缩小COCO数据集

在运行YOLOS模型的过程中，需要使用到COCO2017这个数据集，但从实验运行来看，其所需时间无疑是相当漫长，预计可能需要近几十天才能完成，因此便考虑缩小COCO数据集大小，即尽可能在遵循其分布的情况下，将数据集中的图片数量缩小。博主这里将数据集缩小了16倍。

下面是缩小代码：

# coding:utf8
import json
import time
import shutil
import os
from collections import defaultdict
import json
from pathlib import Pathclass COCO:def __init__(self, annotation_file=None, origin_img_dir=""):"""Constructor of Microsoft COCO helper class for reading and visualizing annotations.:param annotation_file (str): location of annotation file:param image_folder (str): location to the folder that hosts images.:return:"""# load datasetself.origin_dir = origin_img_dirself.dataset, self.anns, self.cats, self.imgs = dict(), dict(), dict(), dict()  # imgToAnns　一个图片对应多个注解(mask) 一个类别对应多个图片self.imgToAnns, self.catToImgs = defaultdict(list), defaultdict(list)if not annotation_file == None:print('loading annotations into memory...')tic = time.time()dataset = json.load(open(annotation_file, 'r'))assert type(dataset) == dict, 'annotation file format {} not supported'.format(type(dataset))print('Done (t={:0.2f}s)'.format(time.time() - tic))self.dataset = datasetself.createIndex()def createIndex(self):# create index　　  给图片->注解,类别->图片建立索引print('creating index...')anns, cats, imgs = {}, {}, {}imgToAnns, catToImgs = defaultdict(list), defaultdict(list)if 'annotations' in self.dataset:for ann in self.dataset['annotations']:imgToAnns[ann['image_id']].append(ann)anns[ann['id']] = annif 'images' in self.dataset:for img in self.dataset['images']:imgs[img['id']] = imgif 'categories' in self.dataset:for cat in self.dataset['categories']:cats[cat['id']] = catif 'annotations' in self.dataset and 'categories' in self.dataset:for ann in self.dataset['annotations']:catToImgs[ann['category_id']].append(ann['image_id'])print('index created!')# create class membersself.anns = annsself.imgToAnns = imgToAnnsself.catToImgs = catToImgsself.imgs = imgsself.cats = catsdef build(self, tarDir=None, tarFile='./new.json', N=1000):load_json = {'images': [], 'annotations': [], 'categories': [], 'type': 'instances', "info": {"description": "This is stable 1.0 version of the 2014 MS COCO dataset.", "url": "http:\/\/mscoco.org", "version": "1.0", "year": 2014, "contributor": "Microsoft COCO group", "date_created": "2015-01-27 09:11:52.357475"}, "licenses": [{"url": "http:\/\/creativecommons.org\/licenses\/by-nc-sa\/2.0\/", "id": 1, "name": "Attribution-NonCommercial-ShareAlike License"}, {"url": "http:\/\/creativecommons.org\/licenses\/by-nc\/2.0\/", "id": 2, "name": "Attribution-NonCommercial License"}, {"url": "http:\/\/creativecommons.org\/licenses\/by-nc-nd\/2.0\/","id": 3, "name": "Attribution-NonCommercial-NoDerivs License"}, {"url": "http:\/\/creativecommons.org\/licenses\/by\/2.0\/", "id": 4, "name": "Attribution License"}, {"url": "http:\/\/creativecommons.org\/licenses\/by-sa\/2.0\/", "id": 5, "name": "Attribution-ShareAlike License"}, {"url": "http:\/\/creativecommons.org\/licenses\/by-nd\/2.0\/", "id": 6, "name": "Attribution-NoDerivs License"}, {"url": "http:\/\/flickr.com\/commons\/usage\/", "id": 7, "name": "No known copyright restrictions"}, {"url": "http:\/\/www.usa.gov\/copyright.shtml", "id": 8, "name": "United States Government Work"}]}if not Path(tarDir).exists():Path(tarDir).mkdir()for i in self.imgs:if(N == 0):breaktic = time.time()img = self.imgs[i]load_json['images'].append(img)fname = os.path.join(tarDir, img['file_name'])anns = self.imgToAnns[img['id']]for ann in anns:load_json['annotations'].append(ann)if not os.path.exists(fname):shutil.copy(self.origin_dir+'/'+img['file_name'], tarDir)print('copy {}/{} images (t={:0.1f}s)'.format(i, N, time.time() - tic))N -= 1for i in self.cats:load_json['categories'].append(self.cats[i])with open(tarFile, 'w+') as f:json.dump(load_json, f, indent=4)coco = COCO('/data/programs/yolos/coco/annotations/instances_train2017.json',origin_img_dir='/data/programs/yolos/coco/train2017')               # 完整的coco数据集的图片和标注的路径
coco.build('/data/datasets/mincoco/train2017', '/data/datasets/mincoco/instances_train2017.json', 7392)  # 保存图片路径coco = COCO('/data/programs/yolos/coco/annotations/instances_val2017.json',origin_img_dir='/data/programs/yolos/coco/val2017')                 # 完整的coco数据集的图片和标注的路径
coco.build('/data/datasets/mincoco/val2017', '/data/datasets/mincoco/instances_val2017.json', 312)       # 保存图片路径# 在2017年数据集中,训练集118287张,验证5000张,测试集40670张.
# 118287/16 = 7392 5000/16 = 312