COCO数据集的种类

COCO数据集共80类，12个大类。其代码示例如下。
以下代码参考cocoapi

import time as time
import json
from collections import defaultdict

def _isArrayLike(obj):
    return hasattr(obj, '__iter__') and hasattr(obj, '__len__')
class COCO:
    def __init__(self, annotation_file=None):
        """
        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 dataset
        self.dataset,self.anns,self.cats,self.imgs = dict(),dict(),dict(),dict()
        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 = dataset
            self.createIndex()

    def createIndex(self):
        # create index
        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']] = ann

        if 'images' in self.dataset:
            for img in self.dataset['images']:
                imgs[img['id']] = img

        if 'categories' in self.dataset:
            for cat in self.dataset['categories']:
                cats[cat['id']] = cat

        if '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 members
        self.anns = anns
        self.imgToAnns = imgToAnns
        self.catToImgs = catToImgs
        self.imgs = imgs
        self.cats = cats

    def getCatIds(self, catNms=[], supNms=[], catIds=[]):
        """
        filtering parameters. default skips that filter.
        :param catNms (str array)  : get cats for given cat names
        :param supNms (str array)  : get cats for given supercategory names
        :param catIds (int array)  : get cats for given cat ids
        :return: ids (int array)   : integer array of cat ids
        """
        catNms = catNms if _isArrayLike(catNms) else [catNms]
        supNms = supNms if _isArrayLike(supNms) else [supNms]
        catIds = catIds if _isArrayLike(catIds) else [catIds]

        if len(catNms) == len(supNms) == len(catIds) == 0:
            print('进入if')
            cats = self.dataset['categories']
        else:
            print('进入else')
            cats = self.dataset['categories']
            cats = cats if len(catNms) == 0 else [cat for cat in cats if cat['name'] in catNms]
            cats = cats if len(supNms) == 0 else [cat for cat in cats if cat['supercategory'] in supNms]
            cats = cats if len(catIds) == 0 else [cat for cat in cats if cat['id'] in catIds]
        print(self.dataset.keys())
        print(cats)
        ids = [cat['id'] for cat in cats]
        return ids
    def loadCats(self, ids=[]):
        """
        Load cats with the specified ids.
        :param ids (int array)       : integer ids specifying cats
        :return: cats (object array) : loaded cat objects
        """
        if _isArrayLike(ids):
            return [self.cats[id] for id in ids]
        elif type(ids) == int:
            return [self.cats[ids]]

dataDir = '../..'
dataType = 'val2017'
annDir = '{}/annotations'.format(dataDir)
annFile = '{}/instances_{}.json'.format(annDir, dataType)
coco = COCO(annFile)
ids = coco.getCatIds()
cats = coco.loadCats(ids)
print(cats)
print(len(cats))

nms=[cat['name'] for cat in cats]
print('COCO categories: \n{}\n'.format(' '.join(nms)))

nms = set([cat['supercategory'] for cat in cats])
print(len(nms))
print('COCO supercategories: \n{}'.format(' '.join(nms)))