Pytorch-yolov3: RuntimeError: There were no tensor arguments to this function (e.g., you passed an empty list of Tensors), but no fallback function is registered for schema aten::_cat. This usually means that this function requires a non-empty list of Tensors. Available functions are [CUDATensorId, CPUTensorId, VariableTensorId]

[xiaoyuzhu666]

Detecting objects: 0%| | 0/619 [00:00 File "E:/PyTorch-YOLOv3-master/test.py", line 98, in
batch_size=8,
File "E:/PyTorch-YOLOv3-master/test.py", line 36, in evaluate
for batch_i, (_, imgs, targets) in enumerate(tqdm.tqdm(dataloader, desc="Detecting objects")):
File "D:Anaconda\envs\PyTorch-YOLOv3-master\lib\site-packages\tqdm\std.py", line 1108, in __iter__
for obj in iterable:
File "D:Anaconda\envs\PyTorch-YOLOv3-master\lib\site-packages\torch\utils\data\dataloader.py", line 345, in __next__
data = self._next_data()
File "D:Anaconda\envs\PyTorch-YOLOv3-master\lib\site-packages\torch\utils\data\dataloader.py", line 856, in _next_data
return self._process_data(data)
File "D:Anaconda\envs\PyTorch-YOLOv3-master\lib\site-packages\torch\utils\data\dataloader.py", line 881, in _process_data
data.reraise()
File "D:Anaconda\envs\PyTorch-YOLOv3-master\lib\site-packages\torch_utils.py", line 394, in reraise
raise self.exc_type(msg)
RuntimeError: Caught RuntimeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "D:Anaconda\envs\PyTorch-YOLOv3-master\lib\site-packages\torch\utils\data_utils\worker.py", line 178, in _worker_loop
data = fetcher.fetch(index)
File "D:Anaconda\envs\PyTorch-YOLOv3-master\lib\site-packages\torch\utils\data_utils\fetch.py", line 47, in fetch
return self.collate_fn(data)
File "E:\PyTorch-YOLOv3-master\utils\datasets.py", line 141, in collate_fn
targets = torch.cat(targets, 0)

RuntimeError: There were no tensor arguments to this function (e.g., you passed an empty list of Tensors), but no fallback function is registered for schema aten::_cat. This usually means that this function requires a non-empty list of Tensors. Available functions are [CUDATensorId, CPUTensorId, VariableTensorId]

[JamMochi]

Hi, I ran into the same problem. Did you ever solve the issue?

[xiaoyuzhu666]

Hi, I ran into the same problem. Did you ever solve the issue?

Yes！
I edited a bit the code in datasets.py as below."JPEGImages" is the name of image file in VOC.
self.label_files = [
path.replace("JPEGImages", "labels").replace(".png", ".txt").replace(".jpg", ".txt")
for path in self.img_files
]

[JockerLin]

I slove this problem by increase the batch_size from 1 to 2, you can increase more if your gpu memory allow.

[SCS2017]

I ran into the same problem. I solve it by modifying the path of validation dataset.

[prh-t]

I slove this problem by increase the batch_size from 1 to 2, you can increase more if your gpu memory allow.

quite frustrating... I think I'm stuck with batch_size == 1, anything other than this gives CUDA out of mem error...

[prh-t]

I ran into the same problem. I solve it by modifying the path of validation dataset.

could you elaborate please?

[SCS2017]

I ran into the same problem. I solve it by modifying the path of validation dataset.

could you elaborate please?
I think it may be that the model does not receive data, so I re-modified the path.

[jinlintansjtu]

the same problem, oh my god

[ananiask8]

Apparently both, the images directory, and the labels directory, need to be located under the data directory.

[brianchap]

This link may be useful:

https://github.com/ninesinc/detectron2/commit/1eef1fa6d0cb00eb5ba5a9a28e0732f12bbb2879

[Cecilia-Ling]

I ran into the same problem. I solve it by modifying the path of validation dataset.

could you elaborate please?
I think it may be that the model does not receive data, so I re-modified the path.

请问能详细说一下是怎么修改的吗？

[Cecilia-Ling]

如果是直接跑yolov3代码，并不是自己修改了训练集之类的应该是不会出这个错的。如果出错，则是路径的问题，我修改 batch_size和作者提供的解决方案都没能解决。我是由于labels文件夹里还有一个labels子文件夹，所以找不到训练集和测试集label的路径了，只留下一个labels文件夹就行了。

[Cecilia-Ling]

It can be solved by modifing your data path, which should be, such as: ~\PyTorch-YOLOv3\data\coco\images\train2014； ~\PyTorch-YOLOv3\data\coco\labels\val2014。