问题
I am using PyTorch. I am going to use the already trained model on multiple GPUs with CPU. how to do this task?
I tried on Anaconda 3 and pytorch with cpu only i dont have gpu
model = models.get_pose_net(config, is_train=False)
gpus = [int(i) for i in config.GPUS.split(',')]
model = torch.nn.DataParallel(model, device_ids=gpus).cuda()
print('Created model...')
print(model)
checkpoint = torch.load(config.MODEL.RESUME)
model.load_state_dict(checkpoint)
model.eval()
print('Loaded pretrained weights...')
the error i got is
AssertionError Traceback (most recent call last)
<ipython-input-15-bbfcd201d332> in <module>()
2 model = models.get_pose_net(config, is_train=False)
3 gpus = [int(i) for i in config.GPUS.split(',')]
----> 4 model = torch.nn.DataParallel(model, device_ids=gpus).cuda()
5 print('Created model...')
6 print(model)
C:\Users\psl\Anaconda3\lib\site-packages\torch\nn\modules\module.py in cuda(self, device)
258 Module: self
259 """
--> 260 return self._apply(lambda t: t.cuda(device))
261
262 def cpu(self):
C:\Users\psl\Anaconda3\lib\site-packages\torch\nn\modules\module.py in
_apply(self, fn) 185 def _apply(self, fn): 186 for module in self.children(): --> 187 module._apply(fn) 188 189 for param in self._parameters.values():
C:\Users\psl\Anaconda3\lib\site-packages\torch\nn\modules\module.py in _apply(self, fn)
185 def _apply(self, fn):
186 for module in self.children():
--> 187 module._apply(fn)
188
189 for param in self._parameters.values():
C:\Users\psl\Anaconda3\lib\site-packages\torch\nn\modules\module.py in _apply(self, fn)
191 # Tensors stored in modules are graph leaves, and we don't
192 # want to create copy nodes, so we have to unpack the data.
--> 193 param.data = fn(param.data)
194 if param._grad is not None:
195 param._grad.data = fn(param._grad.data)
C:\Users\psl\Anaconda3\lib\site-packages\torch\nn\modules\module.py in <lambda>(t)
258 Module: self
259 """
--> 260 return self._apply(lambda t: t.cuda(device))
261
262 def cpu(self):
C:\Users\psl\Anaconda3\lib\site-packages\torch\cuda\__init__.py in _lazy_init()
159 raise RuntimeError(
160 "Cannot re-initialize CUDA in forked subprocess. " + msg)
--> 161 _check_driver()
162 torch._C._cuda_init()
163 _cudart = _load_cudart()
C:\Users\psl\Anaconda3\lib\site-packages\torch\cuda\__init__.py in _check_driver()
80 Found no NVIDIA driver on your system. Please check that you
81 have an NVIDIA GPU and installed a driver from
---> 82 http://www.nvidia.com/Download/index.aspx""")
83 else:
84 # TODO: directly link to the alternative bin that needs install
AssertionError:
Found no NVIDIA driver on your system. Please check that you
have an NVIDIA GPU and installed a driver from
http://www.nvidia.com/Download/index.aspx
回答1:
To force load the saved model onto cpu, use the following command.
torch.load('/path/to/saved/model',map_location='cpu')
In your case change it to
torch.load(config.MODEL.RESUME, map_location='cpu')
来源:https://stackoverflow.com/questions/55511857/how-to-load-the-gpu-trained-model-into-the-cpu