YOLO V1 - YOU ONLY LOOK ONCE || YOLO OBJECT DETECTION SERIES

Поділитися
Вставка
  • Опубліковано 4 гру 2024

КОМЕНТАРІ •

  • @MLForNerds
    @MLForNerds  2 роки тому +4

    Watch my latest in-detailed video on YOLO-V2 object detector.
    ua-cam.com/video/PYpn1GSwWnc/v-deo.html

  • @TimidMeercat
    @TimidMeercat Рік тому +16

    After viewing multiple videos on YOLO workings, I found your video very detailed and helpful. Thanks!

    • @MLForNerds
      @MLForNerds  Рік тому +1

      Thank you Nitin, glad it helped you.

  • @madhavpr
    @madhavpr Рік тому +10

    Hands down the BEST explanation of the Yolo family found online. Great job brother!! Keep up the great work.

  • @ahsentahir4473
    @ahsentahir4473 8 місяців тому +2

    Great! I have not seen such indepth explanation anywhere. God bless you!

    • @MLForNerds
      @MLForNerds  7 місяців тому

      Glad it was helpful!

  • @shubha07m
    @shubha07m Рік тому +19

    I am so surprised that, you are doing such a phenomenal job, (trust me: almost no UA-cam channel does such a deep dive into theoretical understanding video!), but you do not have so many subscribers! I will definitely spread about this excellent channel.

  • @SonNguyen-y2e3o
    @SonNguyen-y2e3o 9 місяців тому +2

    Bro ! I stuck to understand Yolo until I found your video. This deserves more than 15k views. now I know at least how Yolo working

  • @Dontknow-s2x
    @Dontknow-s2x 2 місяці тому

    2 min silence for those who can't find this video ! Best video for yolo i read it paper,watch video , read article and i was confused like hell in loss fn and bounding box now its clear thank you so much i recommed to everyone who is planning to study deep learning
    ❤♥

  • @aryangaur276
    @aryangaur276 10 місяців тому +3

    You are really awesome. My all concepts cleared.

  • @ankitsharma-ol9qn
    @ankitsharma-ol9qn 2 місяці тому

    Greatest lecture... I have ever seen on youtube...Thank you so much..

  • @chandank5266
    @chandank5266 11 місяців тому +1

    The best video on yolo v1 so far.

  • @rogribas
    @rogribas Місяць тому

    Incredible explanation, thank you very much

  • @ParbatSingh-sl3ko
    @ParbatSingh-sl3ko 8 місяців тому +2

    Loved the simplicity of explaining, and the presentation was also very minimal and apt. You really deserve more subs and views
    🙌❤

  • @zaidazhari9386
    @zaidazhari9386 Рік тому +5

    Thank you very much sir, i've been watching few videos regarding YOLO v1, but had difficulty grasping the loss function. But your video has helped a lot in understanding it 👍👍👍

  • @consumeentertainment9310
    @consumeentertainment9310 4 місяці тому

    You rock!!! It was very detailed. Clearly, you have out a lot of work into this. Thank you so much🙏🙏🙏🙏🙏🙏

  • @kvnptl4400
    @kvnptl4400 8 місяців тому +2

    🌟A very in-depth analysis of the paper. I would say this is one of the best easy to understand explanations of YOLOv1. Keep up the good work

    • @MLForNerds
      @MLForNerds  7 місяців тому +1

      Glad it was helpful!

  • @AyushAgarwal-r4v
    @AyushAgarwal-r4v 11 місяців тому

    You are a god man ! Thanks for such clear and deep explanations of Yolo.

  • @harshans7712
    @harshans7712 3 місяці тому

    Thanks a lot for your video, this helped me a lot to understand its working

  • @giriprasad5221
    @giriprasad5221 Рік тому +1

    Great work in the image, class probability map says that cell occupies max area than we are giving that class and building targets we are just giving zeros to the cells which contains of center of object

  • @azama74
    @azama74 Рік тому

    Thanks, your videos is the best from another related videos of yolo expalanation

  • @pavantripathi1890
    @pavantripathi1890 Рік тому +1

    Great explanation of loss function.

  • @adityaa8918
    @adityaa8918 5 місяців тому

    Underrated. Keep going man!

  • @salilbhatnagar3260
    @salilbhatnagar3260 Рік тому +1

    A great lecture about YoLO! Thanks!

  • @mdminhazurrahman8673
    @mdminhazurrahman8673 Рік тому +1

    your videos are gems bro!! I have not got such a clear explanation on yolo anywhere. please make a video on yolov5 as well. thank you!!!

    • @MLForNerds
      @MLForNerds  Рік тому

      Thank you Rahman, Sure will make.

  • @AryanKumarBaghel-cp1jv
    @AryanKumarBaghel-cp1jv 6 місяців тому

    Fantastic explaination. Super clear

  • @poojaverma9168
    @poojaverma9168 Рік тому +1

    Great content, very informative wating for the next versions...🙂

  • @Тима-щ2ю
    @Тима-щ2ю 6 місяців тому

    Hi! thank you for your wonderfull explanation! Unfortunately in the original paper there are many unclear moments. Your video helped me a lot. But i still have some questions.
    1) "Grid cell is "responsible" if the center of bbox falls into it." In training data we have annotated bboxes. But in test data there are no annotated bboxes and therefore centers. So which grid cell will be "responsible" in that case?
    2) if c < threshold, then we simply nullify all the values in the vector or we should train the model to nullify the vector on its own?
    3) if only 2 grid cells (in your case) predict the coordinates of bboxes, what is the use of the other 47 grid cells (are the useless at all or not?)
    4) How one small grid cell (64x64) predicts a box for an object that is a way bigger than this cell (450x450)?
    5) Why you are telling that there are only 2 object cells, if the woman overlap at least 6 cells? Maybe you mean only 2 "responsible" cells?

  • @sagaradoshi
    @sagaradoshi 8 місяців тому

    Hello , Great explanation on the content. Not seen such detailed content on YOLO. I have some question looking forward for your support.
    1. Each cell can have two bounding box, but how is that the size of bounding box for each grid cell be different. For example in grid cell1 one bounding box could be rectangle and other as square. Or both are rectangles with different dimensions. So how is this possible?
    2. Each bounding box provides x,y,w,h relative to grid cell starting co-ordinate and original/ground truth width and height bounding box. Correct? What I didn't further understand is how each cell calculates it C score value per bounding box and how it calculated probabilities value?
    3. Then later you mentioned that out of two bounding box any one is considered for each cell based on confidence score of that bounding box * class probability right?
    4. When you are calculating the final loss.
    a. For cell with object , we took one of two bounding box and its x,y,w,h and c value and compared with ground truth value . Right?
    b. For cell with no object, we took C values from both bounding box and subtracted with 0 since ground truth confidence score is 0 for that cell. Right?
    5. Do we use IOU to calculate C value per bounding box per grid cell? If yes, how is it possible to calculate C value per grid as IOU depends on original size of bounding box which may spread across cells. Isn't?
    5. To get this ground truth value for each cell (x,y,w,h,c, p1....p20) do we do manual annotation for all the images in dataset if its custom dataset?
    Looking forward for your support

  • @Jayanth_mohan
    @Jayanth_mohan Рік тому

    It was really awesomoe Learnt a lot !! Thanks

    • @MLForNerds
      @MLForNerds  Рік тому

      Glad you liked it! Thank you 👍

  • @jayeshshinde9625
    @jayeshshinde9625 10 днів тому

    03:40 Iam confused, how the cell would know that the ground truth object's center falls inside it both in training and inference part. And after that , how the cell predicts the x, y, w, h, coordinates (anchors) as we don't know the size or shape of the object. Cause after training, the CNN would be able to extract the object features. Hence Objectness scores and class probabilities for each cell are understandable.

  • @jeffreydanowitz3083
    @jeffreydanowitz3083 11 місяців тому

    This is a very clear and concise video. It really helped me to put everything together. Question: each supergrid box has associated with it 2 bounding boxes for the object. So the algorithms allows for dual results. If surrounding supergrid boxes decide to give some confidence - say for a larger object - is there some non-maximal suppression or some mechanism that makes sure that each object is reported, in the end, only 1 time?
    Also just for clarity - in the training, the 2 5 valued vectors for the box are identical, I assume. Is this correct? We are just giving the algorithm some breathing space by potentially finding 2 bounding boxes per supergrid boxes in my understanding. Is this also correct?

  • @nayabwaris-pl8lj
    @nayabwaris-pl8lj 6 місяців тому +1

    please make video soon on remaining yolo variants

  • @aishwaryamahajan6773
    @aishwaryamahajan6773 Рік тому +2

    Awesome Content, please can you also create videos on RCNN, SPPNet, Fast RCNN, SSD and FPN, It would vey grateful, if possible. Very well explained. Waiting for more on videos🙂

  • @Endless_emotions1
    @Endless_emotions1 11 місяців тому

    Amazing video overall 👏

  • @mdabdullahalhasib1730
    @mdabdullahalhasib1730 9 місяців тому +1

    please release all the version of YOLO. Thanks

  • @prodbyprodigy
    @prodbyprodigy 5 місяців тому

    this is such a great vid

  • @YarkoFFXI
    @YarkoFFXI Рік тому +4

    Great content man, I'm really grateful for your videos. I have 2 questions regarding YOLO v1 that I hope you can help me with.
    1) how did the authors pretrain the model on 224x224 images, and then "resize" their network to accommodate 448x448 images for further training? Were you able to find details about this step?
    2) the authors state that yolo considers the whole image as opposed to more classical sliding window techniques such as overfeat. Is this thanks to the fully connected layers at the end? Because up until the 7x7x1024 conv layer, each activation has a receptive field that is smaller than the full image. So the only step that is a function of the whole image are the last FC layers.. And that's one weird architecture, my brain has a hard time keeping track what is going on, considering the flattening, the dense layers, and then reshaping again. Ugh.

    • @thuytran2880
      @thuytran2880 Рік тому

      hello, i read your cmt and such a very amazing question. It almost 5 months ago, but I wanna ask have you found out the answer? If you have, can you share the answer with me

    • @YarkoFFXI
      @YarkoFFXI Рік тому

      @@thuytran2880 no unfortunately I haven't made any progress in finding these answers :/

    • @praveenkandula8011
      @praveenkandula8011 10 місяців тому

      "the authors state that yolo considers the whole image as opposed to more classical sliding window techniques such as overfeat. Is this thanks to the fully connected layers at the end? ". The network structure doesn't play anyrole but the way they train does. In sliding window, slices of image pass thorugh a classifer multple times. Whereas in yolo, image is passed single time and the bounding box predictions are caluclated.

  • @vishnum7985
    @vishnum7985 2 роки тому +2

    Great content.
    Can you create a videos on latest YOLO models (7).
    Waiting for more. Good Luck!

    • @MLForNerds
      @MLForNerds  2 роки тому

      Thank you Vishnu, I will make all the yolo versions one by one.

  • @adityakrishnajaiswal8663
    @adityakrishnajaiswal8663 4 місяці тому

    Just wow!

  • @lovekesh88
    @lovekesh88 2 місяці тому

    class confidence is not conditional probability, the individual probabilities are conditional P(class_i | Object) and when you multiply with C_1 aka Pr(object), we get non conditional probabilities i.e. only Pr(Class_i)

  • @fotoluminescencjastudiesai1239
    @fotoluminescencjastudiesai1239 5 місяців тому +1

    great video, now I finally understand it :) could you just please clarify why in 22:32 only 2 grid cells contain objects? the woman appears in a few other cells as well, so why only two?

    • @MLForNerds
      @MLForNerds  5 місяців тому

      Wherever the object centroid falls, only those cells are considered

    • @fotoluminescencjastudiesai1239
      @fotoluminescencjastudiesai1239 5 місяців тому

      @@MLForNerds thank you!! just to make sure that I understand correctly - in this example, one cell has a centroid for the horse and one has a centroid for the person?
      also, are you planning on making a video on Yolo v7? :)

    • @MLForNerds
      @MLForNerds  5 місяців тому +1

      Yes, you are right regarding object centers. I will continue this series and finish all yolo versions

  • @daminirijhwani5792
    @daminirijhwani5792 3 місяці тому

    This is amazing could you do a transformer series!

  • @thuytran2880
    @thuytran2880 Рік тому +2

    Thank youu, you helped me so much. But can I ask you a question? I tried to find the knowledge about yolov1: the paper, websites, ... but I didnt find any sources having detailed knowledge as your video. Please, can you share to me how do you search and have this deep understanding. I will be very very very very very happy if you see my comment and reply me.

    • @MLForNerds
      @MLForNerds  Рік тому +1

      Yes of course! Read the paper and look inti the code implementation to understand in detail. Once you look at the implementation, most of your doubts get clarified. Hope it helps!

    • @tttmgwl
      @tttmgwl Рік тому

      Thank you very much❤❤, i will try reading the code

  • @sumanthpichika5295
    @sumanthpichika5295 5 місяців тому

    very detailed explanation, Thanks for making it more clear. I believe i didn't find any such video with the way you explained the things in deep. I have a doubt when you said total loss = obj loss+no obj loss, In the example you considered only 2 grid cells has an object which means obj loss is calculated for those 2 grid cells and remaining 47 grid cells falls under no obj loss right?

  • @mallaswetha5629
    @mallaswetha5629 Рік тому +1

    sir can you explain yolov5 or suggest me the best video for yolov5??????

  • @karthickmurugan8478
    @karthickmurugan8478 2 місяці тому

    Please explain more yolo versions from yolov5

  • @benna_plusplus
    @benna_plusplus 10 місяців тому +1

    Thank you for the video.. very well detailed. I have a question: how Yolo create 2 bounding box for each celll? By randomly creating the coordinates? This is still not clear for me.

    • @MLForNerds
      @MLForNerds  8 місяців тому

      Yes, correct. Box coordinates are learned as regression parameters.

  • @AndreiChegurovRobotics
    @AndreiChegurovRobotics 7 місяців тому

    great material!

  • @matecaste
    @matecaste 11 місяців тому

    I have two question. If YOLO predicts two boxes, how do you create the label? Do you repeat (x,y,w,h,c) two times?? And finally, what would you do in the process of create the label if the center of two objects are in the same cell?? Thank you, NICE VIDEO!!

  • @prathameshdinkar2966
    @prathameshdinkar2966 Рік тому +1

    Very nicely explained!
    I have a doubt, what if there are more than one gt box centers in one cell?

    • @neeru1196
      @neeru1196 Рік тому

      That's one of the limitations I guess. Each cell can only output one class.

    • @prathameshdinkar2966
      @prathameshdinkar2966 Рік тому

      @@neeru1196 Ok thanks

  • @pratikpatil2866
    @pratikpatil2866 4 місяці тому

    could you please mention source of the mathematical explanations it would be great help.

  • @asthapatidar5507
    @asthapatidar5507 10 місяців тому +1

    how the center of object is marked?..........for calculating the target?

    • @MLForNerds
      @MLForNerds  8 місяців тому

      That happens during training. You can calculate the center from bounding box obtained from GT

  • @spencergameing3575
    @spencergameing3575 Рік тому +1

    there are two C scores if the grid cell contains object. then for( Ci-Ci^)^2 whihch one should we consider

    • @MLForNerds
      @MLForNerds  Рік тому

      Consider the highest confidence score and it's corresponding object.

  • @srivaasjaideep522
    @srivaasjaideep522 8 місяців тому +1

    how is the center of the object detected?

    • @MLForNerds
      @MLForNerds  8 місяців тому +1

      From the groundtruth box, we can calculate the center of the object. It's used to identify which grid is responsible for detecting that object.

  • @luansouzasilva31
    @luansouzasilva31 7 місяців тому +1

    If only one grid cell is labeled as class X, how does it get the bbox for the entire object?

    • @MLForNerds
      @MLForNerds  7 місяців тому +1

      Grid call is only for box centre, the box dimensions will be learned as regression parameters

  • @abbasjafarpour4506
    @abbasjafarpour4506 Рік тому

    Very informative, thank you.

  • @dmlane_sougata
    @dmlane_sougata Рік тому

    Sir, can you please explain YOLOv5 architecture.

  • @akarshjain7141
    @akarshjain7141 Рік тому +1

    Why IoU is not taken into account while selecting the bbox out of 2 predicted bounding box?

    • @MLForNerds
      @MLForNerds  Рік тому +1

      During prediction, there is no groundtruth, how can we calculate IOU?

    • @ZakiMubarak-wk1vl
      @ZakiMubarak-wk1vl 11 місяців тому

      @@MLForNerds then, when do we use IoU?

  • @giuliorusso1046
    @giuliorusso1046 8 місяців тому

    But in the paper they say the objecness is Pr(Object) x IoU. Can anyone explain that? Why the video say 1?

  • @dimitrisspiridonidis3284
    @dimitrisspiridonidis3284 2 роки тому

    I often see in other videos people saying that width and height is relative to the grid contrary to the paper which clearly states relative to the image. Even Andrew ng him self in his courses says relative to the grid meaning that width and height can be greater than 1 , I wonder why is every one get's it wrong maybe they change it relative to the grid in the next papers.

    • @MLForNerds
      @MLForNerds  2 роки тому +2

      Yes, but I checked few implementations, they are implementing as in the paper. Only x&y is encoded with respect to grid cell. Width and height are just normalised by image dimensions.

  • @Raj-xz4vz
    @Raj-xz4vz Рік тому +1

    How we got ground truth value here i.e 200,311,142,250

    • @MLForNerds
      @MLForNerds  Рік тому +1

      Groundtruth values are provided by dataset.

  • @techie_gangwar
    @techie_gangwar Рік тому +1

    Can you share the ppt? It's really helpful

    • @MLForNerds
      @MLForNerds  Рік тому

      github.com/MLForNerds/YOLO-OBJECT-DETECTION-TUTORIALS

  • @yasht1328
    @yasht1328 Рік тому +1

    Bro please upload YOLOv5 model as soon as possible 🙏

  • @jeffg4686
    @jeffg4686 8 місяців тому

    Grounding Dino, what do you guys need a refresher course?
    It's all YOLO World these days...
    ua-cam.com/video/SjJYNZirQCU/v-deo.html