YOLO Object Detection (Part 1)

Поделиться
HTML-код
  • Опубликовано: 28 ноя 2024

Комментарии • 57

  • @Kmysiak1
    @Kmysiak1 3 года назад +23

    The audio sucks but this man knows what he's talking about. I was taking Andrew Ng's deep learning course which confused the hell out of me and these videos made it much clearer! Can you maybe produce a video explaining the training of the model. Something which would explain the input features.

  • @RS-vu5um
    @RS-vu5um 4 года назад +18

    Audio quality is bad

  • @prasanjitrath281
    @prasanjitrath281 4 года назад +25

    You mention the metric as "Union over Intersection"? By the formula you mentioned, I'm pretty sure the metric is "Intersection over Union" as the latter makes sense from the division. Do think about this or let me know if the former one is actually also in place.

  • @randalllionelkharkrang4047
    @randalllionelkharkrang4047 2 года назад +3

    You are an amazing teacher . Thank you for sharing this.

  • @dorasnaranjit82
    @dorasnaranjit82 Год назад +1

    A part from the IoU (not UoI) these explanations are great! Thank you :-)

  • @rodghani6692
    @rodghani6692 Год назад

    Super good review. THANK YOU

  • @nmaajidkhan
    @nmaajidkhan 2 года назад +1

    Pro Tip before you begin the video: Use subtitles to relate with the audio

  • @giprincesa
    @giprincesa 4 года назад +3

    very good details on Yolo, thank you

  • @fatanehsadeghi5723
    @fatanehsadeghi5723 Год назад

    explanation is really great. thank you for fluently and simple explanation.just the audio wasn't great as much. thank you so much

  • @abdshomad
    @abdshomad 3 года назад +4

    Thank you very much for the clear explanation.
    Where can I watch the "part 2" of this series? The title said this is "part 1"

    • @drawdeelyofiug4651
      @drawdeelyofiug4651 3 года назад +2

      ruclips.net/video/pFp5WOoWTlU/видео.html . Second part :)

    • @abdshomad
      @abdshomad 3 года назад

      @@drawdeelyofiug4651 Thank you. Very helpful ....

    • @reubenthomas1033
      @reubenthomas1033 2 года назад

      @@abdshomad Where is the second part?

    • @abdshomad
      @abdshomad 2 года назад

      @@reubenthomas1033 seems like this is the 2nd part: ruclips.net/video/pFp5WOoWTlU/видео.html

  • @s2ms10ik5
    @s2ms10ik5 2 года назад

    thank god for the subtitles

  • @pathikghugare
    @pathikghugare 2 года назад

    Such a clear explaination !
    but I want to make sure that what I understood is correct so here's my understanding and doubts:
    1. we divide image into S x S grid
    2. In each grid, we try to predict probability that the bounding box(which we are predicting from our model) contains an object or not
    3. With 2, we try to predict the coordinates of the bounding box and the respctive conditional probabilities of classes
    4. Step 2,3 is I suppose the output of the model w.r.t each grid
    but I am still confused that if B is no of bounding boxes which we want to predict then why do we need 5B+C vectors?

    • @marcospiotto9755
      @marcospiotto9755 Год назад

      i think 5B+C is the lenght of the y vector, so if B = 2 then the y vector needs 5 elements for p,x,y,h,w of the first bounding box, then p,x,y,h,w for the second bounding box and lastly C elements for the probability of each class, 5*2 + C

  • @fukui307
    @fukui307 2 года назад +1

    should it be 5(B+C)?

  • @miko1335
    @miko1335 2 года назад

    Amazing teacher ! Thank you

  • @noureddineghoggali2380
    @noureddineghoggali2380 3 года назад

    where can I found the code or this tutorial
    part 2

  • @neotodsoltani5902
    @neotodsoltani5902 Год назад

    why the instructor says UoI thought the whole course??
    isn't it IoU? (as the formula shows, Intersection over Union)

  • @umar_muhammad_yaree
    @umar_muhammad_yaree 2 года назад +1

    Nice video 👍
    Can you share the slides

  • @salmakhaled2397
    @salmakhaled2397 2 года назад

    Thank you 🙏🏻

  • @ahmednserel_din2786
    @ahmednserel_din2786 8 месяцев назад

    can you share slides

  • @citizenuniverse8808
    @citizenuniverse8808 4 месяца назад

    Anyone confused about what the difference between c and p in the output vector?

  • @poojakabra1479
    @poojakabra1479 3 года назад

    Great explanation, thank you!

  • @lakshaydulani
    @lakshaydulani 2 года назад

    really nice video!
    do we call the Bounding boxes at 5:29 as "Anchor boxes"?

    • @GARUDA1992152
      @GARUDA1992152 2 года назад +1

      Anchor boxes are nothing but initial guesses of the bounding boxes, calculated using the aspect ratios and sizes of bounding boxes in the training dataset

  • @sb-tq3xw
    @sb-tq3xw 3 года назад

    when we train YOLO what are the labels? are labels also a tensor of shape SxSx(5B+C) ?

    • @toonepali9814
      @toonepali9814 3 года назад

      yup

    • @tulliolevichivita5130
      @tulliolevichivita5130 3 года назад

      Hi, All!. Thank you for this good video, but I'm wondering why the formula is S*S*(5*B+C), because according to this ruclips.net/video/vRqSO6RsptU/видео.html the formula should be S*S*B*(5+C). Can you elaborate on that?

    • @TheEully
      @TheEully 3 года назад +1

      @@tulliolevichivita5130 Hi! Here's what I interpreted from the video. SxS refers to the number of grids initially defined. For each of those grids there is a certain amount of Bounding Boxes (B) defined by p_c, b_h, b_w, b_x, b_y (5 params) and the probabilities of each bounding box belonging to the different classes (C). I think the second formula is the right one, as it makes no sense defining bounding boxes and not clasifying the object in it.

  • @kamiseqYT
    @kamiseqYT 4 года назад +3

    The content is one thing, knowing what to say is other but you need to master how present the information and how you speak, sound quality is really bad.
    But I like the content. Thanks.

  • @charleenlozi4775
    @charleenlozi4775 2 года назад

    12:20 I thought yolo has no pooling layer?

  • @9891676610
    @9891676610 Год назад +1

    At 11.08 output should be (S, S, No of Bounding Box x (5 + No of Total Classes)) and not (S, S, (5X no of bounding boxes + No of Classes))

    • @zukofire6424
      @zukofire6424 Год назад +1

      no you're wrong, read the paper is says that for each cell you get B*5+C values as output

  • @samc6368
    @samc6368 2 года назад

    at 11:00 isnt it better label with S x S X (5 (B+C))

    • @samc6368
      @samc6368 2 года назад

      Excellent overview, thanks, one more clarification at 15:00 is it UoI or IoU ?

  • @ExplotaOxxos
    @ExplotaOxxos 4 года назад

    thanks, very useful video. its possible to ignore some classes from coco? to detect only cats and ignore the others 79 detections

    • @nguyenvu6371
      @nguyenvu6371 4 года назад

      You have to re-train it or you can just display the bbox and label of the objet you want, ignore the rest

  • @daffercoll1998
    @daffercoll1998 3 года назад

    Thanks a lot!

  • @toonepali9814
    @toonepali9814 3 года назад

    can anyone explain bh and bw? what does it mean by percentage?

    • @vigneshwaranm456
      @vigneshwaranm456 3 года назад

      bh is the height of the detected object and bw is the width, the percentage say that yolo is sure that the detected object is 0.5 that is 50%

  • @saidgadiri6393
    @saidgadiri6393 4 года назад

    thanks

  • @moawiyaguinoubi836
    @moawiyaguinoubi836 3 года назад

    the sound is sooo low i could barely hear you :(

  • @BasicPoke
    @BasicPoke 3 года назад

    Thanks for the video. The audio is terrible.

  • @bitbyte8177
    @bitbyte8177 3 года назад

    You voice is dropping a lot

  • @ThePentanol
    @ThePentanol 3 года назад +2

    Low voice quality

  • @sahhaf1234
    @sahhaf1234 3 года назад +1

    Audio sucks.. All the effort put into this video went straight to garbage can because of the atrocious audio..

  • @science_electronique
    @science_electronique 10 месяцев назад

    bad quakity audio