Win10 Labelme标注数据转为YOLOV5 训练的数据集

男娘i 2022-12-11 07:48 410阅读 0赞

*  将Labelme标注的数据复制到工程的根目录，并将其命名为LabelmeData。我的工程根目录是yolov5-master，如下图：![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2hoaGhoaGhoaGh3d3d3d3d3d3d3_size_16_color_FFFFFF_t_70][]

*  打开工程，在根目录新建LabelmeToYolov5.py。写入下面的代码

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 = ["aircraft", "oiltank"]
    # 1.标签路径
    labelme_path = "LabelmeData/"
    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")
    '''
    file1 = open("tmp/train.txt", "r")
    file2 = open("tmp/val.txt", "r")
    file_list1 = file1.readlines()  # 将所有变量读入列表file_list1
    
    file_list2 = file2.readlines()  # 将所有变量读入列表file_list2
    file3 = open("tmp/trainval.txt", "w")
    for line in file_list1:
        print(line)
        file3.write(line)
    for line in file_list2:
        print(line)
        file3.write(line)
    '''

这段代码执行完成会在LabelmeData生成每个图片的txt标注数据，同时在tmp文件夹下面生成训练集、验证集和测试集的txt，txt记录的是图片的路径，为下一步生成YoloV5训练和测试用的数据集做准备。

*  在tmp文件夹新建makedata.py。执行完成后会在工程的根目录生成VOC数据集。

import shutil
    import os
    
    file_List = ["train", "val", "test"]
    for file in file_List:
        if not os.path.exists('../VOC/images/%s' % file):
            os.makedirs('../VOC/images/%s' % file)
        if not os.path.exists('../VOC/labels/%s' % file):
            os.makedirs('../VOC/labels/%s' % file)
        print(os.path.exists('../tmp/%s.txt' % file))
        f = open('../tmp/%s.txt' % file, 'r')
        lines = f.readlines()
        for line in lines:
            print(line)
            line = "/".join(line.split('/')[-5:]).strip()
            shutil.copy(line, "../VOC/images/%s" % file)
            line = line.replace('jpg', 'txt')
            shutil.copy(line, "../VOC/labels/%s/" % file)

运行结果如下：![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2hoaGhoaGhoaGh3d3d3d3d3d3d3_size_16_color_FFFFFF_t_70 1][]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2hoaGhoaGhoaGh3d3d3d3d3d3d3_size_16_color_FFFFFF_t_70]: /images/20221123/77a1017d862846f4aa2fe071d37b2d9b.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2hoaGhoaGhoaGh3d3d3d3d3d3d3_size_16_color_FFFFFF_t_70 1]: /images/20221123/b2d14456b1c541f9a84924d76ba1ac05.png