COCO数据集中图像的caption读取到txt文件

annotations_trainval2017.zip

import os
import shutil
import json

captions_path = r"G:\SketchDiffusion\Sketchycoco\Dataset\annotations\captions_train2017.json"
# 读取json文件
with open(captions_path, 'r') as f1:
    dictortary = json.load(f1)

# 得到images和annotations信息
images_value = dictortary.get("images")
annotations_value = dictortary.get("annotations")

# 使用images下的图像名的id创建txt文件
list=[]
id2name = dict()
for i in images_value:
    list.append(i.get("id"))
    id2name[i.get("id")] = i.get("file_name")

# 将id对应图片的caption写入txt文件中
txt_path = r"G:\SketchDiffusion\Sketchycoco\Dataset\caption"
for i in list:
    for j in annotations_value:
        if j.get("image_id") == i:
            imgname = id2name.get(i).split(".")[0]
            file_name = txt_path + "\\coco_" + imgname + '.txt'
            if not os.path.exists(file_name):
                open(file_name, 'w')
            with open(file_name, 'a') as f2:
                f2.write(j.get("caption")+"\n")

print('over！')

结果：