YOLO algorithm bounding boxes car detection

[Max_Rivera]

I’m really confused with some details of YOLO. For a finer grid (19x19), we’re applying a convNet simultaneously to each grid cell. And each grid cell that contains a car, we give it a 1 for the car anchor box.

• How would it know a car is in a grid cell that just contains a tip or edge of a car?

• And then how does it choose which box contains the center?

• Is the grid cell that contains the center the ONLY grid cell that contains any bounding box information?

[ai_curious]

All of these questions have been discussed at one time or another in this forum. Have you searched on the keywords at all?

Here’s one that might be helpful: Quick question regarding YOLO algorithm

Or this one:

How does a cell detect a bounding box bigger than itself, YOLO?

@ai_curious Thanks! This gives me a fair bit of clarity, I even looked up the model architecture online and it makes sense. What threw me off was the course giving emphasis to each grid cell performing object localization which made me imagine something completely different. So does this mean that the grid structure is purely for training and us, assigning the center to grid and defining bounding boxes to allow the yolo architecture to learn it, but model in itself is not diving the image into …