y2}，即左上角到右下角的两个点坐标。labelme2coco转换为COCO格式时将bbox自动转为{x1,y1,w,h}，但PyTorch中的目标检测需要{x1,y1,x2,y2}，所以实现中需要：boxes.append([x, y, x + w, y + h])

CocoDataset类实现如下：

import argparse
import colorama
import json
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms
from PIL import Image
from pathlib import Pathdef parse_args():parser = argparse.ArgumentParser(description="labelme to coco")parser.add_argument("--dataset_path", type=str, help="image dataset path")parser.add_argument("--json_file", type=str, help="image dataset json file, coco format")args = parser.parse_args()return argsclass CocoDataset(Dataset):def __init__(self, json_file, image_dir, transforms=None):self.image_dir = image_dirself.transforms = transformswith open(json_file, mode="r", encoding="utf-8") as f:coco = json.load(f)self.image_infos = {img["id"]: img for img in coco["images"]}self.image_ids = list(self.image_infos.keys())self.annotations = {}for ann in coco["annotations"]:img_id = ann["image_id"]self.annotations.setdefault(img_id, []).append(ann)def __len__(self):return len(self.image_ids)def __getitem__(self, idx):img_id = self.image_ids[idx]img_info = self.image_infos[img_id]file_path = Path(self.image_dir) / Path(img_info["file_name"]).nameif not file_path.exists():raise FileNotFoundError(colorama.Fore.RED + f"image not found: {file_path}")image = Image.open(file_path).convert("RGB")anns = self.annotations.get(img_id, [])boxes, labels, areas, iscrowd = [], [], [], []for ann in anns:x, y, w, h = ann["bbox"]if w <= 0 or h <= 0:continue# COCO bbox:[xmin, ymin, width, height]; PyTorch need:[xmin, ymin, xmax, ymax]boxes.append([x, y, x + w, y + h])labels.append(ann["category_id"])areas.append(ann.get("area", w * h))iscrowd.append(ann.get("iscrowd", 0))target = {"boxes": boxes,"labels": labels,"image_id": img_id,"areas": areas,"iscrowd": iscrowd,}if self.transforms is not None:image = self.transforms(image)return image, target# custom batch processing function to process different numbers of targets
def collate_fn(batch):return tuple(zip(*batch))if __name__ == "__main__":colorama.init(autoreset=True)args = parse_args()transform = transforms.Compose([transforms.ToTensor()])dataset = CocoDataset(args.json_file, args.dataset_path, transforms=transform)data_loader = DataLoader(dataset, batch_size=2, shuffle=True, num_workers=2, collate_fn=collate_fn)for idx, (images, targets) in enumerate(data_loader):print(f"idx: {idx}")for i in range(len(images)):print(f"image{i} shape: {images[i].shape}")print(f"boxes{i}: {targets[i]['boxes']}")print(f"labels{i}: {targets[i]['labels']}")print(colorama.Fore.GREEN + "====== execution completed ======")

执行结果如下图所示：