PermissionError: [WinError 5] 拒绝访问

[YChao99]

你好，我想知道为什么我训练途中会出错？ 使用 --resume 后效果很差，并且也会出现同样的错误

Epoch   gpu_mem      GIoU       obj       cls     total   targets  img_size
79/299     6.01G   0.02431   0.04288   0.01463   0.08182        35       608: 100%|██████████| 289/289 [02:33<00:00,  1.88it/s]
           Class      Images     Targets           P           R      [email protected]  [email protected]:.95:   0%|          | 0/97 [00:00<?, ?it/s]Traceback (most recent call last):

File "", line 1, in Class Images Targets P R [email protected] [email protected]:.95: 0%| | 0/97 [00:02<?, ?it/s] File "D:\Soft\Anaconda3\envs\yangchao\lib\multiprocessing\spawn.py", line 116, in spawn_main Traceback (most recent call last): File "D:/YC/PyTorch_YOLOv4-u5/train.py", line 479, in exitcode = _main(fd, parent_sentinel) File "D:\Soft\Anaconda3\envs\yangchao\lib\multiprocessing\spawn.py", line 126, in _main self = reduction.pickle.load(from_parent) EOFError: Ran out of input train(hyp, tb_writer, opt, device) File "D:/YC/PyTorch_YOLOv4-u5/train.py", line 349, in train results, maps, times = test.test(opt.data, File "D:\YC\PyTorch_YOLOv4-u5\test.py", line 79, in test for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)): File "D:\Soft\Anaconda3\envs\yangchao\lib\site-packages\tqdm\std.py", line 1166, in iter for obj in iterable: File "D:\Soft\Anaconda3\envs\yangchao\lib\site-packages\torch\utils\data\dataloader.py", line 352, in iter return self._get_iterator() File "D:\Soft\Anaconda3\envs\yangchao\lib\site-packages\torch\utils\data\dataloader.py", line 294, in _get_iterator return _MultiProcessingDataLoaderIter(self) File "D:\Soft\Anaconda3\envs\yangchao\lib\site-packages\torch\utils\data\dataloader.py", line 801, in init w.start() File "D:\Soft\Anaconda3\envs\yangchao\lib\multiprocessing\process.py", line 121, in start self._popen = self._Popen(self) File "D:\Soft\Anaconda3\envs\yangchao\lib\multiprocessing\context.py", line 224, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "D:\Soft\Anaconda3\envs\yangchao\lib\multiprocessing\context.py", line 327, in _Popen return Popen(process_obj) File "D:\Soft\Anaconda3\envs\yangchao\lib\multiprocessing\popen_spawn_win32.py", line 93, in init reduction.dump(process_obj, to_child) File "D:\Soft\Anaconda3\envs\yangchao\lib\multiprocessing\reduction.py", line 60, in dump ForkingPickler(file, protocol).dump(obj) File "D:\Soft\Anaconda3\envs\yangchao\lib\multiprocessing\synchronize.py", line 104, in getstate h = context.get_spawning_popen().duplicate_for_child(sl.handle) File "D:\Soft\Anaconda3\envs\yangchao\lib\multiprocessing\popen_spawn_win32.py", line 99, in duplicate_for_child return reduction.duplicate(handle, self.sentinel) File "D:\Soft\Anaconda3\envs\yangchao\lib\multiprocessing\reduction.py", line 79, in duplicate return _winapi.DuplicateHandle( PermissionError: [WinError 5] 拒绝访问。

Process finished with exit code 1

[yufanxin]

Set the num_work process to 0

[xxyClass]

What is the specific operation? thank you.

[xxyClass]

I'm really sorry, I can't find a place to modify the configuration.

[xxyClass]

I'm really sorry, I can't find a place to modify the "num_work" configuration

[betray0427]

我训练的时候发生这个问题 Traceback (most recent call last): File "F:\Code\Swin-Unet-main\train.py", line 99, in trainer[dataset_name](args, net, args.output_dir) File "F:\Code\Swin-Unet-main\trainer.py", line 53, in trainer_synapse for i_batch, sampled_batch in enumerate(trainloader): File "D:\Anaconda\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 359, in iter return self._get_iterator() File "D:\Anaconda\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 305, in _get_iterator return _MultiProcessingDataLoaderIter(self) File "D:\Anaconda\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 918, in init w.start() File "D:\Anaconda\envs\pytorch\lib\multiprocessing\process.py", line 112, in start self._popen = self._Popen(self) File "D:\Anaconda\envs\pytorch\lib\multiprocessing\context.py", line 223, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "D:\Anaconda\envs\pytorch\lib\multiprocessing\context.py", line 322, in _Popen return Popen(process_obj) File "D:\Anaconda\envs\pytorch\lib\multiprocessing\popen_spawn_win32.py", line 89, in init reduction.dump(process_obj, to_child) File "D:\Anaconda\envs\pytorch\lib\multiprocessing\reduction.py", line 60, in dump ForkingPickler(file, protocol).dump(obj) AttributeError: Can't pickle local object 'trainer_synapse..worker_init_fn' Traceback (most recent call last): File "", line 1, in File "D:\Anaconda\envs\pytorch\lib\multiprocessing\spawn.py", line 99, in spawn_main new_handle = reduction.steal_handle(parent_pid, pipe_handle) File "D:\Anaconda\envs\pytorch\lib\multiprocessing\reduction.py", line 87, in steal_handle _winapi.DUPLICATE_SAME_ACCESS | _winapi.DUPLICATE_CLOSE_SOURCE) PermissionError: [WinError 5] 拒绝访问。