Closed lx2u16 closed 1 year ago
I also encountered the same problem when running, may I ask if there is any progress in updating the step?
By modifying lines 779 and 1111 of the train.py file, I change classerr.add(output.data.permute(0, 2, 3,1).flatten(start_dim=0,end_dim=2),target.flatten())
to classerr.add(output.data, target)
, Now it's working properly!
I don't know if this is correct, but it works!
With best wishes.
This issue has been marked stale because it has been open for over 30 days with no activity. It will be closed automatically in 10 days unless a comment is added or the "Stale" label is removed.
Commit #187 fixes that issue. thanks for reporting.
Hi, I am currently trying to run the training and evaluation scripts of faceid. They only work when I set batch size 1, and other sizes will give me this tensor size mismatch error.
e.g. with batch size 100
Could you please give me some help on how to fix this? Thanks.