bethgelab/siamese-mask-rcnn

How to design the loss function?

kidcad1412 opened this issue · 4 comments

I confuse the loss function,please help.

I am not sure I understood your question. Are you asking, what the loss is composed of?

I mean the loss function is same as the loss function in Mask R-CNN ? How the metric show in the loss function?

Exactly. The only difference is that the classification is only done for 2 classes ("is this an object from the same category as the reference or is it background") and not 81 classes ("is this an object from one of 80 predefined categories or is it background"). We thus made no changes to the loss but only to the labels which are conditioned on the reference.

thank you so much