RuntimeError: 预期标量类型 Long 但发现 Float

Question

我无法让 dtypes 匹配，如果我将张量更改为 long，则损失需要很长时间，或者模型需要浮动。张量的形状是 42000、1、28、28 和 42000。我不确定在哪里可以更改模型或损失所需的 dtype。

我不确定是否需要 dataloader，使用 Variable 也不起作用。

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}")

这使

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

Answer 1

LongTensor与整数同义。PyTorch 不会接受 aFloatTensor作为分类目标，因此它告诉您将张量转换为LongTensor. 这是您应该如何更改目标数据类型：

Yt_train = Yt_train.type(torch.LongTensor)

这在 PyTorch 网站上有很好的记录，您绝对不会后悔花一两分钟阅读此页面。PyTorch 本质上定义了九种 CPU 张量类型和九种 GPU 张量类型：

???????????????????????????????????????????????????????????????????????????????????????????????????????????
?        Data type         ?             dtype             ?     CPU tensor     ?       GPU tensor        ?
???????????????????????????????????????????????????????????????????????????????????????????????????????????
? 32-bit floating point    ? torch.float32 or torch.float  ? torch.FloatTensor  ? torch.cuda.FloatTensor  ?
? 64-bit floating point    ? torch.float64 or torch.double ? torch.DoubleTensor ? torch.cuda.DoubleTensor ?
? 16-bit floating point    ? torch.float16 or torch.half   ? torch.HalfTensor   ? torch.cuda.HalfTensor   ?
? 8-bit integer (unsigned) ? torch.uint8                   ? torch.ByteTensor   ? torch.cuda.ByteTensor   ?
? 8-bit integer (signed)   ? torch.int8                    ? torch.CharTensor   ? torch.cuda.CharTensor   ?
? 16-bit integer (signed)  ? torch.int16 or torch.short    ? torch.ShortTensor  ? torch.cuda.ShortTensor  ?
? 32-bit integer (signed)  ? torch.int32 or torch.int      ? torch.IntTensor    ? torch.cuda.IntTensor    ?
? 64-bit integer (signed)  ? torch.int64 or torch.long     ? torch.LongTensor   ? torch.cuda.LongTensor   ?
? Boolean                  ? torch.bool                    ? torch.BoolTensor   ? torch.cuda.BoolTensor   ?
???????????????????????????????????????????????????????????????????????????????????????????????????????????