如何将 COCO 标注转换为 YOLO 格式#

from ultralytics.data.converter import convert_coco

convert_coco(
    labels_dir="my_dataset/annotations/",  # 包含 JSON 文件的目录
    save_dir="my_dataset/converted/",  # 转换后标签的保存位置
    cls91to80=False,  # 自定义数据集请设为 False（见下方警告）
)

my_dataset/
├── images/
│   ├── train/
│   │   ├── img_001.jpg
│   │   ├── img_002.jpg
│   │   └── ...
│   └── val/
│       ├── img_100.jpg
│       └── ...
└── annotations/
    ├── instances_train.json
    └── instances_val.json

{
    "images": [{ "id": 1, "file_name": "img_001.jpg", "width": 640, "height": 480 }],
    "annotations": [
        {
            "id": 1,
            "image_id": 1,
            "category_id": 1,
            "bbox": [100, 50, 200, 150],
            "area": 30000,
            "iscrowd": 0
        }
    ],
    "categories": [
        { "id": 1, "name": "helmet" },
        { "id": 2, "name": "vest" }
    ]
}

my_dataset/converted/
├── images/      # created but left empty
└── labels/
    ├── train/   # from instances_train.json
    │   ├── img_001.txt
    │   └── ...
    └── val/     # from instances_val.json
        └── ...

import shutil
from pathlib import Path

converted_dir = Path("my_dataset/converted/labels")
dataset_dir = Path("my_dataset")

# convert_coco 会以对应 JSON 文件名（去掉 "instances_" 前缀）命名每个子目录，
# 因此请遍历实际的子目录，而不要假定目录名为 "train"/"val"。
for src in converted_dir.iterdir():
    if not src.is_dir():
        continue
    dst = dataset_dir / "labels" / src.name
    dst.mkdir(parents=True, exist_ok=True)
    for f in src.glob("*.txt"):
        shutil.move(str(f), str(dst / f.name))

my_dataset/
├── images/
│   ├── train/
│   │   ├── img_001.jpg
│   │   └── ...
│   └── val/
│       └── ...
├── labels/
│   ├── train/
│   │   ├── img_001.txt
│   │   └── ...
│   └── val/
│       └── ...
└── dataset.yaml

import json
from pathlib import Path

import yaml

# 从 COCO JSON 读取类别
with open("my_dataset/annotations/instances_train.json") as f:
    coco = json.load(f)

# 构建与 convert_coco 输出相匹配的类别名称（category_id - 1）
categories = sorted(coco["categories"], key=lambda x: x["id"])
names = {cat["id"] - 1: cat["name"] for cat in categories}
# 注意：convert_coco 会将类别 ID 映射为 category_id - 1，因此 category_id 必须
# 从 1 开始。如果类别从 0 开始，请先将每个 ID 加 1。

# 创建 dataset.yaml
dataset = {
    "path": str(Path("my_dataset").resolve()),
    "train": "images/train",
    "val": "images/val",
    "names": names,
}

with open("my_dataset/dataset.yaml", "w") as f:
    yaml.dump(dataset, f, default_flow_style=False)

path: /absolute/path/to/my_dataset
train: images/train
val: images/val
names:
    0: helmet
    1: vest

from pathlib import Path

label_file = Path("my_dataset/labels/train/img_001.txt")
for line in label_file.read_text().strip().splitlines():
    parts = line.split()
    cls_id = int(parts[0])
    coords = [float(v) for v in parts[1:5]]
    assert cls_id >= 0, f"Negative class ID {cls_id} — category_id in your JSON may start from 0"
    assert all(0 <= v <= 1 for v in coords), f"Coordinates out of [0, 1] range: {coords}"