Question

我不明白此错误告诉我什么。在a different post中，同样的问题也得到解决，但是对此没有有用的解决方案。

Traceback (most recent call last):
  File "train.py", line 252, in <module>
    main()
  File "train.py", line 231, in main
    train(net, training_dataset, targets, device, criterion, optimizer, epoch, args.epochs)
  File "train.py", line 103, in train
    loss.backward()
  File "/home/hb119056/.local/lib/python3.6/site-packages/torch/tensor.py", line 107, in backward
    torch.autograd.backward(self, gradient, retain_graph, create_graph)
  File "/home/hb119056/.local/lib/python3.6/site-packages/torch/autograd/__init__.py", line 93, in backward
    allow_unreachable=True)  # allow_unreachable flag
RuntimeError: Function MulBackward0 returned an invalid gradient at index 0 - expected type torch.cuda.FloatTensor but got torch.FloatTensor

这是我代码中的对应段。

outputs = net(x, indices)
outputs = outputs.transpose(0, 1)
prob = F.normalize(outputs, p=1, dim=1).detach()
target = torch.from_numpy(np.load(file_dir + '/points/points{:03}.npy'.format(i))).to(device)
rv = torch.zeros(12 * outputs.shape[0])

for j in [x for x in range(10) if x != i]:
    source = torch.from_numpy(np.load(file_dir + '/points/points{:03}.npy'.format(j))).to(device)
    rv = factor.ransac(source, target, prob, n_iter, tol, device) # self-written

predicted = factor.predict(source, rv, outputs, device) # self-written
loss = criterion(predicted, target.type(torch.FloatTensor).to(device))
loss.backward() # error occurs here
optimizer.step()

非常感谢您的帮助，在此先感谢您！

Answer 1

更改此行：

loss = criterion(predicted, target.type(torch.FloatTensor).to(device))

到

predicted = predicted.to(device)
target=target.type(predicted.type()).to(predicted.device)
loss = criterion(predicted, target)

Answer 2

尝试更改 loss = criterion(predicted, target.type(torch.FloatTensor).to(device)) 至 loss = criterion(predicted, target.to(device).float())

PyTorch：RuntimeError：函数MulBackward0在索引0处返回了无效的渐变-预期类型为torch.cuda.FloatTensor，但得到了torch.FloatTensor

2 个答案: