Github下載的Pytorch0.4.1的代碼，linux運行沒問題，轉到windows出現錯誤！
File “D:\Anaconda3.7\lib\multiprocessing\process.py”, line 112, in start
self._popen = self._Popen(self)
File “D:\Anaconda3.7\lib\multiprocessing\context.py”, line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File “D:\Anaconda3.7\lib\multiprocessing\context.py”, line 322, in _Popen
return Popen(process_obj)
File “D:\Anaconda3.7\lib\multiprocessing\popen_spawn_win32.py”, line 89, in init
reduction.dump(process_obj, to_child)
File “D:\Anaconda3.7\lib\multiprocessing\reduction.py”, line 60, in dump
ForkingPickler(file, protocol).dump(obj)
TypeError: can’t pickle Environment objects
出現問題原因：
多線程導致的
data_loader = data.DataLoader(dataset, batch_size, num_workers=args.num_workers,shuffle=True, collate_fn=detection_collate, pin_memory=True)
解決方法：
修改num_workers=0，即可解決。
num_workers (int, optional):
這個參數決定了有幾個進程來處理data loading。0意味着所有的數據都會被load進主進程。（默認爲0）