I can't get the dtypes to match, either the loss wants long or the model wants float if I change my tensors to long. The shape of the tensors are 42000, 1, 28, 28 and 42000. I'm not sure where I can change what dtypes are required for the model or loss.

I'm not sure if dataloader is required, using Variable didn't work either.

dataloaders_train = torch.utils.data.DataLoader(Xt_train, batch_size=64)

dataloaders_test = torch.utils.data.DataLoader(Yt_train, batch_size=64)

class Network(nn.Module):
    def __init__(self):
        super().__init__()


        self.hidden = nn.Linear(42000, 256)

        self.output = nn.Linear(256, 10)


        self.sigmoid = nn.Sigmoid()
        self.softmax = nn.Softmax(dim=1)

    def forward(self, x):

        x = self.hidden(x)
        x = self.sigmoid(x)
        x = self.output(x)
        x = self.softmax(x)

        return x

model = Network()

input_size = 784
hidden_sizes = [28, 64]
output_size = 10 
model = nn.Sequential(nn.Linear(input_size, hidden_sizes[0]),
                      nn.ReLU(),
                      nn.Linear(hidden_sizes[0], hidden_sizes[1]),
                      nn.ReLU(),
                      nn.Linear(hidden_sizes[1], output_size),
                      nn.Softmax(dim=1))
print(model)

criterion = nn.NLLLoss()
optimizer = optim.SGD(model.parameters(), lr=0.003)

epochs = 5

for e in range(epochs):
    running_loss = 0
    for images, labels in zip(dataloaders_train, dataloaders_test):

        images = images.view(images.shape[0], -1)
        #images, labels = Variable(images), Variable(labels)
        print(images.dtype)
        print(labels.dtype)

        optimizer.zero_grad()

        output = model(images)
        loss = criterion(output, labels)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
    else:
        print(f"Training loss: {running_loss}")

Which gives

RuntimeError                              Traceback (most recent call last)
<ipython-input-128-68109c274f8f> in <module>
     11 
     12         output = model(images)
---> 13         loss = criterion(output, labels)
     14         loss.backward()
     15         optimizer.step()

/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
    530             result = self._slow_forward(*input, **kwargs)
    531         else:
--> 532             result = self.forward(*input, **kwargs)
    533         for hook in self._forward_hooks.values():
    534             hook_result = hook(self, input, result)

/opt/conda/lib/python3.6/site-packages/torch/nn/modules/loss.py in forward(self, input, target)
    202 
    203     def forward(self, input, target):
--> 204         return F.nll_loss(input, target, weight=self.weight, ignore_index=self.ignore_index, reduction=self.reduction)
    205 
    206 

/opt/conda/lib/python3.6/site-packages/torch/nn/functional.py in nll_loss(input, target, weight, size_average, ignore_index, reduce, reduction)
   1836                          .format(input.size(0), target.size(0)))
   1837     if dim == 2:
-> 1838         ret = torch._C._nn.nll_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
   1839     elif dim == 4:
   1840         ret = torch._C._nn.nll_loss2d(input, target, weight, _Reduction.get_enum(reduction), ignore_index)

RuntimeError: expected scalar type Long but found Float