yolov5训练自己的数据集——labelme生成的json文件转txt文件

搜了好多json改txt的文章，有的看不懂自己用需要改哪里，有的只能单张转换，下面记录一下整个文件夹的json文件改txt文件的方法吧。

labelme对jpg文件进行标注后保存为json格式，json内主要信息如下：

{
  "version": "5.1.1",
  "flags": {},
  "shapes": [ { "label": "SmallCar",
      "points": [        [          2036.0,          548.0        ],        [          2756.0,          1126.0        ]      ],
      "group_id": null,
      "shape_type": "rectangle",
      "flags": {}
    },....... ],

"imagePath": "118.jpg",

"imageHeight": 1860,

"imageWidth": 2880
}

shapes：保存着bbox的类别和坐标（左上角，右下角）；

imagePath：json文件对应的原图名称；

imageHeight：原图的高度；

imageWidth：原图的宽度；

将json文件中的信息提取至txt文件内，代码实现如下：

import os
import json
import numpy as np
# 类和索引
CLASSES = ["SmallCar", "BigCar", "NonMotorVeh", "Cyclist", "R", "RG", "RR", "RY", "LR", "Pedestrain", "LY", "G", "B", "FR", "FG"]   # 改这


def convert(size, box):
    '''
    input:
    size:(width,height);
    box:(x1,x2,y1,y2)
    output:
    (x,y,w,h)
    '''
    dw = 1. / size[0]
    dh = 1. / size[1]
    x = (box[0] + box[1]) / 2.0
    y = (box[2] + box[3]) / 2.0
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x * dw
    w = w * dw
    y = y * dh
    h = h * dh
    return (x, y, w, h)


# json -> txt
def json2txt(path_json, path_txt):
    with open(path_json, "r") as path_json:
        jsonx = json.load(path_json)
        width = int(jsonx["imageWidth"])      # 原图的宽
        height = int(jsonx["imageHeight"])    # 原图的高
        with open(path_txt, "w+") as ftxt:
            # 遍历每一个bbox对象
            for shape in jsonx["shapes"]:
                obj_cls = str(shape["label"])     # 获取类别
                cls_id = CLASSES.index(obj_cls)   # 获取类别索引
                points = np.array(shape["points"])    # 获取(x1,y1,x2,y2)
                x1 = int(points[0][0])
                y1 = int(points[0][1])
                x2 = int(points[1][0])
                y2 = int(points[1][1])
                # (左上角,右下角) -> (中心点,宽高) 归一化
                bb = convert((width, height), (x1, x2, y1, y2))
                ftxt.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + "\n")


if __name__ == "__main__":
    # json文件夹 不同的json文件夹记得换路径
    dir_json = "/home/lyn/Desktop/mydatasets/labels/val/"
    # txt文件夹 想让生成的txt文件放哪就改到哪个路径
    dir_txt = "/home/lyn/Desktop/mydatasets/labels/val/"
    if not os.path.exists(dir_txt):
        os.makedirs(dir_txt)
    # 得到所有json文件
    list_json = os.listdir(dir_json)
    # 遍历每一个json文件,转成txt文件
    for cnt, json_name in enumerate(list_json):
        print("cnt=%d,name=%s" % (cnt, json_name))
        path_json = dir_json + json_name
        path_txt = dir_txt + json_name.replace(".json", ".txt")
        # (x1,y1,x2,y2)->(x,y,w,h)
        json2txt(path_json, path_txt)

转换不同文件夹内的json文件只需将文件夹路径传入dir_json；

dir_txt后为生成的txt文件存放位置。

注意CLASSES=[ ]内要放置json文件对应含有的类。

小改一下，源码来自YouOnly_LiveOnce https://www.bilibili.com/read/cv18350780 出处bilibili

方法二：

import os
import numpy as np
import json
from glob import glob
import cv2
from sklearn.model_selection import train_test_split
from os import getcwd

classes = ["SmallCar", "BigCar", "G", "R", "RG", "Cyclist", "B", "NonMotorVeh"]   # 输入json文件内含有的类
labelme_path = "/home/lyn/Desktop/yolov5-master/datasets/"   # 这个文件夹内同时放了jpg文件和json文件，生成的txt文件也会存放其中
isUseTest = True  # 是否创建test集
# 3.获取待处理文件
files = glob(labelme_path + "*.json")
files = [i.replace("\\", "/").split("/")[-1].split(".json")[0] for i in files]
print(files)
if isUseTest:
    trainval_files, test_files = train_test_split(files, test_size=0.1, random_state=55)
else:
    trainval_files = files
# split
train_files, val_files = train_test_split(trainval_files, test_size=0.1, random_state=55)


def convert(size, box):
    dw = 1. / (size[0])
    dh = 1. / (size[1])
    x = (box[0] + box[1]) / 2.0 - 1
    y = (box[2] + box[3]) / 2.0 - 1
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x * dw
    w = w * dw
    y = y * dh
    h = h * dh
    return (x, y, w, h)


wd = getcwd()
print(wd)


def ChangeToYolo5(files, txt_Name):
    if not os.path.exists('tmp/'):
        os.makedirs('tmp/')
    list_file = open('tmp/%s.txt' % (txt_Name), 'w')
    for json_file_ in files:
        json_filename = labelme_path + json_file_ + ".json"
        imagePath = labelme_path + json_file_ + ".jpg"
        list_file.write('%s/%s\n' % (wd, imagePath))
        out_file = open('%s/%s.txt' % (labelme_path, json_file_), 'w')
        json_file = json.load(open(json_filename, "r", encoding="utf-8"))
        height, width, channels = cv2.imread(labelme_path + json_file_ + ".jpg").shape
        for multi in json_file["shapes"]:
            points = np.array(multi["points"])
            xmin = min(points[:, 0]) if min(points[:, 0]) > 0 else 0
            xmax = max(points[:, 0]) if max(points[:, 0]) > 0 else 0
            ymin = min(points[:, 1]) if min(points[:, 1]) > 0 else 0
            ymax = max(points[:, 1]) if max(points[:, 1]) > 0 else 0
            label = multi["label"]
            if xmax <= xmin:
                pass
            elif ymax <= ymin:
                pass
            else:
                cls_id = classes.index(label)
                b = (float(xmin), float(xmax), float(ymin), float(ymax))
                bb = convert((width, height), b)
                out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
                print(json_filename, xmin, ymin, xmax, ymax, cls_id)


ChangeToYolo5(train_files, "train")
ChangeToYolo5(val_files, "val")
ChangeToYolo5(test_files, "test")

尝试后发现两个生成的txt文件点的坐标值略微有点区别，具体用哪一个本人水平不够看不出来哪个更好，能跑哪个是哪个吧。