split_conversion将json转成yolo训练用的txt,在直接按照8：1：1的比例分成训练集，测试集，验证集

第一章使用说明

类别自己在代码中改，其他四个参数

--json-folder:json文件夹路径

--txt-folder：转换成功后txt的存放路径

--images-dir：图片文件夹路径

--save-dir：转换完成分割后所有文件的路径

终端命令行：python split_conversion.py --json-folder "" --txt-folder "" --images-dir "" --save-dir ""

""处是四个路径

第二章导包

import json
import os
from tqdm import tqdm
import shutil
import random
import argparse

第三章转换格式函数

def labelme_json_to_yolo(txt_save_path, json_path, class_map):
    """
    将LabelMe格式JSON转换为YOLO TXT标注文件
    :param txt_save_path: TXT保存路径
    :param json_path: LabelMe JSON文件路径
    :param class_map: 类别名映射字典（如{"person": 0}）
    """
    with open(json_path, 'r', encoding='utf-8') as f:
        data = json.load(f)

    img_height = data["imageHeight"]
    img_width = data["imageWidth"]
    img_name = os.path.basename(data["imagePath"])  # 提取图片文件名
    txt_name = os.path.splitext(img_name)[0] + ".txt"
    txt_path = os.path.join(txt_save_path, txt_name)

    lines = []
    for shape in data["shapes"]:
        label = shape["label"]
        if label not in class_map:
            continue  # 跳过未定义类别
        cls_id = class_map[label]

        # 解析多边形/矩形标注为边界框（xmin, ymin, xmax, ymax）
        points = shape["points"]
        x_coords = [p[0] for p in points]
        y_coords = [p[1] for p in points]
        xmin = min(x_coords)
        ymin = min(y_coords)
        xmax = max(x_coords)
        ymax = max(y_coords)

        # 计算YOLO格式坐标（归一化中心坐标+宽高）
        x_center = (xmin + xmax) / (2 * img_width)
        y_center = (ymin + ymax) / (2 * img_height)
        w = (xmax - xmin) / img_width
        h = (ymax - ymin) / img_height

        # 过滤无效坐标（避免越界）
        if 0 <= x_center <= 1 and 0 <= y_center <= 1 and w > 0 and h > 0:
            lines.append(f"{cls_id} {x_center:.6f} {y_center:.6f} {w:.6f} {h:.6f}")

    # 保存TXT文件
    with open(txt_path, 'w') as f:
        f.write('\n'.join(lines))

第四章划分函数

def batch_convert_labelme_to_yolo(json_folder, txt_folder, class_map):
    """
    批量转换LabelMe格式JSON文件夹到YOLO TXT
    :param json_folder: JSON文件夹路径
    :param txt_folder: TXT保存路径
    :param class_map: 类别名映射字典（如{"person": 0}）
    """
    os.makedirs(txt_folder, exist_ok=True)
    json_files = [f for f in os.listdir(json_folder) if f.lower().endswith('.json')]

    for json_file in tqdm(json_files, desc="转换中"):
        json_path = os.path.join(json_folder, json_file)
        labelme_json_to_yolo(txt_folder, json_path, class_map)

    print(f"批量转换完成！共处理{len(json_files)}个JSON文件，保存到：{txt_folder}")

第五章确认文件夹是否存在

def mkdir(path):
    if not os.path.exists(path):
        os.makedirs(path)

第六章主函数

def main(image_dir, txt_dir, save_dir):
    # 创建文件夹
    mkdir(save_dir)
    images_dir = os.path.join(save_dir, 'images')
    labels_dir = os.path.join(save_dir, 'labels')

    img_train_path = os.path.join(images_dir, 'train')
    img_test_path = os.path.join(images_dir, 'test')
    img_val_path = os.path.join(images_dir, 'val')

    label_train_path = os.path.join(labels_dir, 'train')
    label_test_path = os.path.join(labels_dir, 'test')
    label_val_path = os.path.join(labels_dir, 'val')

    mkdir(images_dir)
    mkdir(labels_dir)
    mkdir(img_train_path)
    mkdir(img_test_path)
    mkdir(img_val_path)
    mkdir(label_train_path)
    mkdir(label_test_path)
    mkdir(label_val_path)

    # 数据集划分比例，训练集80%，验证集10%，测试集10%，按需修改
    train_percent = 0.8
    val_percent = 0.1
    test_percent = 0.1

    total_txt = os.listdir(txt_dir)
    num_txt = len(total_txt)
    list_all_txt = range(num_txt)  # 范围 range(0, num)

    num_train = int(num_txt * train_percent)
    num_val = int(num_txt * val_percent)
    num_test = num_txt - num_train - num_val

    train = random.sample(list_all_txt, num_train)
    # 在全部数据集中取出train
    val_test = [i for i in list_all_txt if not i in train]
    # 再从val_test取出num_val个元素，val_test剩下的元素就是test
    val = random.sample(val_test, num_val)

    print("训练集数目：{}, 验证集数目：{}, 测试集数目：{}".format(len(train), len(val), len(val_test) - len(val)))
    for i in list_all_txt:
        name = total_txt[i][:-4]

        srcImage = os.path.join(image_dir, name + '.jpg')
        srcLabel = os.path.join(txt_dir, name + '.txt')

        if i in train:
            dst_train_Image = os.path.join(img_train_path, name + '.jpg')
            dst_train_Label = os.path.join(label_train_path, name + '.txt')
            shutil.copyfile(srcImage, dst_train_Image)
            shutil.copyfile(srcLabel, dst_train_Label)
        elif i in val:
            dst_val_Image = os.path.join(img_val_path, name + '.jpg')
            dst_val_Label = os.path.join(label_val_path, name + '.txt')
            shutil.copyfile(srcImage, dst_val_Image)
            shutil.copyfile(srcLabel, dst_val_Label)
        else:
            dst_test_Image = os.path.join(img_test_path, name + '.jpg')
            dst_test_Label = os.path.join(label_test_path, name + '.txt')
            shutil.copyfile(srcImage, dst_test_Image)
            shutil.copyfile(srcLabel, dst_test_Label)

第七章主函数调用

if __name__ == "__main__":
    parser = argparse.ArgumentParser(description='Convert LabelMe JSON to YOLO TXT and split datasets')
    parser.add_argument('--json-folder', type=str, default=r'',
                        help='LabelMe JSON folder path')
    parser.add_argument('--txt-folder', type=str, default=r'',
                        help='YOLO TXT save path')
    parser.add_argument('--class-map', default={"自己的类别": 0}, type=dict,
                        help='Class name mapping dictionary (e.g. {"person": 0})')
    parser.add_argument('--images-dir', type=str, default=r'', help='images path dir')
    parser.add_argument('--save-dir', default=r'', type=str, help='save dir')
    args = parser.parse_args()

    json_folder = args.json_folder
    txt_folder = args.txt_folder
    class_map = args.class_map
    image_dir = args.images_dir
    save_dir = args.save_dir

    # 转换LabelMe JSON到YOLO TXT
    batch_convert_labelme_to_yolo(json_folder, txt_folder, class_map)

    # 划分数据集
    main(image_dir, txt_folder, save_dir)

全部代码如下：

import json
import os
from tqdm import tqdm  # 可选进度条库
import shutil
import random
import argparse


def labelme_json_to_yolo(txt_save_path, json_path, class_map):
    """
    将LabelMe格式JSON转换为YOLO TXT标注文件
    :param txt_save_path: TXT保存路径
    :param json_path: LabelMe JSON文件路径
    :param class_map: 类别名映射字典（如{"person": 0}）
    """
    with open(json_path, 'r', encoding='utf-8') as f:
        data = json.load(f)

    img_height = data["imageHeight"]
    img_width = data["imageWidth"]
    img_name = os.path.basename(data["imagePath"])  # 提取图片文件名
    txt_name = os.path.splitext(img_name)[0] + ".txt"
    txt_path = os.path.join(txt_save_path, txt_name)

    lines = []
    for shape in data["shapes"]:
        label = shape["label"]
        if label not in class_map:
            continue  # 跳过未定义类别
        cls_id = class_map[label]

        # 解析多边形/矩形标注为边界框（xmin, ymin, xmax, ymax）
        points = shape["points"]
        x_coords = [p[0] for p in points]
        y_coords = [p[1] for p in points]
        xmin = min(x_coords)
        ymin = min(y_coords)
        xmax = max(x_coords)
        ymax = max(y_coords)

        # 计算YOLO格式坐标（归一化中心坐标+宽高）
        x_center = (xmin + xmax) / (2 * img_width)
        y_center = (ymin + ymax) / (2 * img_height)
        w = (xmax - xmin) / img_width
        h = (ymax - ymin) / img_height

        # 过滤无效坐标（避免越界）
        if 0 <= x_center <= 1 and 0 <= y_center <= 1 and w > 0 and h > 0:
            lines.append(f"{cls_id} {x_center:.6f} {y_center:.6f} {w:.6f} {h:.6f}")

    # 保存TXT文件
    with open(txt_path, 'w') as f:
        f.write('\n'.join(lines))


def batch_convert_labelme_to_yolo(json_folder, txt_folder, class_map):
    """
    批量转换LabelMe格式JSON文件夹到YOLO TXT
    :param json_folder: JSON文件夹路径
    :param txt_folder: TXT保存路径
    :param class_map: 类别名映射字典（如{"person": 0}）
    """
    os.makedirs(txt_folder, exist_ok=True)
    json_files = [f for f in os.listdir(json_folder) if f.lower().endswith('.json')]

    for json_file in tqdm(json_files, desc="转换中"):
        json_path = os.path.join(json_folder, json_file)
        labelme_json_to_yolo(txt_folder, json_path, class_map)

    print(f"批量转换完成！共处理{len(json_files)}个JSON文件，保存到：{txt_folder}")


# 检查文件夹是否存在
def mkdir(path):
    if not os.path.exists(path):
        os.makedirs(path)


def main(image_dir, txt_dir, save_dir):
    # 创建文件夹
    mkdir(save_dir)
    images_dir = os.path.join(save_dir, 'images')
    labels_dir = os.path.join(save_dir, 'labels')

    img_train_path = os.path.join(images_dir, 'train')
    img_test_path = os.path.join(images_dir, 'test')
    img_val_path = os.path.join(images_dir, 'val')

    label_train_path = os.path.join(labels_dir, 'train')
    label_test_path = os.path.join(labels_dir, 'test')
    label_val_path = os.path.join(labels_dir, 'val')

    mkdir(images_dir)
    mkdir(labels_dir)
    mkdir(img_train_path)
    mkdir(img_test_path)
    mkdir(img_val_path)
    mkdir(label_train_path)
    mkdir(label_test_path)
    mkdir(label_val_path)

    # 数据集划分比例，训练集80%，验证集10%，测试集10%，按需修改
    train_percent = 0.8
    val_percent = 0.1
    test_percent = 0.1

    total_txt = os.listdir(txt_dir)
    num_txt = len(total_txt)
    list_all_txt = range(num_txt)  # 范围 range(0, num)

    num_train = int(num_txt * train_percent)
    num_val = int(num_txt * val_percent)
    num_test = num_txt - num_train - num_val

    train = random.sample(list_all_txt, num_train)
    # 在全部数据集中取出train
    val_test = [i for i in list_all_txt if not i in train]
    # 再从val_test取出num_val个元素，val_test剩下的元素就是test
    val = random.sample(val_test, num_val)

    print("训练集数目：{}, 验证集数目：{}, 测试集数目：{}".format(len(train), len(val), len(val_test) - len(val)))
    for i in list_all_txt:
        name = total_txt[i][:-4]

        srcImage = os.path.join(image_dir, name + '.jpg')
        srcLabel = os.path.join(txt_dir, name + '.txt')

        if i in train:
            dst_train_Image = os.path.join(img_train_path, name + '.jpg')
            dst_train_Label = os.path.join(label_train_path, name + '.txt')
            shutil.copyfile(srcImage, dst_train_Image)
            shutil.copyfile(srcLabel, dst_train_Label)
        elif i in val:
            dst_val_Image = os.path.join(img_val_path, name + '.jpg')
            dst_val_Label = os.path.join(label_val_path, name + '.txt')
            shutil.copyfile(srcImage, dst_val_Image)
            shutil.copyfile(srcLabel, dst_val_Label)
        else:
            dst_test_Image = os.path.join(img_test_path, name + '.jpg')
            dst_test_Label = os.path.join(label_test_path, name + '.txt')
            shutil.copyfile(srcImage, dst_test_Image)
            shutil.copyfile(srcLabel, dst_test_Label)


if __name__ == "__main__":
    parser = argparse.ArgumentParser(description='Convert LabelMe JSON to YOLO TXT and split datasets')
    parser.add_argument('--json-folder', type=str, default=r'',
                        help='LabelMe JSON folder path')
    parser.add_argument('--txt-folder', type=str, default=r'',
                        help='YOLO TXT save path')
    parser.add_argument('--class-map', default={"自己的类别": 0}, type=dict,
                        help='Class name mapping dictionary (e.g. {"person": 0})')
    parser.add_argument('--images-dir', type=str, default=r'', help='images path dir')
    parser.add_argument('--save-dir', default=r'', type=str, help='save dir')
    args = parser.parse_args()

    json_folder = args.json_folder
    txt_folder = args.txt_folder
    class_map = args.class_map
    image_dir = args.images_dir
    save_dir = args.save_dir

    # 转换LabelMe JSON到YOLO TXT
    batch_convert_labelme_to_yolo(json_folder, txt_folder, class_map)

    # 划分数据集
    main(image_dir, txt_folder, save_dir)