Bbox is 'Nan' when weights have 0 about weighted-boxes-fusion HOT 4 OPEN

The easiest solution is to remove predictions from ensemble you don't need to use (e. g. weight = 0).

from weighted-boxes-fusion.

Yeah, that's right.
Weights [1, 0] made the ensembled model improve 0.03 mAP than the single model, 0.51 to 0.54 mAP ,but weights [1, 1] only obtained 0.002 mAP.
Maybe more models show the ability of the ensemble method better?

from weighted-boxes-fusion.

I meant you can remove second set of boxes and set weights to weights=[1], then WBF will be applied to first set of boxes only. It's the equiualent to weights=[1, 0]. Looks like you have some of boxes intersected in the predictions of same model, so they fuse in process.

from weighted-boxes-fusion.

from weighted-boxes-fusion.