Open joker-lb7 opened 1 year ago
Encountered a similar situation on our private dataset, where after several rounds in the Keypt
stage, the negative det_loss
has fallen to tens of thousands.
BTW, the detector loss is defined in the D3Feat paper and it's designed to allow for the negative values, but i'm not sure if the value (tens of thousands) is as expected.
details as following:: Epoch: 3 [10400/33532] data_time: 0.03s model_time: 0.10s ref_loss: 0.000000 ref_error: 0.000000 desc_loss: 0.000000 desc_acc: 52.416992 eqv_loss: 0.000000 eqv_acc: 0.000000 det_loss: -94.586985 match_loss: 0.000000