YOLO non-max supression

Course Q&A Deep Learning Specialization Convolutional Neural Networks
5

@dmunera3

I had the same question (I needed a few more words for it though :smile:): Course 4, week 3, programming assignment 1: non-max suppression and multiple classes

@ai_curious

the grid cell and anchor box indices associated with each prediction are already gone by the time the list of predicted bounding boxes is passed to NMS. You just have the coordinates and the confidence to work with

Are you sure about this? In the function we implemented, yolo_non_max_suppression((), all information needed to calculate the NMS per class is still there (in the tensors boxes, scores, and classes). It is true though that the class information is not passed to totf.image.non_max_suppression() - but we still had that information ready. So presumably, the TF implementation of NMS used here actually does not do the NMS per class.

@TMosh

It appears that TF automatically handles this inside the non_max_suppression() function.

I wonder how then. The class information, which is available, is not given to the TF implementation of NMS (tf.image.non_max_suppression()). Or do you mean that classes are just ignored?