python - 在 GPU 中进行 60 分钟 Blitz 训练 PyTorch 分类器时出错

Question

我已经开始在 jupyter 实验室中通过他们官方的 60 分钟 blitz 教程(使用他们的 .ipynb 文件 link to the tutorial )学习 pytorch，并成功完成它，直到使用 GPU 进行分类器的转换和训练。我认为我已经根据这些结果成功地更改了网络、输入和标签的设备:

net=net.to(device)
net.fc1.weight.type()

输出:

'torch.cuda.FloatTensor'

并且:

inputs, labels = inputs.to(device), labels.to(device)
inputs.type(),labels.type()

输出:

('torch.cuda.FloatTensor', 'torch.cuda.LongTensor')

运行这些单元后，我运行了用于训练模型的单元，其中包含以下代码:

for epoch in range(2):  # loop over the dataset multiple times

running_loss = 0.0
for i, data in enumerate(trainloader, 0):
    # get the inputs
    inputs, labels = data

    # zero the parameter gradients
    optimizer.zero_grad()

    # forward + backward + optimize
    outputs = net(inputs)
    loss = criterion(outputs, labels)
    loss.backward()
    optimizer.step()

    # print statistics
    running_loss += loss.item()
    if i % 2000 == 1999:    # print every 2000 mini-batches
        print('[%d, %5d] loss: %.3f' %
              (epoch + 1, i + 1, running_loss / 2000))
        running_loss = 0.0

print('Finished Training') 

并收到此错误:

RuntimeError                              Traceback (most recent call last)
<ipython-input-55-fe85c778b0e6> in <module>()
     10 
     11         # forward + backward + optimize
---> 12         outputs = net(inputs)
     13         loss = criterion(outputs, labels)
     14         loss.backward()

~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in __call__(self, 
*input, **kwargs)
    475             result = self._slow_forward(*input, **kwargs)
    476         else:
--> 477             result = self.forward(*input, **kwargs)
    478         for hook in self._forward_hooks.values():
    479             hook_result = hook(self, input, result)

<ipython-input-52-725d44154459> in forward(self, x)
    14 
    15     def forward(self, x):
--->16         x=self.conv1(x)
    17         x = self.pool(F.relu(x))
    18         x = self.pool(F.relu(self.conv2(x)))

~\Anaconda3\lib\site-packages\torch\nn\modules\module.py in __call__(self, 
*input, **kwargs)
    475             result = self._slow_forward(*input, **kwargs)
    476         else:
--> 477             result = self.forward(*input, **kwargs)
    478         for hook in self._forward_hooks.values():
    479             hook_result = hook(self, input, result)

~\Anaconda3\lib\site-packages\torch\nn\modules\conv.py in forward(self, 
input)
    299     def forward(self, input):
    300         return F.conv2d(input, self.weight, self.bias, self.stride,
--> 301                         self.padding, self.dilation, self.groups)
    302 
    303 

RuntimeError: Expected object of type torch.FloatTensor but found type 
torch.cuda.FloatTensor for argument #2 'weight' 

为什么我会收到此错误以及如何修复它？

Answer 1

您还需要在训练循环内将输入和标签移动到GPU。

for i, data in enumerate(trainloader, 0):
    # get the inputs
    inputs, labels = data

    # move to GPU
    inputs = inputs.to(device)
    labels = labels.to(device)

    ...