anyuexuan
commented
1 year ago I believe you ran it on Windows. For now, Pytorch's support for multi-processing on Windows is very patchy. You can try it on Linux or MacOS.
Open Vanguitar opened 1 year ago
anyuexuan
commented
1 year ago I believe you ran it on Windows. For now, Pytorch's support for multi-processing on Windows is very patchy. You can try it on Linux or MacOS.
There is a problem:
pre_train()
File "./CSS-main/run_css.py", line 56, in pre_train
model.pre_train_loop(pre_epoch, base_loader, optimizer) # model are called by reference, no need to return
File ".\CSS-main\methods\CSS.py", line 81, in pre_trainloop
for i, (x, ) in enumerate(train_loader):
File "D:\anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 355, in iter
return self._get_iterator()
File "D:\anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 301, in _get_iterator
return _MultiProcessingDataLoaderIter(self)
File "D:\anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 914, in init
w.start()
File "D:\anaconda3\envs\pytorch\lib\multiprocessing\process.py", line 112, in start
self._popen = self._Popen(self)
File "D:\anaconda3\envs\pytorch\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "D:\anaconda3\envs\pytorch\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "D:\anaconda3\envs\pytorch\lib\multiprocessing\popen_spawn_win32.py", line 89, in init
reduction.dump(process_obj, to_child)
File "D:\anaconda3\envs\pytorch\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
_pickle.PicklingError: Can't pickle <function at 0x000002B97ABE4168>: attribute lookup on data.dataset failed
" Start pre-training! Traceback (most recent call last): File "./CSS-main/run_css.py", line 174, in
Process finished with exit code 1 " my torch is 1.8.1, could you help me to check the issue?