Empty tensor from cross entropy loss function

[zeus (pyzeus)]

My input to the cross entropy loss function is torch.Size([69856, 21]) and target is torch.Size([69856]) and output is torch.Size([]).
When I mention nn.CrossEntropyLoss(reduce=None) it is giving empty tensor
when I mention nn.CrossEntropyLoss(reduce=False) it gives correct output shape but values are Nan.
Please help me solve this issue.

[KFrank]

Hi Zeus!

@zeus

My input to the cross entropy loss function is torch.Size([69856, 21]) and target is torch.Size([69856]) and output is torch.Size([]).

Could you post a simplified, but complete and runnable script that
illustrates this issue, together with the output of the script?

Best.

K. Frank

[zeus (pyzeus)]

My predicted scores are full of nan. That’s why it is returning empty tensors.