JSON转TXT

import json
import os,glob



categories = [
        {
            "id": 12,
            "name": "OREO",
            "supercategory": "icbin"
        },
        {
            "id": 16,
            "name": "Paper Cup",
            "supercategory": "icbin"
        },
        {
            "id": 4,
            "name": "School Glue",
            "supercategory": "icbin"
        },
        {
            "id": 7,
            "name": "Straw Cups",
            "supercategory": "icbin"
        },
        {
            "id": 9,
            "name": "Highland",
            "supercategory": "icbin"
        },
        {
            "id": 10,
            "name": "Soueakair",
            "supercategory": "icbin"
        },
        {
            "id": 2,
            "name": "Cheez-it",
            "supercategory": "icbin"
        },
        {
            "id": 1,
            "name": "Copper Plus",
            "supercategory": "icbin"
        },
        {
            "id": 8,
            "name": "Stir Stick",
            "supercategory": "icbin"
        },
        {
            "id": 14,
            "name": "Stanley",
            "supercategory": "icbin"
        },
        {
            "id": 3,
            "name": "Crayola",
            "supercategory": "icbin"
        },
        {
            "id": 13,
            "name": "Mirado",
            "supercategory": "icbin"
        },
        {
            "id": 11,
            "name": "Munchkin",
            "supercategory": "icbin"
        },
        {
            "id": 6,
            "name": "Greenies",
            "supercategory": "icbin"
        },
        {
            "id": 5,
            "name": "White Board Cake",
            "supercategory": "icbin"
        },
        {
            "id": 15,
            "name": "Main Arm",
            "supercategory": "icbin"
        }
    ]

def convert(size, box):
    dw = 1. / (size[0])
    dh = 1. / (size[1])
    x = box[0] + box[2] / 2.0
    y = box[1] + box[3] / 2.0
    w = box[2]
    h = box[3]
 
    x = x * dw
    w = w * dw
    y = y * dh
    h = h * dh
    return (x, y, w, h)
 
def to_yolo(data_path):
    json_path=data_path+'/scene_gt_coco.json' 
    save_path = data_path+ '/labels/'

    json_file =   json_path # COCO Object Instance 类型的标注
    ana_txt_save_path = save_path  # 保存的路径
 
    data = json.load(open(json_file, 'r'))
    if not os.path.exists(ana_txt_save_path):
        os.makedirs(ana_txt_save_path)
    id_map = {} # coco数据集的id不连续！重新映射一下再输出！
    print(data['categories'])
    # # categories = sorted(data['categories'], key=lambda x: x['id'])

    for i, category in enumerate(categories): 
        # id_map[category['id']] = int(category['id'])
        id_map[category['id']] = i
    # 通过事先建表来降低时间复杂度
    max_id = 0
    for img in data['images']:
        max_id = max(max_id, img['id'])
    # 注意这里不能写作 [[]]*(max_id+1)，否则列表内的空列表共享地址
    img_ann_dict = [[] for i in range(max_id+1)] 
    for i, ann in enumerate(data['annotations']):
        img_ann_dict[ann['image_id']].append(i)
 
    for img in data['images']:
        filename = img["file_name"]
        img_width = img["width"]
        img_height = img["height"]
        img_id = img["id"]
        head, tail = os.path.splitext(filename)
        ana_txt_name = head.split('/')[-1] + ".txt"  # 对应的txt名字，与jpg一致
        f_txt = open(os.path.join(ana_txt_save_path, ana_txt_name), 'w')
        '''for ann in data['annotations']:
            if ann['image_id'] == img_id:
                box = convert((img_width, img_height), ann["bbox"])
                f_txt.write("%s %s %s %s %s\n" % (id_map[ann["category_id"]], box[0], box[1], box[2], box[3]))'''
        # 这里可以直接查表而无需重复遍历
        for ann_id in img_ann_dict[img_id]:
            ann = data['annotations'][ann_id]
            box = convert((img_width, img_height), ann["bbox"])
            
            f_txt.write("%s %s %s %s %s\n" % (id_map[ann["category_id"]], box[0], box[1], box[2], box[3]))
        f_txt.close()
    print(f'==> coco to yolo images:{len(data["images"])}, save path: {save_path}')

    
def train_val_test(data_path):
    sets = ['train','val','test']#生成txt的文件名称

    image_ids = glob.glob(os.path.join(data_path, 'images', '*.jpg'))

    train_ratio = 0.7  # 训练集比例
    val_ratio = 0.2  # 验证集比例
    test_ratio = 0.1  # 测试集比例

    train_size = int(len(image_ids) * train_ratio)
    val_size = int(len(image_ids) * val_ratio)
    test_size = len(image_ids) - train_size - val_size

    data  = [image_ids[:train_size], image_ids[train_size:train_size + val_size], image_ids[train_size + val_size:]]
    
    

    for i, image_set in enumerate(sets):
    
        image_ids = data[i]
        list_file = open(data_path+'/%s.txt' % (image_set), 'w')
        for image_id in image_ids:
            image_id = image_id.replace('/rgb','/images')
            list_file.write(image_id + "\n")
            # convert_annotation(image_id)
        # 关闭文件
        list_file.close()
    
    print(f'==> train image: {train_size}')
    print(f'==> valid image: {val_size}')
    print(f'==> test  image: {test_size}')

if __name__ == '__main__':
    data_path = 'H:/Dataset/COCO/train_pbr/000002'
    to_yolo(data_path)
    train_val_test(data_path)
    # print([cat['name'] for cat in categories])

重命名

以00000061*开头

txt文件中类别信息的转换

加79（从0开始，80类的COCO）

import codecs
import os

path = 'H:/Dataset/COCO/train_pbr/000002/labelNew/'  # 标签文件train路径
m = os.listdir(path)
# 读取路径下的txt文件
for n in range(0, len(m)):
    t = codecs.open('H:/Dataset/COCO/train_pbr/000002/labelNew/' + m[n], mode='r', encoding='utf-8')
    line = t.readline()  # 以行的形式进行读取文件
    list1 = []
    while line:
        a = line.split()
        list1.append(a)
        line = t.readline()
    t.close()

    lt = open('H:/Dataset/COCO/train_pbr/000002/labelNew/' + m[n], "w")
    for num in range(0, len(list1)):
        list1[num][0] = str(int(list1[num][0])+79)  # 第一列为0时，将0改为1
        lt.writelines(' '.join(list1[num]) + '\n')  # 每个元素以空格间隔，一行元素写完并换行
    lt.close()
    print(m[n] + " 修改完成")