Dataloader throws random error

File “C:\Users\joelf_000\anaconda3\envs\hdr_env\lib\site-packages\tqdm\”, line 1185, in iter
for obj in iterable:
File “C:\Users\joelf_000\anaconda3\envs\hdr_env\lib\site-packages\torch\utils\data\”, line 521, in next
data = self._next_data()
File “C:\Users\joelf_000\anaconda3\envs\hdr_env\lib\site-packages\torch\utils\data\”, line 1183, in _next_data
return self._process_data(data)
File “C:\Users\joelf_000\anaconda3\envs\hdr_env\lib\site-packages\torch\utils\data\”, line 1229, in _process_data
File “C:\Users\joelf_000\anaconda3\envs\hdr_env\lib\site-packages\”, line 425, in reraise
raise self.exc_type(msg)
TypeError: init() missing 1 required positional argument: ‘dtype’

My dataloader is randomly throwing this error while training. I have no idea why. Im running kinda low on ram but it shouldnt be the problem since the error appears randomly (sometimes during the first epoch, other times after 10+ epochs). Any help would be appreciated.