Loss value for invalid samples when training

[jetta]

Hi, for this multi-task network, if there is no valid samples for some task in one batch, such as no -2 label for landmark features or no -1 and 1 labels for bbox features. when this happens, what the corresponding loss value should be? nan or 0?
Thanks in advance!

[ilyanelken]

@jetta Hi, loss function should be calculated according to samples you do have. If you look in the original paper target loss function, this is controlled by beta coefficient (sample type indicator). Ilya