coco数据集2014下载地址：
链接: https://pan.baidu.com/s/1-oYvt2vpR_vzgvzGd7xmig 密码: r3bt
按照这个可以看到最终需要什么样子的格式，主要为： 第一个是目标矩形框的类别标签和外框坐标+长宽 第二个图片（train+test） 第三和四是图片检索列表
我这边现有的数据为 json格式的，因为原先的检测是centernet网络 里面的格式看这里：COCO数据集的标注格式
转换的代码如下：
#python import json from collections import defaultdict #这个模块实现了特定目标的容器，以提供Python标准内建容器 dict、list、set、tuple 的替代选择 from pycocotools.coco import COCO import numpy as np import tqdm import argparse """hyper parameters""" json_file_path = '/home/psdz/桌面/YOLO/data/cocodj/annotations/instances_trainval2014.json' images_dir_path = 'data/cocodj/images/train/' output_file = '/home/psdz/桌面/YOLO/data/cocodj/train.txt' name1='data/cocodj/images/train/' """load json file""" name_box_id = defaultdict(list) #defaultdict：字典的子类，提供了一个工厂函数，为字典查询提供了默认值 id_name = dict() #Python内置了字典：dict的支持，dict全称dictionary，在其他语言中也称为map，字典是另 一种可变容器模型，且可存储任意类型对象。具有极快的查找速度。 def arg_parser(): parser = argparse.ArgumentParser('code by rbj') parser.add_argument('--annotation_path', type=str, default=json_file_path) #生成的txt文件保存的目录 parser.add_argument('--save_base_path', type=str, default='/home/psdz/桌面/YOLO/data/cocodj/labels/train/') args = parser.parse_args() return args args = arg_parser() annotation_path = args.annotation_path save_base_path = args.save_base_path data_source = COCO(annotation_file=annotation_path) catIds = data_source.getCatIds() categories = data_source.loadCats(catIds) categories.sort(key=lambda x: x['id']) classes = {} coco_labels = {} coco_labels_inverse = {} for c in categories: coco_labels[len(classes)] = c['id'] coco_labels_inverse[c['id']] = len(classes) classes[c['name']] = len(classes) img_ids = data_source.getImgIds() for index, img_id in tqdm.tqdm(enumerate(img_ids), desc='change .json file to .txt file'): img_info = data_source.loadImgs(img_id)[0] file_name = img_info['file_name'].split('.')[0] height = img_info['height'] width = img_info['width'] save_path = save_base_path + file_name + '.txt' with open(save_path, mode='w') as fp: annotation_id = data_source.getAnnIds(img_id) boxes = np.zeros((0, 5)) if len(annotation_id) == 0: fp.write('') continue annotations = data_source.loadAnns(annotation_id) lines = '' for annotation in annotations: box = annotation['bbox'] # some annotations have basically no width / height, skip them if box[2] < 1 or box[3] < 1: continue #top_x,top_y,width,height---->cen_x,cen_y,width,height box[0] = round((box[0] + box[2] / 2) / width, 6) box[1] = round((box[1] + box[3] / 2) / height, 6) box[2] = round(box[2] / width, 6) box[3] = round(box[3] / height, 6) label = coco_labels_inverse[annotation['category_id']] lines = lines + str(label) for i in box: lines += ' ' + str(i) lines += '\n' fp.writelines(lines) print('finish') with open(json_file_path, encoding='utf-8') as f: data = json.load(f) #https://blog.csdn.net/fireflychh/article/details/83040205 annotations = data['annotations'] #选择这个词典，具体类别看上面的博客就可以了 data_source = COCO(annotation_file=json_file_path) #读取的api initialize COCO api for instance annotations for ant in annotations: id = ant['image_id'] img_info = data_source.loadImgs(id)[0] file_name = img_info['file_name'].split('.')[0] name = name1+file_name+'.jpg' cat = ant['category_id'] if cat >= 1 and cat <= 11: cat = cat - 1 name_box_id[name].append([ant['bbox'], cat]) """write to txt""" with open(output_file, 'w') as f: for key in name_box_id.keys(): f.write(key) f.write('\n')可以看出里面有两个生成地址，因为我整合了一下大佬们的转换代码，一次性生成上面说的两种txt文件。 这个是检索的txt 这个是目标标记的txt
部分参考链接：
voc定位数据xml转coco数据集格式json
COCO数据集训练格式转换成YOLO格式
