RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument max in method wrapper_clamp_Tensor)

[kaiwendulantediyiren]

Swin_V2运行报这个错，想问问要怎么解决呢？

[yang-0201]

训练命令加了“--device 0”嘛

[kaiwendulantediyiren]

训练命令加了“--device 0”嘛

加了，一样报这个错

[kaiwendulantediyiren]

训练命令加了“--device 0”嘛
你的能跑起来吗？

[kaiwendulantediyiren]

Who can solve this problem？

[yang-0201]

You can chat with me privately to see what your problem is, Wechat: 1111554

[iscyy]

You can try
!pip install torch==1.9.0+cu111 torchvision==0.10.0+cu111 torchaudio==0.9.0 -f https://download.pytorch.org/whl/torch_stable.html

[kaiwendulantediyiren]

It has been resolved. You can replace the torch and cuda versions.
!pip install torch==1.9.0+cu111 torchvision==0.10.0+cu111 torchaudio==0.9.0 -f

[lixiangMindSpore]

It has been resolved. You can replace the torch and cuda versions. !pip install torch==1.9.0+cu111 torchvision==0.10.0+cu111 torchaudio==0.9.0 -f

你下发命令是什么？

[zxp771]

@iscyy
hi,i followed you suggestion,but the error still there.

Traceback (most recent call last):
File "D:\yy\yolov7-main\test.py", line 320, in
test(opt.data,
File "D:\yy\yolov7-main\test.py", line 88, in test
model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once
File "D:\Anaconda\envs\yolo-hornet\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "D:\yy\yolov7-main\utils\torch_utils.py", line 372, in forward
out = self.model(x)
File "D:\Anaconda\envs\yolo-hornet\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
RuntimeError: The following operation failed in the TorchScript interpreter.
Traceback of TorchScript (most recent call last):
D:\yy\yolov7-main\models\common.py(1688): forward
D:\Anaconda\envs\yolo-hornet\lib\site-packages\torch\nn\modules\module.py(1039): _slow_forward
D:\Anaconda\envs\yolo-hornet\lib\site-packages\torch\nn\modules\module.py(1051): _call_impl
D:\yy\yolov7-main\models\common.py(1828): forward
D:\Anaconda\envs\yolo-hornet\lib\site-packages\torch\nn\modules\module.py(1039): _slow_forward
D:\Anaconda\envs\yolo-hornet\lib\site-packages\torch\nn\modules\module.py(1051): _call_impl
D:\Anaconda\envs\yolo-hornet\lib\site-packages\torch\nn\modules\container.py(139): forward
D:\Anaconda\envs\yolo-hornet\lib\site-packages\torch\nn\modules\module.py(1039): _slow_forward
D:\Anaconda\envs\yolo-hornet\lib\site-packages\torch\nn\modules\module.py(1051): _call_impl
D:\yy\yolov7-main\models\common.py(1867): forward
D:\Anaconda\envs\yolo-hornet\lib\site-packages\torch\nn\modules\module.py(1039): _slow_forward
D:\Anaconda\envs\yolo-hornet\lib\site-packages\torch\nn\modules\module.py(1051): _call_impl
D:\yy\yolov7-main\models\common.py(516): forward
D:\Anaconda\envs\yolo-hornet\lib\site-packages\torch\nn\modules\module.py(1039): _slow_forward
D:\Anaconda\envs\yolo-hornet\lib\site-packages\torch\nn\modules\module.py(1051): _call_impl
D:\yy\yolov7-main\models\yolo.py(625): forward_once
D:\yy\yolov7-main\models\yolo.py(599): forward
D:\Anaconda\envs\yolo-hornet\lib\site-packages\torch\nn\modules\module.py(1039): _slow_forward
D:\Anaconda\envs\yolo-hornet\lib\site-packages\torch\nn\modules\module.py(1051): _call_impl
D:\Anaconda\envs\yolo-hornet\lib\site-packages\torch\jit_trace.py(952): trace_module
D:\Anaconda\envs\yolo-hornet\lib\site-packages\torch\jit_trace.py(735): trace
D:\yy\yolov7-main\utils\torch_utils.py(362): init
D:\yy\yolov7-main\test.py(63): test
D:\yy\yolov7-main\test.py(320):
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!