Closed Noiredd closed 1 year ago
"indices = torch.topk(- distances, k)[1]" aims to find the top k nearest category-specific features in the codebook. It seems that the dimension of the codebook is not correct? I suggest checking the dimension of the "distances" and "codebook".
Just found this ancient issue which by the way has nevered occurred again after I reinstalled your repo. Must've been something with dependencies.
Thanks for the interesting paper and easy to run implementation!
I tried following your training guide but got surprisingly stuck on the first step (D2SA training):
I modified the config to make a quick test, only changing the
SOLVER
entry in theBase-RCNN-FPN-D2SA.yaml
as follows:(Single image per batch, less iterations, no stepping and no checkpoints.) I figured this kind of change would let me run the model quickly, see if everything works, and then I'd run the whole thing overnight.
After successfully training for 7000 iterations the process crashed at evaluation with the following traceback:
I know this error pops up when one tries to run
torch.topk
withk
greater than the number of classes, but honestly I have no idea where to look for the source of this in the model configs. Any hints?