Error in running code on CPU.

[parimuns]

Hello
I am trying to reproduce the code for power scheduling. But I don't have access to GPU , so I am running codes on a windows system with CPU.In your code,I have removed cuda() wherever it was written.But I am getting errors which I am not able to resolve.Your support in solving issues will be highly appreciated.
I have attached modified main.py and nets.py files.

For power scheduling,I am getting error in main file as
model_rmse = nets.run_rmse_net(model_rmse, variables_rmse, X_train, Y_train)

files.zip

`AttributeError Traceback (most recent call last)
in
----> 1 model_rmse = nets.run_rmse_net(model_rmse, variables_rmse, X_train, Y_train)

~\Untitled Folder 1\nets.py in run_rmse_net(model, variables, X_train, Y_train)
42 model.train()
43 train_loss = nn.MSELoss()(
---> 44 model(variables['X_train_']), variables['Y_train_'])
45 train_loss.backward()
46 opt.step()

c:\users\appdata\local\programs\python\python37\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs)
720 result = self._slow_forward(*input, **kwargs)
721 else:
--> 722 result = self.forward(*input, **kwargs)
723 for hook in itertools.chain(
724 _global_forward_hooks.values(),

c:\users\appdata\local\programs\python\python37\lib\site-packages\torch\nn\modules\loss.py in forward(self, input, target)
443
444 def forward(self, input: Tensor, target: Tensor) -> Tensor:
--> 445 return F.mse_loss(input, target, reduction=self.reduction)
446
447

c:\users\appdata\local\programs\python\python37\lib\site-packages\torch\nn\functional.py in mse_loss(input, target, size_average, reduce, reduction)
2633 mse_loss, tens_ops, input, target, size_average=size_average, reduce=reduce,
2634 reduction=reduction)
-> 2635 if not (target.size() == input.size()):
2636 warnings.warn("Using a target size ({}) that is different to the input size ({}). "
2637 "This will likely lead to incorrect results due to broadcasting. "

AttributeError: 'tuple' object has no attribute 'size'
`

[priyald17]

I have updated the code to use the newest version of PyTorch (76d19e4), which should hopefully resolve this issue.