CPU only pytorch is crashing with error AssertionError: Torch not compiled with CUDA enabled
CPU only pytorch is crashing with error AssertionError: Torch not compiled with CUDA enabled
我正在尝试 运行 来自 this repository 的代码，我需要使用 Pytorch 1.4.0。我已经使用 pip install torch==1.4.0+cpu torchvision==0.5.0+cpu -f https://download.pytorch.org/whl/torch_stable.html.
安装了 CPU 唯一版本的 pytorch
我通过 py -m train_Kfold_CV --device 0 --fold_id 10 --np_data_dir "C:\Users\username\OneDrive\Desktop\emadeldeen\AttnSleep\prepare_datasets\edf_20_npz" 运行 程序，但出现此错误：
File "C:\Users\username\AppData\Local\Programs\Python\Python37\lib\runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "C:\Users\username\AppData\Local\Programs\Python\Python37\lib\runpy.py", line 85, in _run_code
exec(code, run_globals)
File "C:\Users\username\OneDrive\Desktop\emadeldeen\AttnSleep\train_Kfold_CV.py", line 94, in <module>
main(config, fold_id)
File "C:\Users\username\OneDrive\Desktop\emadeldeen\AttnSleep\train_Kfold_CV.py", line 65, in main
trainer.train()
File "C:\Users\username\OneDrive\Desktop\emadeldeen\AttnSleep\base\base_trainer.py", line 66, in train
result, epoch_outs, epoch_trgs = self._train_epoch(epoch, self.epochs)
File "C:\Users\username\OneDrive\Desktop\emadeldeen\AttnSleep\trainer\trainer.py", line 49, in _train_epoch
loss = self.criterion(output, target, self.class_weights)
File "C:\Users\username\OneDrive\Desktop\emadeldeen\AttnSleep\model\loss.py", line 6, in weighted_CrossEntropyLoss
cr = nn.CrossEntropyLoss(weight=torch.tensor(classes_weights).cuda())
File "C:\Users\username\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\cuda\__init__.py", line 196, in _lazy_init
_check_driver()
File "C:\Users\username\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\cuda\__init__.py", line 94, in _check_driver
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
我已将配置中的 GPU 数量更改为 0，并尝试在程序开头添加 device = torch.device('cpu')，但它没有任何作用。我该如何解决这个错误？如果有帮助，我将 windows 10 与 python 3.7.9 一起使用
谢谢
您只使用 CPU pytorch，但您的代码有类似 cr = nn.CrossEntropyLoss(weight=torch.tensor(classes_weights).cuda()) 的语句，它试图将张量移动到 GPU。
要修复它，
删除所有 .cuda() 操作。
我正在尝试 运行 来自 this repository 的代码，我需要使用 Pytorch 1.4.0。我已经使用 pip install torch==1.4.0+cpu torchvision==0.5.0+cpu -f https://download.pytorch.org/whl/torch_stable.html.
我通过 py -m train_Kfold_CV --device 0 --fold_id 10 --np_data_dir "C:\Users\username\OneDrive\Desktop\emadeldeen\AttnSleep\prepare_datasets\edf_20_npz" 运行 程序，但出现此错误：
File "C:\Users\username\AppData\Local\Programs\Python\Python37\lib\runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "C:\Users\username\AppData\Local\Programs\Python\Python37\lib\runpy.py", line 85, in _run_code
exec(code, run_globals)
File "C:\Users\username\OneDrive\Desktop\emadeldeen\AttnSleep\train_Kfold_CV.py", line 94, in <module>
main(config, fold_id)
File "C:\Users\username\OneDrive\Desktop\emadeldeen\AttnSleep\train_Kfold_CV.py", line 65, in main
trainer.train()
File "C:\Users\username\OneDrive\Desktop\emadeldeen\AttnSleep\base\base_trainer.py", line 66, in train
result, epoch_outs, epoch_trgs = self._train_epoch(epoch, self.epochs)
File "C:\Users\username\OneDrive\Desktop\emadeldeen\AttnSleep\trainer\trainer.py", line 49, in _train_epoch
loss = self.criterion(output, target, self.class_weights)
File "C:\Users\username\OneDrive\Desktop\emadeldeen\AttnSleep\model\loss.py", line 6, in weighted_CrossEntropyLoss
cr = nn.CrossEntropyLoss(weight=torch.tensor(classes_weights).cuda())
File "C:\Users\username\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\cuda\__init__.py", line 196, in _lazy_init
_check_driver()
File "C:\Users\username\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\cuda\__init__.py", line 94, in _check_driver
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
我已将配置中的 GPU 数量更改为 0，并尝试在程序开头添加 device = torch.device('cpu')，但它没有任何作用。我该如何解决这个错误？如果有帮助，我将 windows 10 与 python 3.7.9 一起使用
谢谢
您只使用 CPU pytorch，但您的代码有类似 cr = nn.CrossEntropyLoss(weight=torch.tensor(classes_weights).cuda()) 的语句，它试图将张量移动到 GPU。
要修复它，
删除所有 .cuda() 操作。