Negative numbers appeared when I was training with 3dmatch dataset, is this normal?

The-Learning-And-Vision-Atelier-LAVA / BUFFER

[CVPR 2023] BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration

MIT License

68 stars 8 forks source link

Negative numbers appeared when I was training with 3dmatch dataset, is this normal? #8

Open joker-lb7 opened 1 year ago

joker-lb7 commented 1 year ago

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

wzp21142 commented 8 months 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.