Why am I getting a Pytorch Runtime Error on Test Set

Question

I have a model that is a binary image classification model with the resnext model. I keep getting a run time error when it gets to the test set. Error message is RuntimeError: Expected object of backend CPU but got backend CUDA for argument #2 'weight'

I am sending my test set tensors to my GPU like my train model. I've looked at the following and I'm doing what was suggested here as stated above.

Here is my model code:

resnext = models.resnext50_32x4d(pretrained=True)
resnext = resnext.to(device)
for param in resnext.parameters():
    param.requires_grad = True
resnext.classifier = nn.Sequential(nn.Linear(2048, 1000),
                                 nn.ReLU(),
                                 nn.Dropout(0.4),
                                 nn.Linear(1000, 2),
                                 nn.Softmax(dim = 1))
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(resnext.classifier.parameters(), lr=0.001)
import time
start_time = time.time()

epochs = 1

max_trn_batch = 5
max_tst_batch = 156

y_val_list = []
policy_list = []

train_losses = []
test_losses = []
train_correct = []
test_correct = []

for i in range(epochs):
    for i in tqdm(range(0, max_trn_batch)):
        trn_corr = 0
        tst_corr = 0

        # Run the training batches
        for b, (X_train, y_train, policy) in enumerate(train_loader):
            #print(y_train, policy)
            X_train = X_train.to(device)
            y_train = y_train.to(device)
            if b == max_trn_batch:
                break
            b+=1

            # Apply the model
            y_pred = resnext(X_train)
            loss = criterion(y_pred, y_train)

            # Tally the number of correct predictions
            predicted = torch.max(y_pred.data, 1)[1]
            batch_corr = (predicted == y_train).sum()
            trn_corr += batch_corr
            # Update parameters
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()

            # Print interim results
            if b%1 == 0:
                print(f'epoch: {i:2}  batch: {b:4} [{100*b:6}/63610]  loss: {loss.item():10.8f}  \
    accuracy: {trn_corr.item()/(100*b):7.3f}%')

        train_losses.append(loss)
        train_correct.append(trn_corr)

        # Run the testing batches
        with torch.no_grad():
            for b, (X_test, y_test, policy) in enumerate(test_loader):
                policy_list.append(policy)
                X_test.to(device)
                y_test.to(device)
                if b == max_tst_batch:
                    break

                # Apply the model
                y_val = resnext(X_test)
                y_val_list.append(y_val.data)
                # Tally the number of correct predictions
                predicted = torch.max(y_val.data, 1)[1] 
                tst_corr += (predicted == y_test).sum()

        loss = criterion(y_val, y_test)
        test_losses.append(loss)
        test_correct.append(tst_corr)

    print(f'\nDuration: {time.time() - start_time:.0f} seconds') # print the time elapsed

Here is the full traceback:

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-84-48bce2e8d4fa> in <module>
     60 
     61                 # Apply the model
---> 62                 y_val = resnext(X_test)
     63                 y_val_list.append(y_val.data)
     64                 # Tally the number of correct predictions

C:\ProgramData\Anaconda3\lib\site-packages\torch\nn\modules\module.py in __call__(self, *input, **kwargs)
    545             result = self._slow_forward(*input, **kwargs)
    546         else:
--> 547             result = self.forward(*input, **kwargs)
    548         for hook in self._forward_hooks.values():
    549             hook_result = hook(self, input, result)

C:\ProgramData\Anaconda3\lib\site-packages\torchvision\models\resnet.py in forward(self, x)
    194 
    195     def forward(self, x):
--> 196         x = self.conv1(x)
    197         x = self.bn1(x)
    198         x = self.relu(x)

C:\ProgramData\Anaconda3\lib\site-packages\torch\nn\modules\module.py in __call__(self, *input, **kwargs)
    545             result = self._slow_forward(*input, **kwargs)
    546         else:
--> 547             result = self.forward(*input, **kwargs)
    548         for hook in self._forward_hooks.values():
    549             hook_result = hook(self, input, result)

C:\ProgramData\Anaconda3\lib\site-packages\torch\nn\modules\conv.py in forward(self, input)
    341 
    342     def forward(self, input):
--> 343         return self.conv2d_forward(input, self.weight)
    344 
    345 class Conv3d(_ConvNd):

C:\ProgramData\Anaconda3\lib\site-packages\torch\nn\modules\conv.py in conv2d_forward(self, input, weight)
    338                             _pair(0), self.dilation, self.groups)
    339         return F.conv2d(input, weight, self.bias, self.stride,
--> 340                         self.padding, self.dilation, self.groups)
    341 
    342     def forward(self, input):

RuntimeError: Expected object of backend CPU but got backend CUDA for argument #2 'weight'

Again, my tensors and the model are sent to the GPU so I'm not sure what is going on. Does anyone see my mistake?

Answer 1

[...] my tensors and the model are sent to the GPU [...]

Not the test Tensors. It is a simple mistake:

X_test.to(device)
y_test.to(device)

should be

X_test = X_test.to(device)
y_test = y_test.to(device)