YOLO Object Detection (TensorFlow tutorial)

แชร์
ฝัง
  • เผยแพร่เมื่อ 16 ม.ค. 2025

ความคิดเห็น • 980

  • @yet2BnAm3d
    @yet2BnAm3d 7 ปีที่แล้ว +133

    I literally just sat down to do an assignment on this. Siraj, your timing is impeccable

    • @SirajRaval
      @SirajRaval  7 ปีที่แล้ว +7

      thanks!

    • @DuhBroadcaster
      @DuhBroadcaster 7 ปีที่แล้ว +1

      @Siraj Raval, can you comment or make a video on how YOLO is trained? Are the two parts trained on different networks and then combined? Or are they all trained in one go? More info would be appreciated.

    • @sethagastya
      @sethagastya 5 ปีที่แล้ว +1

      I just liked this comment to bring the total to 69 :D

    • @TejasChaudhari22
      @TejasChaudhari22 5 ปีที่แล้ว

      Hfish21 please can you tell me how did u do all this work... Because its my project work.. It need it at any cost please

    • @tonystark8493
      @tonystark8493 4 ปีที่แล้ว

      Hey my name is naazim I have made this video on detecting actions in basketball match with Yolo, tensorflow etc
      Pls check it out if you are interested in this topic
      th-cam.com/video/0X6yTkXn-qQ/w-d-xo.html

  • @Lunsterful
    @Lunsterful 7 ปีที่แล้ว +1680

    Gotta send a link of this to my ex-wife! Maybe she can finally detect that I am a person.

    • @theAppleWizz
      @theAppleWizz 7 ปีที่แล้ว +25

      Way to much info to much but it's good your venting.

    • @contentity
      @contentity 7 ปีที่แล้ว +21

      Never marry a lizard person

    • @SirajRaval
      @SirajRaval  7 ปีที่แล้ว +74

      haha wow thats real af

    • @mulindwajoseph5176
      @mulindwajoseph5176 7 ปีที่แล้ว +1

      #LIZARD PERSON REALLY?/@#

    • @bluebear25519
      @bluebear25519 7 ปีที่แล้ว +2

      Lol, i wish in future it can detect and read mind

  • @JossWhittle
    @JossWhittle 7 ปีที่แล้ว +143

    At 4:10, HOG does actually mean Gradient in the same way as backprop does. An image is just a discrete representation of a continuous 2D signal, the gradient of the continuous signal at a point can be approximated from the discrete representation by taking the finite difference between neighbouring pixels.

    • @DavidSaintloth
      @DavidSaintloth 7 ปีที่แล้ว +11

      yeah I was surprised that Siraj didn't know that this was identical to a gradient.

    • @mike61890
      @mike61890 7 ปีที่แล้ว +6

      I think he meant the gradients don’t have the same function as they do in backprop, i.e. representing an error value

    • @MasterNeiXD
      @MasterNeiXD 7 ปีที่แล้ว +4

      So pretty much like a vector in physics.

    • @tioguerra
      @tioguerra 7 ปีที่แล้ว +11

      Joss Whittle is right, and Siraj comment startled me as well first time I watched. The derivative always points to the direction of the (possibly local) maximum. The gradient definition used in the context of backprop is not different. Even though in HOG it does not represent an error to be minimized, the property still holds.

    • @Vancha112
      @Vancha112 7 ปีที่แล้ว +1

      Yes one is gradient as in describing a slope, the other is gradient as in color. I think thats what he means by different :)

  • @Loopyengineeringco
    @Loopyengineeringco 7 ปีที่แล้ว +11

    TBH, I only clicked this because it said YOLO. Now my brain is exploding.
    But joking aside, you're a great explainer and this is all starting to make sense. Thanks for the video!

  • @georgebockari289
    @georgebockari289 7 ปีที่แล้ว +137

    Bro you might not know this...but you're pretty good at this TH-cam thing lol. Thanks man you're the best

    • @xavdel0
      @xavdel0 7 ปีที่แล้ว +15

      The secret is use deeplearning to improve the video

    • @RiteshKumarMaurya
      @RiteshKumarMaurya 7 ปีที่แล้ว +2

      Watch me man!
      th-cam.com/video/jc_-AIYvfKs/w-d-xo.html

    • @SirajRaval
      @SirajRaval  7 ปีที่แล้ว +6

      Thanks George lots of practice

    • @holychipotle
      @holychipotle 7 ปีที่แล้ว +2

      teaching is the best way to learn

  • @yashchandraverma3131
    @yashchandraverma3131 5 ปีที่แล้ว +39

    CNN works this time
    1- Computation
    2- Large Amount of Image available

  • @med12med
    @med12med 6 ปีที่แล้ว +13

    Man! You are amazing. your kind of presentation makes me stay completely focused!

  • @schulca
    @schulca 7 ปีที่แล้ว +31

    These videos are great! also a lot easier to focus on when there aren’t memes popping up all the time. I enjoy the lecture style.

    • @SirajRaval
      @SirajRaval  7 ปีที่แล้ว +2

      thanks Carl noted

  • @planktonfun1
    @planktonfun1 7 ปีที่แล้ว +48

    It seems that there's a faster algorithm called ssd multibox object detection, even works somewhat fast in android

    • @kevaldholu7366
      @kevaldholu7366 4 ปีที่แล้ว

      yes.. ssd is faster than the yolo. and better suit for real-time applications.

    • @lordbry470
      @lordbry470 4 ปีที่แล้ว +1

      @@kevaldholu7366 well yes. But the yolo is more favored because its simplicity than the latter.

  • @oliviersaint-jean6330
    @oliviersaint-jean6330 6 ปีที่แล้ว +12

    For videos, I think the algorithms should take the time dimension into account, (ie. increasing the probability of an object detected in one frame to be there again in the next frame) to decrease computation cost.

  • @intr0vrt639
    @intr0vrt639 7 ปีที่แล้ว +131

    Object detection made easy

    • @sharoseali708
      @sharoseali708 7 ปีที่แล้ว +1

      plz tell me how to implement this on my Windows PC ..plz tell me some way out for this bro.. ....

    • @TheAnirudhable
      @TheAnirudhable 7 ปีที่แล้ว +2

      Buy a MAC

    • @sharoseali708
      @sharoseali708 7 ปีที่แล้ว +1

      Bro this isn't a valid solution..

    • @sharoseali708
      @sharoseali708 7 ปีที่แล้ว +1

      The dark net has also windows version.. but i haven't know complete knowledge to set environment on Windows

    • @relionB
      @relionB 7 ปีที่แล้ว +2

      Use VoTT and CNTK docs.microsoft.com/en-us/cognitive-toolkit/object-detection-using-faster-r-cnn

  • @Lavimoe
    @Lavimoe 7 ปีที่แล้ว +2

    The whole video is very thorough and comprehensive, which makes such intimidating subject a no-brainer for the beginners. Not sure how I will use YOLO in my future projects, but I really learned a lot from this video!

    • @CAGonRiv
      @CAGonRiv ปีที่แล้ว

      Its been five years. How about now?

  • @doctorpurple5173
    @doctorpurple5173 5 ปีที่แล้ว +128

    I'm a genius now, thx

    • @rediyusputra8333
      @rediyusputra8333 5 ปีที่แล้ว +2

      @Xingming Pinyin this will make you genius, xigishihiwifisidirixieitiyiuiiy

  • @josephfoltz2423
    @josephfoltz2423 6 ปีที่แล้ว

    You sir, are the reason my company is headed into softwsee development, coding, and programming. This video is worth more than gold.

  • @ubvzard3944
    @ubvzard3944 6 ปีที่แล้ว +10

    @siraj, at 0:50; And we are going to build our own model as well....". But, when did we build our own model???

  • @RatherBeCancelledThanHandled
    @RatherBeCancelledThanHandled 7 ปีที่แล้ว +1

    I thank God, that I started studying programming/math, so much fun and so fascinating to be able to take part in such cool technological advancements.

  • @Carl-gi3il
    @Carl-gi3il 6 ปีที่แล้ว +12

    17:27. As a C programmer, I'm kinda offended, but at the same time I think the best language for machine learning is python and the best framework is tensorflow.

  • @saysoy1
    @saysoy1 6 ปีที่แล้ว +23

    0:41 i'm still searching for the train!

  • @guiller2371
    @guiller2371 หลายเดือนก่อน

    I love this video!
    Never expect any but the best from Siraj.

  • @LeEnnyFace
    @LeEnnyFace 7 ปีที่แล้ว +3

    i love how siraj's videos are understandable until the last quarter or so and then it's a freaking downhill

  • @jbuist
    @jbuist 6 ปีที่แล้ว

    That was an excellent description of a topic that has been confusing the heck out of me for many hours. Thank you!

  • @exratt
    @exratt 7 ปีที่แล้ว +3

    Hi Siraj,
    thanks for your video. I never heard of the YOLO detector before and find this approach very interesting, as I'm used to the good old brute force method of detecting objects. I have a few remarks concerning the two mentioned pre-deep-learning algorithms.
    Regarding the Viola-Jones detector: The features are hand-coded (Haar-like features, which are basically the gray-scale value difference of neighboring rectangular regions), but the locations are not selected by the researchers themselves, as suggested by your video. Instead, they are selected by the training algorithm. They did not use a support vector machine for classification, but a cascade of simple classifiers, which were trained using AdaBoost. Maybe you confused it with the HOG approach.
    What made the Viola-Jones detector so efficient was the features and cascade. The features could be computed very efficiently using an integral image (only three additions to compute the sum of gray-scale values over any axis-aligned rectangular region). The cascade was trained such that image windows which did not contain a face would be discarded very quickly, so only very few windows needed to compute all the features and go through all cascades.
    The image on your slides is also a bit misleading. It mentions local binary patterns, which is another feature extraction method. The image shows face recognition, in this very case to find out whether a face belongs to the person it pretends to be.
    The Dalal-Triggs detector uses histograms of oriented gradients, as you mention. They build histograms over each cell, so it does not only contain the strongest gradient direction of all the pixels in a cell.

  • @kevinmcaleer28
    @kevinmcaleer28 6 ปีที่แล้ว

    This is the best explanation of object detection I've watched. Great work Siraj

  • @jazzpote4316
    @jazzpote4316 7 ปีที่แล้ว +3

    Your videos are so amazing. You cover all the fields of CS practically, with a state of the art approach.
    So helpful, keep it up

  •  7 ปีที่แล้ว +1

    Hi Siraj, just another killer tuto !!! Let me just add that windows users (like me by the way) might have difficulties to install darkflow. They can encounter a cl.exe exit code 2. To get around that you have to use the pip install . within the cross compiler x86_64 command prompt. To do that you just use the Windows key, followed by ctrl-tab and then type v on the keyboard. This should lead you to the Visual Studio command prompts list. Choose the right one and then go to the cloned darkflow dir to issue the pip command. Keep up the great work Man !!!

  • @gabrielvoss6251
    @gabrielvoss6251 7 ปีที่แล้ว +11

    Yeeeee I waited for so long for yolo

    • @RiteshKumarMaurya
      @RiteshKumarMaurya 7 ปีที่แล้ว +1

      The Magic V, do you want to have a tutorial on Google Speech API, i.e., convert your speech into text!
      Watch this:
      th-cam.com/video/jc_-AIYvfKs/w-d-xo.html

  • @dirkvanbeveren5042
    @dirkvanbeveren5042 7 ปีที่แล้ว +2

    This is Brilliant. I'm actually gonna play with it. Thanks Siraj!

  • @llawliet6429
    @llawliet6429 7 ปีที่แล้ว +34

    "we are going to build"?. i think you used someone else's code. 20 min of explanation and 2 of demonstration ::thinking::

    • @carlosflar
      @carlosflar 7 ปีที่แล้ว

      L Lawliet yeah it was done by someone else

    • @ismailsahin9600
      @ismailsahin9600 7 ปีที่แล้ว +4

      ok you can do 20 min of demo and 2 min explanation, but you wont. So why, because never believe in appreciation

    • @llawliet6429
      @llawliet6429 7 ปีที่แล้ว +2

      i appreciate his videos, i am a programmer and i am thinking of staying aside anything that will destroy jobs. i guess i am just hating. if you think, the car is the most useful invention, and i am starting to think computers are not the answer to a "better world" :(. i am depressed.

    • @cynthiahabonimana2097
      @cynthiahabonimana2097 6 ปีที่แล้ว +3

      I am in CS too ! :) Just like a knife, deep learning can be used for wrong or good things depending on whose hands it is in ! I think our ethics should be questioned instead, to make sure we understand the impact what we’re creating. Cheer up ! Personally, I am excited for machine learning, what a time to be alive! :))

    • @possiblyadickhead6653
      @possiblyadickhead6653 6 ปีที่แล้ว

      Cynthia Habonimana will all laugh when theses fuckers of ai learn to code

  • @TushhsuT
    @TushhsuT 7 ปีที่แล้ว

    "gradient - they just using this word for this"
    lol !!!! you did my day man ;)
    It is you guys in neural networks, who probably JUST use this word for something else.
    Gradient is the mathematical value that shows whether the function is rising or decreasing and how fast. And it is correctly used for those purposes.
    But anyway - cool video!

  • @gugasevero76
    @gugasevero76 6 ปีที่แล้ว +6

    Siraj, can you do a video showing how to install YOLO, please? Thank you so much

  • @MrZouzan
    @MrZouzan 7 ปีที่แล้ว

    I was looking for this just a few days ago and was a great coincidence that you decided to upload this video , thanks!!

  • @ThisOLmaan
    @ThisOLmaan 5 ปีที่แล้ว +10

    wow it detects MP4 recorded files and in "Real Time" cooooool

    • @sarahmachin3665
      @sarahmachin3665 4 ปีที่แล้ว

      Any ideas why image jpgs work fine and mp4s don't on my mac?? thanks!

  • @kamarolzaman7199
    @kamarolzaman7199 7 ปีที่แล้ว

    Best video yet! I like this lecturer-y style much more, keep it up!

  • @Jonstyle69
    @Jonstyle69 4 ปีที่แล้ว +5

    nice video, plz make more

  • @tonycatman
    @tonycatman 7 ปีที่แล้ว

    10/10 for this. I'd never heard of YOLO, and this is a really great introduction.

  • @sorvex9
    @sorvex9 ปีที่แล้ว +1

    Oh how I miss 2018 machine learning.

  • @mirandaclace4940
    @mirandaclace4940 5 ปีที่แล้ว +9

    Anyone got any opinions/warnings regarding YOLOv3? About to start a project and dont wanna make my life more difficult than it already is

    • @Augmented_AI
      @Augmented_AI 5 ปีที่แล้ว

      Yolo V3 is really simple. I have some experience with it :)

  • @Xartab
    @Xartab 7 ปีที่แล้ว

    Oh, look, apparently now I have to binge-watch all the videos of this new channel that I just discovered. Honestly, at this point amazingly good channels like yours amount to a chore.

  • @VladyVeselinov
    @VladyVeselinov 6 ปีที่แล้ว +3

    Heads up, version 3 is just out: pjreddie.com/darknet/yolo/
    Paper: pjreddie.com/media/files/papers/YOLOv3.pdf

  • @richasingh8513
    @richasingh8513 6 ปีที่แล้ว

    It is such a beautiful initiative taken by you to teach the globe about the threshold technologies. Keep the good work up.

  • @sanstechie_official4669
    @sanstechie_official4669 5 ปีที่แล้ว +4

    I think it's developed by Joseph Redmon ...... YOLO i've seen his TED talk. and also he made it as open source.

  • @bloodaid
    @bloodaid 7 ปีที่แล้ว

    Siraj, even though i don't do anything AI related, I always watch your videos just in case I get started. I've learned so much

  • @Slanimero
    @Slanimero 7 ปีที่แล้ว +4

    I thought SSD, faster R-CNN using ResNet, and R-FCN were all more accurate than YOLOv2

    • @MLbytescse
      @MLbytescse 7 ปีที่แล้ว +3

      you are right yolo is fast but not accurate as other architectures

    • @SirajRaval
      @SirajRaval  7 ปีที่แล้ว

      will look into SSD

  • @lakshmannadipilli7315
    @lakshmannadipilli7315 4 ปีที่แล้ว

    wahh !!!!! what an explanation man ??? mind blown for 30 mins straight

  • @swaaagquan3540
    @swaaagquan3540 7 ปีที่แล้ว +6

    YOLO does seem to be a pretty good, some researchers I've chatted to are making it work for pothole detection: github.com/sekilab/RoadCrackDetector
    Saves anyone having to report a pothole again (in theory).
    It's an interesting time to be alive.

    • @SirajRaval
      @SirajRaval  7 ปีที่แล้ว

      great link!

    • @recklessroges
      @recklessroges 7 ปีที่แล้ว +1

      Good additional confirmation, but I think a distributed used of the anonymised accelerometers in phones is probably more effective. www.boston.gov/departments/new-urban-mechanics/street-bump

    • @swaaagquan3540
      @swaaagquan3540 7 ปีที่แล้ว +2

      Reckless Roges why not both? It's always good to crack the same problem in many ways.

  • @yannickmolinghen3425
    @yannickmolinghen3425 6 ปีที่แล้ว

    Thanks for your work it is the first time I find proper and clear explanations about how to interpret the network output!

  • @dasberserkr
    @dasberserkr 4 ปีที่แล้ว +5

    From a guy who defined the concept of a "logic door"...

  • @JohnnyDoeDoeDoe
    @JohnnyDoeDoeDoe 7 ปีที่แล้ว +1

    Video quality has gone way up! Nice job Siraj!

  • @daaaniel21
    @daaaniel21 7 ปีที่แล้ว +17

    I made this few months back for my college techfest. checkout this ,it is the one that inspired me> github.com/oarriaga/face_classification

    • @edoardo247
      @edoardo247 7 ปีที่แล้ว +2

      Very good work, I will fork for sure :D

    • @SirajRaval
      @SirajRaval  7 ปีที่แล้ว +1

      very cool

    • @maxikanec4545
      @maxikanec4545 7 ปีที่แล้ว +1

      Will it assume my gender??? omg im getting triggered...

    • @octavioarriaga8443
      @octavioarriaga8443 7 ปีที่แล้ว +1

      I am glad to hear that :)!

  • @DannyJulian77
    @DannyJulian77 7 ปีที่แล้ว

    Siraj! Thank you so much! When you explain step by step like this I can undestand everything! Love this video!

  • @0Kaliber0
    @0Kaliber0 7 ปีที่แล้ว +6

    Can you show and explain SSD too? :3 I've read it should be faster then YOLO :)

    • @OBailo
      @OBailo 7 ปีที่แล้ว +1

      Nope, it's not. YOLOv2 is the fastest object detection out there. Check their comparison here (pjreddie.com/darknet/yolo/ )

    • @SirajRaval
      @SirajRaval  7 ปีที่แล้ว +2

      will consider ssd

    • @MrBenjaminb10
      @MrBenjaminb10 6 ปีที่แล้ว

      Did you?

  • @anarcominhoto
    @anarcominhoto 4 ปีที่แล้ว +2

    Can YOLO deal with RGB-D data from a Kinect device for example?

    • @GUINTHERKOVALSKI
      @GUINTHERKOVALSKI 4 ปีที่แล้ว

      sure, as any cnn.

    • @anarcominhoto
      @anarcominhoto 4 ปีที่แล้ว

      @@GUINTHERKOVALSKI How so? How can i input depth and rgb synced data in a cnn?

    • @GUINTHERKOVALSKI
      @GUINTHERKOVALSKI 4 ปีที่แล้ว

      @@anarcominhoto concat depth with rgb channels, so that your dim is (width,height,channels)

    • @anarcominhoto
      @anarcominhoto 4 ปีที่แล้ว

      @@GUINTHERKOVALSKI ok, but can i have a score of class, x,y and 3 bounding boxes parameteres, with that method?

  • @staberas
    @staberas 7 ปีที่แล้ว +46

    stop objectifying dogs siraj /jk

  • @Ricardo-zk9js
    @Ricardo-zk9js 5 ปีที่แล้ว +2

    i will literally pay for enjoy this content in spanish

  • @etiennetiennetienne
    @etiennetiennetienne 7 ปีที่แล้ว +9

    violo jones uses svm? omg can't you google stuff before you talk?? viola jones are famous for combining cascades of boosted classifiers...

    • @SirajRaval
      @SirajRaval  7 ปีที่แล้ว +3

      the improved version uses SVM link.springer.com/chapter/10.1007/978-3-642-22822-3_7

    • @etiennetiennetienne
      @etiennetiennetienne 7 ปีที่แล้ว +2

      "we present a new cascading structure added SVM stages which
      employ the confidence values of multiple preceding Adaboost stages as
      input". ... also, just googling "viola and jones", wikipedia: en.wikipedia.org/wiki/Viola%E2%80%93Jones_object_detection_framework

  • @myperspective5091
    @myperspective5091 7 ปีที่แล้ว

    I've seen YOLO before about a year or two ago it seems like it got better even since then. Good to see them still improving their product.

  • @francium511
    @francium511 7 ปีที่แล้ว +3

    Hey siraj nice work out there
    I am trying to start AI can you give me some recommendations about the content and there order to learn.
    Thank you.

    • @theAppleWizz
      @theAppleWizz 7 ปีที่แล้ว

      he has a playlist in his youtube page where he shows how it work

    • @itsSKG
      @itsSKG 7 ปีที่แล้ว

      See the video quick questions with siraj raval on this channel itself. You will find your answer!

    • @SirajRaval
      @SirajRaval  7 ปีที่แล้ว +1

      my playlists

  • @aprendehohau
    @aprendehohau 5 ปีที่แล้ว

    Thanks for your work it is the first time i find proper and clear explanations about how to interpreter the network output.

  • @jinxblaze
    @jinxblaze 7 ปีที่แล้ว +6

    imagine doing this but with capsule !! new project idea !!

    • @SirajRaval
      @SirajRaval  7 ปีที่แล้ว +3

      sprinkle capsule on everything lol

  • @marutinandan182
    @marutinandan182 5 ปีที่แล้ว

    I just wanted to say thank you for the great video I have been watching your videos for a little while now and I really enjoy the pacing of this one some of your other videos are a little fast and everything goes over my head but I think this was a good balance

  • @LouisCubingChannel
    @LouisCubingChannel 7 ปีที่แล้ว +4

    hi siraj,
    when I doing the YOLO I encountered: AssertionError: Over-read tiny-yolo.weights.
    the env is win7 and python 3.6.3.

  • @joeldejesusmazaamador2101
    @joeldejesusmazaamador2101 4 ปีที่แล้ว +1

    how does it work? android detection algorithms with yolo

  • @hamzakhalid9381
    @hamzakhalid9381 4 ปีที่แล้ว +9

    You're just reading off from a github page that's all and for the implementation part you just flew through it......!!

    • @bishwasmishra8860
      @bishwasmishra8860 4 ปีที่แล้ว +1

      Still helps.

    • @opaaaaaaaaaaa
      @opaaaaaaaaaaa 4 ปีที่แล้ว +1

      The important part is it helps.
      The reason you are here is also the same.😂

  • @aaronle2846
    @aaronle2846 2 ปีที่แล้ว

    Hey dude thanks so much for your lengthy explanations and your enthusiasm when you make your videos. It really helps !

  • @ZelenoJabko
    @ZelenoJabko 7 ปีที่แล้ว +10

    Congrats, you know how to copy-paste. But just barely.

  • @gudikandularamya889
    @gudikandularamya889 4 ปีที่แล้ว +1

    Hello sir...iam working on this project.i followed ur video to do things.but now am getting error no module name nms.if i install nms using pip it will give me another error .module nms has no attribute __pyx_capi__..sir please help me out this problem

  • @ubongfx2436
    @ubongfx2436 5 ปีที่แล้ว +3

    his movements are irretating me :(

  • @burf2000
    @burf2000 6 ปีที่แล้ว +1

    I would love to see an updated version of this, Yolo3 is out and doesn't seem to work with this code

    • @Augmented_AI
      @Augmented_AI 5 ปีที่แล้ว

      YoloV3 is indeed quite robust for common AI-CV applications :).

  • @TheSpellShell
    @TheSpellShell 7 ปีที่แล้ว +5

    Could it recognize person in hijab?

  • @flaviorodrigues197
    @flaviorodrigues197 4 ปีที่แล้ว +1

    is there any good website where i can find yolo implementation for java?

  • @rishavsrivastav500
    @rishavsrivastav500 7 ปีที่แล้ว +23

    😂😂 wasted 22 min.....all u did was reading the lines and in the end u said follow the link in the discription👏👏 if that was the case u could have rounded up the video in 2 min 😤😤😤

    • @brunzero7697
      @brunzero7697 6 ปีที่แล้ว +8

      he spent that time to explain to you in detail what was happening you ingrate

    • @RandomShowerThoughts
      @RandomShowerThoughts 6 ปีที่แล้ว +1

      he explained it really well but i agree

    • @allmightqs1679
      @allmightqs1679 6 ปีที่แล้ว +2

      Wow! People wanna code without knowing the logic behind the code. What has the world come to? 🙈

    • @vishavjeetsingh7862
      @vishavjeetsingh7862 6 ปีที่แล้ว +4

      Bro learning mein ego mat la, this video was useful for lots of folks including me. This video has now given me a direction as to which research papers to start with.

  • @matthewtoews8096
    @matthewtoews8096 5 ปีที่แล้ว

    Watching from my AI Medical Imaging course - very nice!

  • @viktorashistan7207
    @viktorashistan7207 3 ปีที่แล้ว +1

    10:00, haha such a cool trick, you scrolled down without using your hands, you- Oh.... Oh no

  • @ndujudeleonard9475
    @ndujudeleonard9475 3 ปีที่แล้ว

    Mehn!! you are a great teacher I wish I could subscribe a thousand times. Thank you for this♥️

  • @Brehhda
    @Brehhda 7 ปีที่แล้ว

    Thanks so much for this video Siraj, I really enjoy that it doesn't have as many cuts as usual

  • @epicniagarer8040
    @epicniagarer8040 7 ปีที่แล้ว

    Great video! But this has a huge impact on self driving cars, right? Or is there already a better way to identify objects in real time? And the yolo concept is usable on 3D models, isn't it? It would make it way better, I think.

  • @barlospalos3780
    @barlospalos3780 4 ปีที่แล้ว

    Hello Siraj, does YOLO works on TensorFlow 2.0 too?

  • @011azr
    @011azr 7 ปีที่แล้ว

    You know what? I'm a master student but I keep watching your video. I know it's embarrassing but I don't care, lol xD. You don't need a PhD to be an expert in this field. I'm looking forward for your groundbreaking world-changing publication and contribution on deep learning xD. Wait, you've changed the world by teaching the world from TH-cam! Thanks anyway for all of your videos

  • @mbuurmei
    @mbuurmei 6 ปีที่แล้ว

    Great explanation Siraj. This was a very quick way to get an overview in object detection algorithms. Gotta start a project with Yolo, because hey Yolo.

  • @TiagoRodriguesLisboa
    @TiagoRodriguesLisboa 6 ปีที่แล้ว

    Thank you for the lesson! Very awesome video! Keep going!

  • @benjaminf.3760
    @benjaminf.3760 7 ปีที่แล้ว

    Dude your channel is pure gold

  • @wolfgangneumann6789
    @wolfgangneumann6789 6 ปีที่แล้ว

    Wow - impressive! The technology - but even more the way your way to explain it!!

  • @noone-mc1sw
    @noone-mc1sw 4 ปีที่แล้ว

    THE BEST DESCRIBTION I SAW. REALY NDERSTANDABLE

  • @matthewthehuman1744
    @matthewthehuman1744 5 ปีที่แล้ว

    Fantastic video, ridiculously informative. Thank you!

  • @gmanon1181
    @gmanon1181 4 ปีที่แล้ว

    Waoh, it's like passing from electrical signals to file processing. This is a technology miracle.

  • @user-ym8sp2yi1k
    @user-ym8sp2yi1k 6 ปีที่แล้ว

    I luv your hands-free scrolling in this video

  • @nandfednu3502
    @nandfednu3502 6 ปีที่แล้ว

    you are such an awesome human being Siraj

  • @maryangelica5319
    @maryangelica5319 6 ปีที่แล้ว

    So I have several questions...
    When in the training stage, what kind of data do you feed it? Is it the data that you feed a classifying CNN with labels? Do you need to also feed it bounding boxes? I'm working with data that I have to label from scratch, so I can't really use any of the pre-labeled datasets out there. Setting bounding boxes on training data seems also like it could be really subjective...
    What happens when you have more than one object of the same class? The way he described it, it might just pick out the object with the highest probability, right?

    • @lorforlinux
      @lorforlinux 6 ปีที่แล้ว

      this playlist might help you
      th-cam.com/video/PyjBd7IDYZs/w-d-xo.html

  • @OneNewBoy
    @OneNewBoy 6 ปีที่แล้ว

    Thanks a lot for the cool videos siraj (a fan from Morocco) ;)

  • @karunakarpatel194
    @karunakarpatel194 7 ปีที่แล้ว

    Subscribed with the Notifications on..!! Great stuff dude:)

  • @prezhaven8740
    @prezhaven8740 6 ปีที่แล้ว

    I LOVE THE FUTURE!!! YOU R A ROCKSTAR Siraj!!

  • @tgbaozkn
    @tgbaozkn 4 ปีที่แล้ว

    Thank you sir!! Your pronunciation is very well ,amazing ! I understand without subtitles thank you this informative video and your expression

  • @dpcarlyle
    @dpcarlyle 7 ปีที่แล้ว

    Watching while eating breakfast in Saigon Vietnam....you are amazing...thank you for distilling the steps for how to configure and set up...going to have a lot of fun running g through your example.... :)

  • @marciovenanciobatista
    @marciovenanciobatista 7 ปีที่แล้ว

    Man, this video was so great..and the yolo seems to be very good wth detection...I liked to be aware of it , thanks for sharing. Cheers and keep going. Brazil is watching..

  • @vijayabhaskar-j
    @vijayabhaskar-j 7 ปีที่แล้ว

    I was about to do my assignment on YOLO on Deep Learning Specialization by Andrew Ng, and this pops out right on time!

  • @nastaranradmehr3839
    @nastaranradmehr3839 6 ปีที่แล้ว

    Great video! I am waiting to see more videos related to YOLO. I have a question. I was wondering if you could help me. I wanted to buy a laptop. which NVIDIA GPU is suitable for running YOLO?

  • @sramctc
    @sramctc 6 ปีที่แล้ว

    Needless to say, subscribe at once, a very clear and useful presentation.

  • @ashugulati2177
    @ashugulati2177 5 ปีที่แล้ว +1

    Can we use YOLO for food detection or should we prefer some other model?

  • @John-hv2sw
    @John-hv2sw 7 ปีที่แล้ว

    Hi Siraj, I'm just getting into AI, your presentation is great, very well explained!

  • @albin6382
    @albin6382 4 ปีที่แล้ว +2

    3:59 Isn't the mathematical definition of gradient the original meaning and the backpropagation stuff something else that later on got the name? en.wikipedia.org/wiki/Gradient