将json文件转化成yolov8训练格式 |
您所在的位置：网站首页 › 甲骨文数据集 json yolo › 将json文件转化成yolov8训练格式 |
将json文件转化成yolov8训练格式
|
前期条件：已经使用labelme做好json文件。可以看以下博客。 https://blog.csdn.net/Wu_GuiMing/article/details/130625940?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522171280483116800213081813%2522%252C%2522scm%2522%253A%252220140713.130102334..%2522%257D&request_id=171280483116800213081813&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~top_positive~default-1-130625940-null-null.nonecase&utm_term=labelme%E5%AE%89%E8%A3%85&spm=1018.2226.3001.4450 转化过程：1、将json文件转化成txt文件 2、将文件分成训练集、验证集、测试集 以下代码将json文件转化成txt文件 import json import os import argparse from tqdm import tqdm def convert_label_json(json_dir, save_dir, classes): json_paths = os.listdir(json_dir) classes = classes.split(',') for json_path in tqdm(json_paths): # for json_path in json_paths: path = os.path.join(json_dir, json_path) try: with open(path, 'r', encoding='utf-8') as load_f: json_dict = json.loads(load_f.read()) except json.JSONDecodeError: print(f"Error decoding file {path}. Skipping.") continue # with open(path, 'r', encoding='utf-8') as load_f: # json_dict = json.load(load_f) h, w = json_dict['imageHeight'], json_dict['imageWidth'] # save txt path txt_path = os.path.join(save_dir, json_path.replace('json', 'txt')) txt_file = open(txt_path, 'w') for shape_dict in json_dict['shapes']: label = shape_dict['label'] label_index = classes.index(label) points = shape_dict['points'] points_nor_list = [] for point in points: points_nor_list.append(point[0] / w) points_nor_list.append(point[1] / h) points_nor_list = list(map(lambda x: str(x), points_nor_list)) points_nor_str = ' '.join(points_nor_list) label_str = str(label_index) + ' ' + points_nor_str + '\n' txt_file.writelines(label_str) if __name__ == "__main__": """ python json2txt_nomalize.py --json-dir my_datasets/color_rings/jsons --save-dir my_datasets/color_rings/txts --classes "duck" """ parser = argparse.ArgumentParser(description='json convert to txt params') parser.add_argument('--json-dir', type=str, default='H:/labelImg-master/labelImg-master/datas/data/eggbox1json/', help='json path dir') parser.add_argument('--save-dir', type=str, default='H:/labelImg-master/labelImg-master/datas/data/eggbox1txt/', help='txt save dir') parser.add_argument('--classes', type=str, default='eggbox', help='classes') args = parser.parse_args() json_dir = args.json_dir save_dir = args.save_dir classes = args.classes convert_label_json(json_dir, save_dir, classes)以下路径是自己json文件的路径 parser = argparse.ArgumentParser(description='json convert to txt params') parser.add_argument('--json-dir', type=str, default='H:/labelImg-master/labelImg-master/datas/data/eggbox1json/', help='json path dir') parser.add_argument('--save-dir', type=str, default='H:/labelImg-master/labelImg-master/datas/data/eggbox1txt/', help='txt save dir') parser.add_argument('--classes', type=str, default='eggbox', help='classes')--json-dir：json的文件夹；--save-dir：生成txt的文件夹；--classes：类别 生成文件夹如下：
以下代码将文件分成训练集、验证集、测试集 # 将图片和标注数据按比例切分为 训练集和测试集 import shutil import random import os import argparse # 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75%，验证集15%，测试集15%，按需修改 train_percent = 0.85 val_percent = 0.14 test_percent = 0.01 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__': """ python split_datasets.py --image-dir my_datasets/color_rings/imgs --txt-dir my_datasets/color_rings/txts --save-dir my_datasets/color_rings/train_data """ parser = argparse.ArgumentParser(description='split datasets to train,val,test params') parser.add_argument('--image-dir', type=str, default='H:/labelImg-master/labelImg-master/datas/data/eggboximage1/', help='image path dir') parser.add_argument('--txt-dir', type=str, default='H:/labelImg-master/labelImg-master/datas/data/eggbox1txt/', help='txt path dir') parser.add_argument('--save-dir', default='H:/labelImg-master/labelImg-master/datas/data/eggbox1split', type=str, help='save dir') args = parser.parse_args() image_dir = args.image_dir txt_dir = args.txt_dir save_dir = args.save_dir main(image_dir, txt_dir, save_dir)改变以下路径 parser = argparse.ArgumentParser(description='split datasets to train,val,test params') parser.add_argument('--image-dir', type=str, default='H:/labelImg-master/labelImg-master/datas/data/eggboximage1/', help='image path dir') parser.add_argument('--txt-dir', type=str, default='H:/labelImg-master/labelImg-master/datas/data/eggbox1txt/', help='txt path dir') parser.add_argument('--save-dir', default='H:/labelImg-master/labelImg-master/datas/data/eggbox1split', type=str, help='save dir')--image-dir：图像文件夹内容如下所示（有图像就可）
生成如下文件：
参考以下博客：制作自己的数据集并训练的YOLOv8模型_yolov8 分类 训练-CSDN博客 |
【本文地址】
公司简介
联系我们
今日新闻 |
点击排行 |
|
推荐新闻 |
图片新闻 |
|
专题文章 |