Thx to your released code.
Unfortunately i countered an error test on phase 1 (for base class)
line 332, in
inds = torch.nonzero(scores[:, j] > thresh).view(-1)
IndexError: index 16 is out of range for dimension 1 (of size 16)
I guess 'scores' tensor have shape such as [15,~,~...] but the code access this tensor with index 16.
Is there bug in a code..?
Thx to your released code. Unfortunately i countered an error test on phase 1 (for base class) line 332, in
inds = torch.nonzero(scores[:, j] > thresh).view(-1)
IndexError: index 16 is out of range for dimension 1 (of size 16)
I guess 'scores' tensor have shape such as [15,~,~...] but the code access this tensor with index 16. Is there bug in a code..?