ValueError: too many dimensions ‘str’

DETR读取图像时，提示：

loading annotations into memory...
Done (t=0.08s)
creating index...
index created!
loading annotations into memory...
Done (t=0.06s)
creating index...
index created!
Start training
Traceback (most recent call last):
  File "/home/ubuntu/bigdisk/part4/DETR/main.py", line 443, in <module>
    main(args)
  File "/home/ubuntu/bigdisk/part4/DETR/main.py", line 369, in main
    train_stats = train_one_epoch(
  File "/home/ubuntu/bigdisk/part4/DETR/engine.py", line 42, in train_one_epoch
    for samples, targets in metric_logger.log_every(data_loader, print_freq, header, logger=logger):
  File "/home/ubuntu/bigdisk/part4/DETR/util/misc.py", line 238, in log_every
    for obj in iterable:
  File "/home/ubuntu/anaconda3/envs/DETR/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 521, in __next__
    data = self._next_data()
  File "/home/ubuntu/anaconda3/envs/DETR/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1203, in _next_data
    return self._process_data(data)
  File "/home/ubuntu/anaconda3/envs/DETR/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1229, in _process_data
    data.reraise()
  File "/home/ubuntu/anaconda3/envs/DETR/lib/python3.8/site-packages/torch/_utils.py", line 425, in reraise
    raise self.exc_type(msg)
ValueError: Caught ValueError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/home/ubuntu/anaconda3/envs/DETR/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
    data = fetcher.fetch(index)
  File "/home/ubuntu/anaconda3/envs/DETR/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/ubuntu/anaconda3/envs/DETR/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 44, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/ubuntu/bigdisk/part4/DETR/datasets/coco.py", line 51, in __getitem__
    img, target = self.prepare(img, target)
  File "/home/ubuntu/bigdisk/part4/DETR/datasets/coco.py", line 84, in __call__
    image_id = torch.tensor([image_id])
ValueError: too many dimensions 'str'

这个问题的发生有个背景，从VOC转COCO的时候，出现image_id是非数字的问题，我采用脚本批量将其转为数字之后，再次读取image_id，此时会认为其类型为str。所以，只需要在读取的时候强制int即可，下面是原始代码：

    def __call__(self, image, target):
        w, h = image.size

        image_id = target["image_id"]
        image_id = torch.tensor([image_id])

        anno = target["annotations"]

下面是修改后的：

    def __call__(self, image, target):
        w, h = image.size

        image_id = target["image_id"]
        image_id = torch.tensor([int(image_id)])

        anno = target["annotations"]

当然，这个跟代码有关，不过原理是一样的。