Question

我正在使用Windows上的PyTorch在FashionMNIST上训练一个简单的感知器。当我使用cpu运行它时，它执行得很好，但是在gpu上，它会抛出“无效的向量下标”错误。我在做什么错了？

我的代码：

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.fc1 = nn.Linear(28 * 28, 10)

    def forward(self, x):
        x = x.view(-1, 28 * 28)
        x = self.fc1(x)
        return x

net = Net().to(device)
optimizer = torch.optim.Adam(net.parameters(), lr=0.001)
criterion = torch.nn.CrossEntropyLoss()

epochs = 1
for epoch in range(epochs):
    running_loss = 0
    for i, data in enumerate(trainLoader, 0):
        x, y = data
        z = net(x.to(device))
        loss = criterion(z, y.to(device))
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
        if i % 2000 == 1999:
            print(epoch + 1, i + 1, running_loss / 2000)
            running_loss = 0

错误日志：

  File "C:/Users/tarpt/Desktop/deep1.py", line 45, in <module>
    loss.backward()

  File "C:\Program Files (x86)\Microsoft Visual Studio\Shared\Anaconda3_64\lib\site-packages\torch\tensor.py", line 102, in backward
    torch.autograd.backward(self, gradient, retain_graph, create_graph)

  File "C:\Program Files (x86)\Microsoft Visual Studio\Shared\Anaconda3_64\lib\site-packages\torch\autograd\__init__.py", line 90, in backward
    allow_unreachable=True)  # allow_unreachable flag

RuntimeError: invalid vector<T> subscript

PyTorch在GPU上引发“无效的vector <t>下标”

0 个答案: