ethanhe42 / channel-pruning

Channel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)
https://arxiv.org/abs/1707.06168
MIT License
1.08k stars 310 forks source link

AttributeError: Can't pickle local object 'Worker.do.<locals>.job' #102

Closed GaoDoudou closed 6 years ago

GaoDoudou commented 6 years ago

My system is win10 and python 3.5. When running the code, there are some error message and I have no idea with it. Can you tell me why, thank you: no lighting pack File "train.py", line 181, in c3() File "train.py", line 89, in c3 outputs = worker.do(step0, pt=pt, model=model) File "channel-pruning-master\lib\worker.py", line 34, in do p.start() File "python_root\lib\multiprocessing\process.py", line 105, in start self._popen = self._Popen(self) File "python_root\lib\multiprocessing\context.py", line 212, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "python_root\lib\multiprocessing\context.py", line 313, in _Popen return Popen(process_obj) File "python_root\lib\multiprocessing\popen_spawn_win32.py", line 66, in init reduction.dump(process_obj, to_child) File "python_root\lib\multiprocessing\reduction.py", line 59, in dump ForkingPickler(file, protocol).dump(obj) AttributeError: Can't pickle local object 'Worker.do..job' File "python_root\lib\multiprocessing\spawn.py", line 116, in _main self = pickle.load(from_parent) EOFError: Ran out of input

ethanhe42 commented 6 years ago

Please use ubuntu. The code is not tested on Windows.