is the loss_conf right in loss function?

[Hsintao]

Thanks for your work.
i have a question.
loss_conf = .. + 0.5 * self.bce_loss(conf*noobj_mask,0)
why there is a zero?
shouldn't it beloss_conf = .. + 0.5 * self.bce_loss(conf*noobj_mask,tconf*noobj_mask)?
@BobLiu20
And for classification, why dont use a CrossEntropyLoss?

[beckhamchen]

The same doubt with you

[zhaoyang10]

The tconf of noobj is 0