Closed JustinhoCHN closed 5 years ago
Sorry, I made a mistake, the detectors_mask
are those positive examples that in the responsible cells for training, and the 1 - object_detection
are negative examples that in the responsible cells. The reason why the no_objects_loss
multiplied by the 1 - object_detection
is because we should choose less negative examples rather than all the other cells and anchors which are not reponsible for training (1-detectors_mask
). So, the object_detection
part has nothing to do with coordinates loss.
In
keras_yolo.py
line 282, the coordinates_loss code is:But in the original yolo paper, the coordinates_loss should be like this:
In other words, the
object_detection mask
is missing.So what do you think? Correct me if I'm wrong please. Thank you.