MS coco中image_caption的数据格式详解

import json
if __name__==‘__main__‘:
    base_path = r‘/data/antonio/images_data/images/annotations/captions_train2014.json‘

    image_caption={}
    with open(base_path,‘r‘) as f:
        dataset=json.load(f)
    image_caption[‘annotations‘] = []
    for data in dataset[‘annotations‘]:
        image_caption[‘annotations‘].append({})
        for key in data:
            image_caption[‘annotations‘][0][key]=data[key]
        break

    image_caption[‘images‘] = []
    for data in dataset[‘images‘]:
        image_caption[‘images‘].append({})
        for key in data:
            image_caption[‘images‘][0][key]=data[key]
        break

    image_caption[‘info‘] = {}
    for key in dataset[‘info‘]:     #dict
        image_caption[‘info‘][key]=dataset[‘info‘][key]

    image_caption[‘licenses‘] = []
    for data in dataset[‘licenses‘]: #2014 have eight list
        image_caption[‘licenses‘].append({})
        for key in data:
            image_caption[‘licenses‘][0][key]=data[key]
        break
    print(image_caption)

{
    ‘annotations‘: [{
            ‘image_id‘: 318556,#唯一的图片ID，此ID同时是图像文件名的序列号，对应的文件名：COCO_train2014_000000318556.jpg
            ‘id‘: 48, # 唯一的对象ID
            ‘caption‘: ‘A very clean and well decorated empty bathroom‘
        }
        ...
        ...
    ],
    ‘images‘: [{
            ‘license‘: 5,
            ‘date_captured‘: ‘2013-11-14 16:28:13‘,
            ‘flickr_url‘: ‘http://farm4.staticflickr.com/3153/2970773875_164f0c0b83_z.jpg‘,
            ‘coco_url‘: ‘http://images.cocodataset.org/train2014/COCO_train2014_000000057870.jpg‘,
            ‘id‘: 57870 #此id对应的是‘annotations‘中的image_id
            ‘width‘: 640,
            ‘file_name‘: ‘COCO_train2014_000000057870.jpg‘,
            ‘height‘: 480
        }
        ...
        ...
    ],
    ‘licenses‘: [{
            ‘id‘: 1,
            ‘url‘: ‘http://creativecommons.org/licenses/by-nc-sa/2.0/‘,
            ‘name‘: ‘Attribution-NonCommercial-ShareAlike License‘
        }
        ...
        ...
    ],
    ‘info‘: {
        ‘description‘: ‘COCO 2014 Dataset‘,
        ‘year‘: 2014,
        ‘date_created‘: ‘2017/09/01‘,
        ‘contributor‘: ‘COCO Consortium‘,
        ‘url‘: ‘http://cocodataset.org‘,
        ‘version‘: ‘1.0‘
    }
}

from pycocotools.coco import COCO
import torch.utils.data as data
import json
class DataLoader(data.Dataset):
    def __init__(self, json,  transform=None):
        self.coco = COCO(json)
        self.ids = list(self.coco.anns.keys())
        self.transform = transform



if __name__==‘__main__‘:
    base_path = r‘/data/antonio/images_data/images/annotations/captions_train2014.json‘
    dataloader = DataLoader(base_path)