Pytorch Tutorial 中出现“Results do not correspond to current coco set”的解决办法

1、出错代码位置：

def loadRes(self, resFile):
    """
    Load result file and return a result api object.
    :param   resFile (str)     : file name of result file
    :return: res (obj)         : result api object
    """
    res = COCO()
    res.dataset['images'] = [img for img in self.dataset['images']]

    # print('Loading and preparing results...')
    # tic = time.time()
    if isinstance(resFile, torch._six.string_classes):
        anns = json.load(open(resFile))
    elif type(resFile) == np.ndarray:
        anns = self.loadNumpyAnnotations(resFile)
    else:
        anns = resFile
    assert type(anns) == list, 'results in not an array of objects'
    annsImgIds = [ann['image_id'] for ann in anns]
    assert set(annsImgIds) == (set(annsImgIds) & set(self.getImgIds())), \
        'Results do not correspond to current coco set'

2、问题分析：

查看set(annsImgIds)和set(self.getImgIds())的结果发现，annsImgIds的数据类型为tensor，set(self.getImgIds())为数值，
导致set(annsImgIds) & set(self.getImgIds()) 返回结果为空，assert未通过

3、解决方案（非唯一）：

将annsImgIds转换成数值即可，修改后的代码如下：

def loadRes(self, resFile):
    """
    Load result file and return a result api object.
    :param   resFile (str)     : file name of result file
    :return: res (obj)         : result api object
    """
    res = COCO()
    res.dataset['images'] = [img for img in self.dataset['images']]

    # print('Loading and preparing results...')
    # tic = time.time()
    if isinstance(resFile, torch._six.string_classes):
        anns = json.load(open(resFile))
    elif type(resFile) == np.ndarray:
        anns = self.loadNumpyAnnotations(resFile)
    else:
        anns = resFile
    assert type(anns) == list, 'results in not an array of objects'

	# 修改部分
	try:
    	annsImgIds = [ann['image_id'].item() for ann in anns]
	except:
		annsImgIds = [ann['image_id'] for ann in anns]

    assert set(annsImgIds) == (set(annsImgIds) & set(self.getImgIds())), \
        'Results do not correspond to current coco set'