Cannot read the dataset while training

[KowalskiWang]

I tried to train with my own dataset that collects from Udacity simulator, but it outputs:

device is: cuda Traceback (most recent call last): File "self_driving_car.py", line 169, in for local_batch, (centers, lefts, rights) in enumerate(training_generator): File "C:\Users\kayse.conda\envs\csci8980\lib\site-packages\torch\utils\data\dataloader.py", line 352, in iter return self._get_iterator() File "C:\Users\kayse.conda\envs\csci8980\lib\site-packages\torch\utils\data\dataloader.py", line 294, in _get_iterator return _MultiProcessingDataLoaderIter(self) File "C:\Users\kayse.conda\envs\csci8980\lib\site-packages\torch\utils\data\dataloader.py", line 801, in init w.start() File "C:\Users\kayse.conda\envs\csci8980\lib\multiprocessing\process.py", line 105, in start self._popen = self._Popen(self) File "C:\Users\kayse.conda\envs\csci8980\lib\multiprocessing\context.py", line 223, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "C:\Users\kayse.conda\envs\csci8980\lib\multiprocessing\context.py", line 322, in _Popen return Popen(process_obj) File "C:\Users\kayse.conda\envs\csci8980\lib\multiprocessing\popen_spawn_win32.py", line 65, in init reduction.dump(process_obj, to_child) File "C:\Users\kayse.conda\envs\csci8980\lib\multiprocessing\reduction.py", line 60, in dump ForkingPickler(file, protocol).dump(obj) _pickle.PicklingError: Can't pickle <function at 0x0000017C40295EA0>: attribute lookup on main failed (csci8980) D:>Traceback (most recent call last): File "", line 1, in File "C:\Users\kayse.conda\envs\csci8980\lib\multiprocessing\spawn.py", line 105, in spawn_main exitcode = _main(fd) File "C:\Users\kayse.conda\envs\csci8980\lib\multiprocessing\spawn.py", line 115, in _main self = reduction.pickle.load(from_parent) EOFError: Ran out of input