Error when using a Custom dataset with weekly frequency

[elenamanth]

Hello! I have successfully run the iTransformer in a custom dataset with hourly, daily and monthly frequency with no problem. When trying to do the same for a weekly frequency i get the following error:

TypeError: Caught TypeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "c:\Users\Anaconda3\envs\timeseries\lib\site-packages\torch\utils\data_utils\worker.py", line 308, in _worker_loop
data = fetcher.fetch(index)
File "c:\Users\Anaconda3\envs\timeseries\lib\site-packages\torch\utils\data_utils\fetch.py", line 54, in fetch
return self.collate_fn(data)
File "c:\Users\Anaconda3\envs\timeseries\lib\site-packages\torch\utils\data_utils\collate.py", line 264, in default_collate
return collate(batch, collate_fn_map=default_collate_fn_map)
File "c:\Users\Anaconda3\envs\timeseries\lib\site-packages\torch\utils\data_utils\collate.py", line 142, in collate
return [collate(samples, collate_fn_map=collate_fn_map) for samples in transposed] # Backwards compatibility.
File "c:\Users\Anaconda3\envs\timeseries\lib\site-packages\torch\utils\data_utils\collate.py", line 142, in
return [collate(samples, collate_fn_map=collate_fn_map) for samples in transposed] # Backwards compatibility.
File "c:\Users\Anaconda3\envs\timeseries\lib\site-packages\torch\utils\data_utils\collate.py", line 119, in collate
return collate_fn_map[elem_type](batch, collate_fn_map=collate_fn_map)
File "c:\Users\Anaconda3\envs\timeseries\lib\site-packages\torch\utils\data_utils\collate.py", line 169, in collate_numpy_array_fn
raise TypeError(default_collate_err_msg_format.format(elem.dtype))
TypeError: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found object

[WenWeiTHU]

It seems to be a problem with the inconsistent number of variables returned by get_item. Since this issue is less relative to the paper, the issue will be closed.