Expected object of device type cuda but got device type cpu in Pytorch

Question

I have the following code which calculates a loss function:

class MSE_loss(nn.Module):
    """ 
    : metric: L1, L2 norms or cosine similarity
    : mode: training or evaluation mode
    """

    def __init__(self,metric, mode, weighted_sum = False):
        super(MSE_loss, self).__init__()
        self.metric = metric.lower()
        self.loss_function = nn.MSELoss()
        self.mode = mode.lower()
        self.weighted_sum = weighted_sum

    def forward(self, output1, output2, labels):
        self.labels = labels         
        self.linear = nn.Linear(output1.size()[0],1)

        if self.metric == 'cos':
            self.d= F.cosine_similarity(output1, output2)
        elif self.metric == 'l1':
            self.d = torch.abs(output1-output2)
        elif self.metric == 'l2':
            self.d = torch.sqrt((output1-output2)**2)

        def dimensional_reduction(forward):
            if self.weighted_sum:
                distance = self.linear(self.d)
            else:
                distance = torch.mean(self.d,1)
            return distance

        def estimate_loss(forward):
            distance = dimensional_reduction(self.d)
            pred = torch.exp(-distance)
            pred = torch.round(pred)
            loss = self.loss_function(pred, self.labels)
            return pred, loss

        pred, loss = estimate_loss(self.d)

        if self.mode == 'training':
            return loss
        else:
            return pred, loss

Given

criterion = MSE_loss('l1','training', weighted_sum = True)

I would like to get the distance after having gone through the self.linear neuron when implementing criterion. I am, however, prompted with the error 'Expected object of device type cuda but got device type cpu for argument #1 'self' in call to _th_addmm' indicating that something is wrong. I have omitted the first part of the code, but I provide the whole error message, so that you can get an idea of what is going on.

RuntimeError                              Traceback (most recent call last)
<ipython-input-253-781ed4791260> in <module>()
      7 criterion = MSE_loss('l1','training', weighted_sum = True)
      8 
----> 9 train(test_net, train_loader, 10, batch_size, optimiser, clip, criterion)

<ipython-input-207-02fecbfe3b1c> in train(SNN, dataloader, epochs, batch_size, optimiser, clip, criterion)
     57 
     58             # calculate the loss and perform backprop
---> 59             loss = criterion(output1, output2, labels)
     60             a = [[n,p, p.grad] for n,p in SNN.named_parameters()]
     61 

~/.conda/envs/dalkeCourse/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
    539             result = self._slow_forward(*input, **kwargs)
    540         else:
--> 541             result = self.forward(*input, **kwargs)
    542         for hook in self._forward_hooks.values():
    543             hook_result = hook(self, input, result)

<ipython-input-248-fb88b987ce71> in forward(self, output1, output2, labels)
     49             return pred, loss
     50 
---> 51         pred, loss = estimate_loss(self.d)
     52 
     53         if self.mode == 'training':

<ipython-input-248-fb88b987ce71> in estimate_loss(forward)
     43 
     44         def estimate_loss(forward):
---> 45             distance = dimensional_reduction(self.d)
     46             pred = torch.exp(-distance)
     47             pred = torch.round(pred)

<ipython-input-248-fb88b987ce71> in dimensional_reduction(forward)
     36             else:
     37                 if self.weighted_sum:
---> 38                     self.d = self.linear(self.d)
     39                 else:
     40                     self.d = torch.mean(self.d,1)

~/.conda/envs/dalkeCourse/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
    539             result = self._slow_forward(*input, **kwargs)
    540         else:
--> 541             result = self.forward(*input, **kwargs)
    542         for hook in self._forward_hooks.values():
    543             hook_result = hook(self, input, result)

~/.conda/envs/dalkeCourse/lib/python3.6/site-packages/torch/nn/modules/linear.py in forward(self, input)
     85 
     86     def forward(self, input):
---> 87         return F.linear(input, self.weight, self.bias)
     88 
     89     def extra_repr(self):

~/.conda/envs/dalkeCourse/lib/python3.6/site-packages/torch/nn/functional.py in linear(input, weight, bias)
   1368     if input.dim() == 2 and bias is not None:
   1369         # fused op is marginally faster
-> 1370         ret = torch.addmm(bias, input, weight.t())
   1371     else:
   1372         output = input.matmul(weight.t())

RuntimeError: Expected object of device type cuda but got device type cpu for argument #1 'self' in call to _th_addmm

self.d is however a tensor, but this has already been passed into GPU, as shown below:

self.d =
tensor([[3.7307e-04, 8.4476e-04, 4.0426e-04,  ..., 4.2015e-04, 1.7830e-04,
         1.2833e-04],
        [3.9271e-04, 4.8325e-04, 9.5238e-04,  ..., 1.5126e-04, 1.3420e-04,
         3.9260e-04],
        [1.9278e-04, 2.6530e-04, 8.6903e-04,  ..., 1.6985e-05, 9.5103e-05,
         1.9610e-04],
        ...,
        [1.8257e-05, 3.1304e-04, 4.6398e-04,  ..., 2.7327e-04, 1.1909e-04,
         1.5069e-04],
        [1.7577e-04, 3.4820e-05, 9.4168e-04,  ..., 3.2848e-04, 2.2514e-04,
         5.4275e-05],
        [4.2916e-04, 1.6155e-04, 9.3186e-04,  ..., 1.0950e-04, 2.5083e-04,
         3.7374e-06]], device='cuda:0', grad_fn=<AbsBackward>)

Answer 1

In the forward of your MSE_loss, you define a linear layer that is probably still in the CPU (you didn't provide an MCVE, so I can only assume):

self.linear = nn.Linear(output1.size()[0], 1)

If you want to try and see if this is the problem, you can:

self.linear = nn.Linear(output1.size()[0], 1).cuda()

However, if self.d is in the CPU, then it would fail again. To solve this, you could move the linear to the same device of the self.d tensor by doing this:

def forward(self, output1, output2, labels):
    self.labels = labels         
    self.linear = nn.Linear(output1.size()[0], 1)

    if self.metric == 'cos':
        self.d = F.cosine_similarity(output1, output2)
    elif self.metric == 'l1':
        self.d = torch.abs(output1-output2)
    elif self.metric == 'l2':
        self.d = torch.sqrt((output1-output2)**2)

    # move self.linear to the correct device
    self.linear = self.linear.to(self.d.device)

Answer 2

Just as a supplement or a general answer, each time you meet this cuda and cpu unmatched error, you should first check the following three things:

1. Whether you put your model on cuda, in other words, whether you have the similar code as:
   model = nn.DataParallel(model, device_ids=None).cuda()
2. Whether you put your input data on cuda, like input_data.cuda()
3. Whether you put your tensor on cuda, something like:
   loss_sum = torch.tensor([losses.sum], dtype=torch.float32, device=device)

Emm, if you do the three checks, maybe you will solve your problem, good luck.