I am getting this error only during the testing phase, but I do not face any problem in the training and validation phase.
The code snippet looks like the one below,
The “lab” is a tensor value and prints out the range in such a way,
tensor([6, 7, 8])
tensor([ 9, 10, 11])
tensor([21, 22, 23])
(Note*: the length of this lab tensor can be of length ‘n’ based on the value of ElementsPerClass)
Could you check, if lab is an empty tensor at one point?
This would yield the same error message and since it’s calculated by torch.arange this might happen, if start and end have equal values.
I am testing for NumRows = 10 that is, ElementsPerClass = 1
This gives lab as single value tensors on every iteration like,
tensor([1])
tensor([4])
tensor([7])
as I want a single tile of masking for self.mem_dim = 10