0
$\begingroup$

Source: https://towardsdatascience.com/yolo-v3-object-detection-53fb7d3bfe6b

enter image description here

According to this image, it says the red grid is responsible for detecting the dog.

Similarly, do other cells detect "dog" as well or only the center ones?

For example, what do you think the first cell (0,0) would detect?

$\endgroup$
2
$\begingroup$

As the blog mentioned, each cell predicts three things -

  1. bbox coords (tx,ty,tw,th)
  2. objectness score (po)
  3. class scores (p0 - pc)

and again each cell predicts three boxes. Hence you get that big red tensor as model output.

So yes, other cells can detect "dog" and more precisely, each cell can detect any class.

what do you think the first cell (0,0) would detect?

Any object. for eg a sample one box prediction of that cell would be like -

box coords - [ 0.23, 0.12, 0.4, 0.2]

objectness score - (0.6) # this is a probability whether this box contains an object

class scores - [0.2,0.3,0.5] # lets say you have three classes, so here you will get the probability scores for those classes.

And each cell predicts three boxes, so you will get two more similar predictions from this cell. All of these are packed in that red tensor.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.