YOLO (You Only Look Once) algorithm for Object Detection Explained!

Поділитися
Вставка
  • Опубліковано 13 січ 2025

КОМЕНТАРІ • 72

  • @poojapawar-s3i
    @poojapawar-s3i 5 днів тому +1

    Very helpful, great explanation on YOLO. Thank you very much

  • @sagnikroy6405
    @sagnikroy6405 3 роки тому +9

    Thanks, sir. Your content helped a lot. Everybody just codes and moves on, but nobody tells how it happens. Thank You

  • @totally_insane8140
    @totally_insane8140 2 роки тому +10

    Very lucid explanation and easy to understand. Learned a lot from this video alone, thanks and keep it coming

  • @manideep9013
    @manideep9013 Місяць тому

    This is a wonderful explainer, thanks much for doing this 🙏 just getting to know more about YOLO and everything about object detection. Have been in a rabbit hole & watching multiple videos but no other video explains as succinctly as this one.

  • @mohammadyahya78
    @mohammadyahya78 2 роки тому +2

    The best explanation on YOLO so far. Thank you.

  • @conOC
    @conOC 3 роки тому +7

    Simple, clear and instructible. Perfect to introduce to YOLO. SO GOOD

  • @rashibhardwaj506
    @rashibhardwaj506 Рік тому +2

    Amazing video. Thank you for explaining everything in just one video😃

  • @jaysoni7812
    @jaysoni7812 3 роки тому +2

    Amazing explanation with enough time thanks for saving my time

  • @tanmaythaker2905
    @tanmaythaker2905 2 роки тому +2

    Perfect and Crisp Explanation!

  • @rodghani
    @rodghani Рік тому +2

    simple and clear easy to comprehend

  • @chidanandchidu5154
    @chidanandchidu5154 Рік тому +1

    Sir👏, your teaching is just😚

  • @departmentofbasicsciencesc5693
    @departmentofbasicsciencesc5693 11 місяців тому

    very nicely explained thank you.

  • @wcottee
    @wcottee 6 місяців тому +1

    I missed something...for training and testing we have images plus bounding boxes in our inputs. But the final model input is image only. How is this handled?

  • @anandks364
    @anandks364 3 місяці тому

    Excellent brother🎉

  • @qaisjoker8306
    @qaisjoker8306 Рік тому

    Thank you so much. You are a legend!.

  • @venupunna9940
    @venupunna9940 4 роки тому

    really good simplification of yolo part1 ..... Thankyou

  • @srinivasand617
    @srinivasand617 4 роки тому

    Thanks much balaji. This will help me in my project preparations!

  • @krishnendudutta1465
    @krishnendudutta1465 4 роки тому

    Thnx balaji. Your content is awesome

  • @punithpuni927
    @punithpuni927 2 роки тому +2

    Sir I have a doubt please help me, you told that:
    1) Output layer consists of both classification(pc, c1, c2, ...) and bounding box values(bx, by, bh, bw) i.e, its a regression.
    2) At 2:45 you told that for ouput layer softmax activation is applied, but how can a softmax activation be applied on bounding box values which is regression.
    3) Ok let me assume that as the width and height values of Image and grid will be between 0 and 1 their may be a chance of using softmax, because softmax activation output will be between 0 and 1, but Iam not sure about this. But at 17:05 you told that in some cases in output layer bounding box width and height can be more than 1, but softmax which is applied to output layer can give values between 0 and 1, then how can bounding box width and height get the value more than 1.
    4) Softmax when used in output layer it will consider bounding box values also as classes, so how can softmax be used in output layer.
    Can you please solve my confusion.

  • @sagarlekhak7099
    @sagarlekhak7099 3 місяці тому

    Great Explanation

  • @priyathirumalainambi
    @priyathirumalainambi 3 роки тому

    Thanks balaji. You taught really well. Pls upload more videos. will be more useful

  • @nikeshmali8506
    @nikeshmali8506 Рік тому

    thanks for this explaintion

  • @harshdevmurari007
    @harshdevmurari007 2 роки тому

    nice explaination..........really good........

  • @aashishrana9356
    @aashishrana9356 2 роки тому

    well explained , thank you much

  • @prathmeshdeval8773
    @prathmeshdeval8773 Рік тому

    Great explanation!

  •  3 роки тому

    Nice introduction, thank you

  • @manojkpr7934
    @manojkpr7934 4 роки тому

    Very well explained👌

  • @021bethineedilakshmideepak4
    @021bethineedilakshmideepak4 4 роки тому

    @Balaji Srinivasan, Sir you explained exactly like Andrew ng in a detailed manner. Happy to come to know about your channel

  • @sharadpkumar
    @sharadpkumar 9 годин тому

    beautiful...

  • @aiswaryajustin2728
    @aiswaryajustin2728 3 роки тому

    Thanks for sharing ❤️

  • @kollaanantraj3690
    @kollaanantraj3690 2 роки тому

    very well explained

  • @jayeshbagul3961
    @jayeshbagul3961 3 роки тому

    Excelent it really benifical for me Thank you for your guidance

  • @praveenreddy1767
    @praveenreddy1767 3 роки тому +2

    I have doubt could you please clear this...Suppose consider 3 X3 Grid (grid1,2,3,4,5,6) and consider a image ie car is spread over 2 grids (5th and 6th grids ) For Grid 5th, Yolo through CNN operation identifies image and its bounding box and vector cordinates are predicted covering two (5th and 6th) grid cells . Now for 6th grid also same operation will be applied . So now after whole grids operation does.5th and 6th grid predictions combined through NMS and IOU to single prediction where image is exactly PRESENT ? Is my understanding correct?

  • @waqarmurtaza1611
    @waqarmurtaza1611 4 роки тому

    WELL EXPLAINED...

  • @nitinvedwal5786
    @nitinvedwal5786 2 роки тому

    is it for training or identification

  • @lavanyaramesh1241
    @lavanyaramesh1241 4 роки тому

    Must thank you bro❤️

  • @lakshaydulani
    @lakshaydulani 3 роки тому

    great work

  • @jeffreyeiyike122
    @jeffreyeiyike122 Рік тому

    please i want to know which tensor or vector of the images saved. all I see is the bounding box and classification and probability

  • @DeepakSaini-sg3pq
    @DeepakSaini-sg3pq 4 роки тому

    Great explanation thank you 😊
    #Subscribed

  • @sikendrakumar9009
    @sikendrakumar9009 3 роки тому +2

    its is an awesome video and u explained everything quite well. plz make a list of videos about opencv and neural network working.

  • @mehul4mak
    @mehul4mak 2 роки тому

    If y output only detect one object at a time then how come we can have multiple object detected in single frame at a time?

  • @kalidasuangadi4052
    @kalidasuangadi4052 4 роки тому +1

    1. how anchor boxes are placed(initially).
    2. what is the value of ground truth at the time of inferencing

    • @durgeshmishra9449
      @durgeshmishra9449 Рік тому

      Anchor boxes are defined by us by giving the y value as ground truth while training. During the inference time you don't have the ground truth right.

  • @kishorejuniordeveloper4361
    @kishorejuniordeveloper4361 4 роки тому

    HI SIR , Excellent Explanation

  • @PraveenKumar-zf6ks
    @PraveenKumar-zf6ks 4 роки тому

    Hi Balaji, could you pls upload RCNN and its types. Masked RCNN also?

    • @BalajiSrinivasan25
      @BalajiSrinivasan25  4 роки тому +1

      Sure, will upload them in a few days. Thanks for the suggestion 😊

  • @rohankishor3000
    @rohankishor3000 3 роки тому

    How program decides that how many Anchor boxes should be present for that particular image ?

    • @bruhm0ment767
      @bruhm0ment767 2 роки тому

      multiple anchor boxes are predicted for every object, YOLOv2 uses NMS (non maximal suppression through IoU (Intersection over Union)) and the Pc values to reduce down to a single anchor box for every object

  • @codevalley9511
    @codevalley9511 9 місяців тому

    thanks

  • @roobanrajr8866
    @roobanrajr8866 3 роки тому

    Bro today yenaku interview coding test iruku ....object detection model built pana solirukanga help pana mudiyum ma ?I have one two day to complete the code

  • @apurbaroy8411
    @apurbaroy8411 3 роки тому

    Is it possible to integrate the YOLO algorithm with arduino or raspberry pi using a webcam?

  • @riyazbagban9190
    @riyazbagban9190 2 роки тому

    Bro I like this explanation but I have doubts
    How bh bw bx by will be calculated
    Means who is responsible to calculate
    And how bunch of images get bounding boxes for training

    • @abinashpegu8663
      @abinashpegu8663 Рік тому

      Those training data are manually generated by data labellers.

  • @devakinandan23
    @devakinandan23 Місяць тому

    0:27

  • @robinson9822
    @robinson9822 3 роки тому

    Bro can you make aa face mask detection and social distancing using yolo

  • @mazharmumbaiwala9244
    @mazharmumbaiwala9244 2 роки тому

    any resources to the newer or better methods to solve the limitations of anchor boxes?
    what if my image has 100 instances of different objects to be detected, can someone point a link or mention them

  • @thirumalaisurya4587
    @thirumalaisurya4587 3 роки тому

    Bro code not working arguments error came

  • @karthifairhawn9825
    @karthifairhawn9825 4 роки тому +1

    Nanba I'm new subscriber hope you are tamil

  • @Ggghvujhjihhhhh
    @Ggghvujhjihhhhh 8 місяців тому

    Can someone develop project for my business using YOLO.

    • @Vros_vlog
      @Vros_vlog 7 місяців тому

      glad to do for you!

  • @priyanayak2000
    @priyanayak2000 Рік тому

    Code run agilla bro ..

  • @zalakthakker6846
    @zalakthakker6846 3 роки тому

    are able to share me slide?

  • @RishitirthaBanerjee
    @RishitirthaBanerjee Рік тому

    A GOD!!

  • @ruthfavila6015
    @ruthfavila6015 2 роки тому

    #YOLO

  • @bunnyvlogs7647
    @bunnyvlogs7647 3 роки тому

    Love u 3000

  • @tejabolla
    @tejabolla 4 роки тому

    usage: yolo.py [-h] -i IMAGE [-c CONFIDENCE] [-t THRESHOLD]
    yolo.py: error: the following arguments are required: -i/--image
    i am getting above error ,please help ji

  • @toxoreed4313
    @toxoreed4313 Рік тому

    tytytytytyty