IndexError: invalid index of a 0-dim tensor. Use tensor.item() in Python or tensor.item<T>() in C++ to convert a 0-dim tensor to a number

[GeneralJing]

Traceback (most recent call last):
File "main.py", line 152, in
train(epoch)
File "main.py", line 120, in train
100. * batch_idx / len(train_loader), loss.data[0]))
IndexError: invalid index of a 0-dim tensor. Use tensor.item() in Python or tensor.item<T>() in C++ to convert a 0-dim tensor to a number

[shine0801]

I have the same problem. Has it been solved?

[1337Eddy]

That's a version problem. Replace 100. * batch_idx / len(train_loader), loss.data[0])) in line 120 with 100. * batch_idx / len(train_loader), loss.data.item())) and test_loss += F.cross_entropy(output, target, size_average=False).data[0] in line 131 with test_loss += F.cross_entropy(output, target, size_average=False).data.item()