pytorch-retinanet icon indicating copy to clipboard operation
pytorch-retinanet copied to clipboard

Published 20 hours ago • verified publisher icon yhenon

Question: loss for multiclass detection

Open abhaysjuneja opened this issue 2 years ago • 0 comments

Does this loss implementation work for MultiClass classification? I see the use of Binary Cross Entropy, and it makes me wonder how it's being used. Is this applying the One Vs. Rest approach to calculate loss for multiple classes individually?

abhaysjuneja avatar Oct 22 '21 15:10 abhaysjuneja