C4W3L09 YOLO Algorithm

preview_player
Показать описание

Follow us:
Рекомендации по теме
Комментарии
Автор

Same concept is used in YOLO v3, but instead of softmax activation for all classes, logistic regression is applied to each class (meaning there can be an object belonging to two classes)

andresfernandoaranda
Автор

i have read multiple blog posts on yolo, along with the original paper, but this video provides the intuition at a different level. amazing !

ujjalkrdutta
Автор

YOLO algorithm *CORRECTION*

At time 5:00, for the slide titled "Outputting the non-max suppressed output" the text should read "For each grid cell" instead of "For each grid call".

manuel
Автор

I am not clear how will it's work at Inference time? How can I get model output BB into original image format? Kindly give me the mathematics how to compute it?

sahil-
Автор

So, at 1:49 we give the pc value to the 2nd anchor box because it had more IoU and not to the 1st. So to generalize, check if there's something worth in the grid; if there is, assign the associated pc value to anchor box with the highest IoU.

vaibhavsingh
Автор

This algorithm simplified the bounding box regression by having a 3x3 (or some other) grid output, right? What I didn't understand is how anchor boxes are used in this algorithm...

rpcruz
Автор

Is this YOLO or YOLO 9000? According to the YOLO paper, I think the y should be 3x3x((2x5)+3), so y is 3x3x13. Is this right?

Denmark_
Автор

Thank you very much for all your YOLO videos. They are just great :)

PoRouS
Автор

@0:56 I think something is wrong. According to YOLO paper we have [S, S, (B * 5 + C)] which means each cell has C classes but here you said that each anchor box has C classes or [S, S, B*(5+C)].

mehranmehralian
Автор

@5:28 How come bounding boxes size are different ? How is the bounding box size changing ?

maheshmedam
Автор

Is yolo is a deep learning algorithm???

waqasmalik
Автор

Johnson Deborah Miller Jason Garcia Dorothy

LinoMathiasen-mw
Автор

Is this a graduate or undergraduate level course?

GaganDaroach
Автор

Is Non-Max suppression used during training?

manikantabandla
Автор

at 6:01 how this lady's bounding box is there is separate CNN for each grid cell....can somebody explain ?

adityarajora
Автор

Just wanted to let you know that this video has been ripped and re-uploaded:

munzutai
Автор

OK, so how many objects can one cell of YOLOv1 predict? The article says 'we only predict one set of class probabilities per grid cell regardless of the number of boxes'? It seems that the article skirts around the fact that the model can only predict at most 1 object/cell, but the wording above does not exclude, for example, the case when all B objects belong to the same class. So how many?

alexter-sarkisov
Автор

If we divide the image into 3*3=9 small boxes, why do we still need bx, by, bh, bw these box coordinate variables?

lorryzou
Автор

I read some documents and I know yolo use HSV, can you explain for me why?

ngantrieuninh
Автор

Let's say I have an object in 3 of the grid cells. Then, the outputs of all the 3 of the grid cells should be identical, with the same values of bx, by, bh, bw. Am I correct?

lakshmanvengadesan