Suppose you are running non-max suppression during the YOLO algorithm on the predicted boxes as shown below. Assume that boxes with probability less than or equal to 0.4 are discarded, and the IoU threshold for deciding if two boxes overlap is 0.5. How many boxes will remain after non-max suppression stage?
These are the boxes:
tree1: 0.46
tree2: 0.74
car1: 0.62
car2: 0.73
car3: 0.26
motorcycle: 0.58
pedestrian: 0.98

tree1 and tree2 overlap significantly
car1 and car2 overlap significantly