json转txt格式，将隐藏点在txt中可视数据改为1（labelme）

在前几天我使用yolov8时，找网上转格式的代码，发现没有自己想要的，于是进行改编捣鼓了一下。

一、打开labelme

二、创建图形将所要的物体框起来（这里我用的是矩形）

三、打上关键点（即控制点）

对于可见点，正常打点，写名称；对于不可见点，打点写名称后，在discription中写下hidden

四、转换格式代码，由于我的description是hidden，所以代码中我写的是识别到hidden更改可见数据，可按需更改。

import json
import os

#更改为你的标注框的信息
#更改为你关键点的信息（名称）

bbox_class = {
    'pen': 0
}
keypoint_class = [
    'spot_1', 'spot_2', 'spot_3'
]
# 设定文件夹路径
folder_path = r"D:\Download\ultralytics-main\111111labels\camera4\labels"
files = os.listdir(folder_path)

for file in files:
    if file.endswith('.json'):
        # 完整的文件路径
        labelme_path = os.path.join(folder_path, file)
        with open(labelme_path, 'r', encoding='utf-8') as f:
            labelme = json.load(f)

        img_width = labelme['imageWidth']
        img_height = labelme['imageHeight']

        # 生成 YOLO 格式的 txt 文件
        suffix = labelme_path.rsplit('.', 1)[0]
        yolo_txt_path = suffix + '.txt'
        with open(yolo_txt_path, 'w', encoding='utf-8') as f:
            for each_ann in labelme['shapes']:
                if each_ann['shape_type'] == 'rectangle':
                    yolo_str = ''
                    bbox_class_id = bbox_class[each_ann['label']]
                    yolo_str += '{} '.format(bbox_class_id)
                    bbox = [min(each_ann['points'][0][0], each_ann['points'][1][0]),
                            max(each_ann['points'][0][0], each_ann['points'][1][0]),
                            min(each_ann['points'][0][1], each_ann['points'][1][1]),
                            max(each_ann['points'][0][1], each_ann['points'][1][1])]
                    bbox_center_x = (bbox[0] + bbox[1]) / 2
                    bbox_center_y = (bbox[2] + bbox[3]) / 2
                    bbox_width = bbox[1] - bbox[0]
                    bbox_height = bbox[3] - bbox[2]
                    bbox_center_x_norm = bbox_center_x / img_width
                    bbox_center_y_norm = bbox_center_y / img_height
                    bbox_width_norm = bbox_width / img_width
                    bbox_height_norm = bbox_height / img_height

                    yolo_str += '{:.5f} {:.5f} {:.5f} {:.5f} '.format(
                        bbox_center_x_norm, bbox_center_y_norm, bbox_width_norm, bbox_height_norm)

                    bbox_keypoints_dict = {}
                    for point_ann in labelme['shapes']:
                        if point_ann['shape_type'] == 'point':
                            x = point_ann['points'][0][0]
                            y = point_ann['points'][0][1]
                            label = point_ann['label']
                            if bbox[0] < x < bbox[1] and bbox[2] < y < bbox[3]:
                                bbox_keypoints_dict[label] = [x, y]

                    # 创建一个字典来存储每个spot的可视化值
                    spot_visualization_values = {
                        'spot_1': None,
                        'spot_2': None,
                        'spot_3': None
                    }

                    # 遍历所有形状以收集spot的可视化值
                    for shape in labelme['shapes']:
                        if shape['shape_type'] == 'point':
                            label = shape['label']
                            if label in spot_visualization_values:
                                # 检查description是否包含"hidden"
                                is_hidden = 'hidden' in (shape.get('description', '').lower())

                                # 设置可视化值
                                spot_visualization_values[label] = 1 if is_hidden else 2

                    # 遍历所有关键点类
                    for each_class in keypoint_class:
                        if each_class in spot_visualization_values:
                            visualization_value=spot_visualization_values[each_class]
                            # 检查当前spot是否在bbox_keypoints_dict的当前类中定义
                            # 获取关键点坐标并归一化
                            keypoint_x_norm = bbox_keypoints_dict[each_class][0] / img_width
                            keypoint_y_norm = bbox_keypoints_dict[each_class][1] / img_height
                            yolo_str += '{:.6f} {:.6f} {} '.format(keypoint_x_norm, keypoint_y_norm,
                                                                               visualization_value)
                        else:
                            yolo_str += '0 0 0 '
                    f.write(yolo_str + '\n')

        print('{} --> {} 转换完成'.format(labelme_path, yolo_txt_path))
        print(f"Processing class: {each_class}")
        print(f"Available keys in bbox_keypoints_dict: {bbox_keypoints_dict.keys()}")

五、改完数据如下：

前五个是框的数据，后面每三个是关键点的数据，关键点数据中，1表示隐藏点，2可见点。

注意：可见点数据必须要是六位小数（至少我用的版本需要），我就踩坑了，检查了好久才发现是这里出错了。