Валентин Сичкар
Валентин Сичкар
  • 10
  • 107 928
Практический YOLO курс - настрой, обучи, тестируй
В YOLO курсе на практике изучаются навыки запуска обучения YOLO на подготовленном наборе данных: stepik.org/a/202357
Переглядів: 29

Відео

Несколько слов обо мне
Переглядів 568 місяців тому
Несколько слов обо мне
What is YOLO format?
Переглядів 320Рік тому
Join the course! Get and enjoy new Yolo v5 skills: www.udemy.com/course/yolo-v5-label-train-and-test/?referralCode=2171545772F09930296E Questions that are opened: What is YOLO format? What is inside txt file? X & Y axes, coordinates of the object.
Track movement of the object via Convolution
Переглядів 4073 роки тому
Design your own deep CNN, convolutional neural network here: www.udemy.com/course/convolutional-neural-networks-for-image-classification/?referralCode=12EE0D74A405BF4DDE9B Related ipynb code file: www.kaggle.com/valentynsichkar/track-object-via-convolution-in-real-time Related py code file: github.com/sichkar-valentyn/Track-object-via-convolution-in-Real-Time
Convolution in Real Time by camera
Переглядів 4933 роки тому
Design your own deep CNN, convolutional neural network here: www.udemy.com/course/convolutional-neural-networks-for-image-classification/?referralCode=12EE0D74A405BF4DDE9B Related ipynb code file : www.kaggle.com/valentynsichkar/convolution-in-real-time-by-camera Related py code file: github.com/sichkar-valentyn/Convolution-in-Real-Time-by-camera
Confusion Matrix Explained
Переглядів 8363 роки тому
Design your own deep CNN, convolutional neural network here: www.udemy.com/course/convolutional-neural-networks-for-image-classification/?referralCode=12EE0D74A405BF4DDE9B Related code for Confusion Matrix is here: www.kaggle.com/valentynsichkar/confusion-matrix-for-image-classification What does Confusion Matrix show? How to distinguish True Positive & False Positive? What is the difference be...
Introduction into YOLO v3
Переглядів 101 тис.4 роки тому
Train your own detector by YOLO v3-v4 here: www.udemy.com/course/training-yolo-v3-for-objects-detection-with-custom-data/?referralCode=A283956A57327E37DDAD Content of the brief introduction lecture into YOLO version 3: Architecture of YOLO v3; Detections at 3 Scales; Detection Kernels; Grid Cells; Anchor Boxes; Predicted Bounding Boxes; Objectness Score. How to train custom object detector with...
YOLO v3 Detects Traffic Signs
Переглядів 1,4 тис.4 роки тому
Detect Traffic Signs by training custom YOLO v3 model. Join the course here: www.udemy.com/course/training-yolo-v3-for-objects-detection-with-custom-data/?referralCode=A283956A57327E37DDAD Following categories used for detection of Traffic Sings by YOLO v3: prohibitory, danger, mandatory, other.
Real Time Traffic Signs Recognition by YOLO v3
Переглядів 2,6 тис.4 роки тому
Train detector to use it on image, video and in real-time. Join YOLO course here: www.udemy.com/course/training-yolo-v3-for-objects-detection-with-custom-data/?referralCode=A283956A57327E37DDAD Detections of Traffic Sins among four categories: prohibitory, danger, mandatory and other. Trained model can be used with OpenCV.
Traffic Signs Detector based on YOLO v3 Algorithm
Переглядів 1,1 тис.4 роки тому
Build your own detector by labelling, training and testing on image, video and in real time with camera. Join here: www.udemy.com/course/training-yolo-v3-for-objects-detection-with-custom-data/?referralCode=A283956A57327E37DDAD Traffic Sings in this Dataset are grouped into four categories: prohibitory, danger, mandatory, other. Training YOLO v3 for Objects Detection with Custom Data. Explore d...

КОМЕНТАРІ

  • @rishabhgupta734
    @rishabhgupta734 2 роки тому

    One question, is ground truth bounding box and anchor boxes used here interchangeably?

  • @pulkitverma1507
    @pulkitverma1507 2 роки тому

    Very helpful thanks!

  • @seolakim5667
    @seolakim5667 2 роки тому

    Thank you so much for this amazing video. Just one question : at 23:58 , why would you define the "t_0" inside the sigmoid? In the loss function of Yolo v3 they directly use p_0 so I would like to know why! Is this just to make sure that the p_0 is between 0 and 1? Does this t_0 appear somewhere in the model when we implement it? Thanks in advance to anyone who would reply :)

  • @Can-ue7de
    @Can-ue7de 2 роки тому

    Amazing Explanation of Yolo v3. Thank you very much.

  • @sekharbabu8498
    @sekharbabu8498 2 роки тому

    Good explanation. Thank you sir

  • @bharathnvadla
    @bharathnvadla 2 роки тому

    Hi Thank you for the explanation ,I have one question, How is the Objectiveness score calculated during the inference ? There is no groundtruth to refer to, on what basis the objectiveness score is measured ?

  • @tellmebaby183
    @tellmebaby183 3 роки тому

    this is deep and fantastic, i call for vodka shots

  • @sameershaik7250
    @sameershaik7250 3 роки тому

    Explained very well.... great

  • @Илья96-с7б
    @Илья96-с7б 3 роки тому

    Топчик просто. Сразу всё понятно стало. Стало хоть ясно, что за якоря такие

  • @ahhhwhysocute
    @ahhhwhysocute 3 роки тому

    Amazing explanation !! Thank you

  • @mainulalam7767
    @mainulalam7767 3 роки тому

    Thank you for this super explanation. I have a question regarding the objectness score. As you explained mathematically : P0 = sigmoid ( to) = P(object) * IoU -> my question is how we obtain this "P(object)" - predicted probability ? Thanks in advance for your support ..

    • @bharath5666
      @bharath5666 3 роки тому

      yes,it is predicted probability by the network.

    • @jessmendoza1483
      @jessmendoza1483 2 роки тому

      @@bharath5666 can i find how does the network predices P(object), but like mathematically or somewhere in the code?

  • @kyawnaingwin8300
    @kyawnaingwin8300 3 роки тому

    Should the input image for detection be same size as training images used in model fitting? Or how big is an input image size ok?

    • @valentynsichkar
      @valentynsichkar 3 роки тому

      Hello there, There is no need to resize images before training or testing after training. The framework (e.g. the one on GitHub framework for YOLO) will take care of resizing. Moreover, separate images, both for training and testing, can be also of different dimensions.

    • @kyawnaingwin8300
      @kyawnaingwin8300 3 роки тому

      @@valentynsichkar thanks for reply. In my case my test image is 20,000 x 20,000 size (drone photo mosaic) and model cannot detect. Only when I split the input image as tiles of same size of training images, it work. According to you, I think I can make bigger tiles for detection but just want to know the limit of input size.

  • @erack1
    @erack1 3 роки тому

    New to machine learning and I'm wanting to create an object detection for video games. What are some good resources to start learning, I know the basics essentially of neural networks and their functions. I've bought your course and will be starting to learn that.

  • @muhammadjamil8171
    @muhammadjamil8171 3 роки тому

    Great content 😊 Thanks Sir !

  • @zubairsk1624
    @zubairsk1624 3 роки тому

    hello dear i hope you are okay i want to ask you few questions 1- can i apply some edit on yolo equation to get better detection 2- can you recommend me some videos that explain every thing about YOLOv4 3- how can i write these equations in python? i hope you answer me thank you

    • @jessmendoza1483
      @jessmendoza1483 2 роки тому

      i've read some articles where they improve yolov3 by adding an equation, you should search some, maybe it could help you

  • @abdulwarissherzad9914
    @abdulwarissherzad9914 3 роки тому

    Nice, can we use it for YOLO object detector? If not or yes what is the reasons. Thank you ...

    • @valentynsichkar
      @valentynsichkar 3 роки тому

      Hello there! The Confusion Matrix displays mis-Classifications among classes. Any detection algorithm, after locating object on the image, has classification phase. Therefore, Confusion Matrix also can be build at this particular stage. The other case can be when ensemble of NNs are applied, e.g., one for detection and another for final classification.

    • @abdulwarissherzad9914
      @abdulwarissherzad9914 3 роки тому

      @@valentynsichkar Thank you for your prompt reply, I have already watched your previous video about the explanation of YOLOv3, so YOLOv3 or YOLOv4 when we run the mAP command line, it just calculate the TP and FP condition not another condition like TN, and FN, but at all it doesn’t have TN. How to calculate the confusion table without these four conditions, which we don’t have in YOLO value for this four condition. But these four conditions are important to have them exactly for each class that you want to classify and adding the value to confusion matrix.

    • @valentynsichkar
      @valentynsichkar 3 роки тому

      Yes, there are tools to help to calculate different metrics for YOLO, including Confusion Matrix. Have a look on GitHub by following keywords: "confusion matrix YOLO". Another one with more results: "YOLO metrics".

    • @abdulwarissherzad9914
      @abdulwarissherzad9914 3 роки тому

      @@valentynsichkar Thank you, the references were great, but I want to find out for "YOLOv4 custom object detector" a proper source code to count and print confusion matrix. Those references are for the coco dataset which is already trained by YOLOs authors. would you like to make a video for YOLO and SSD object detector about its mAP and Confusion matrix, because in recent years these two object detection algorithms have become popular.

    • @valentynsichkar
      @valentynsichkar 3 роки тому

      Thank you for the suggestion. I'll think about creating separate video lecture on how to compute Confusion Matrix for YOLO.

  • @glowwell4292
    @glowwell4292 3 роки тому

    Thanks a lot. Explained neatly. Please make videos on V4 and V5 too.

  • @mohssineserraji1098
    @mohssineserraji1098 3 роки тому

    Great presentation

  • @sachinbharadwajm2120
    @sachinbharadwajm2120 3 роки тому

    great explanation & presentation!!!

  • @syafiqbasri8789
    @syafiqbasri8789 3 роки тому

    thank you so much sir.Its very useful and great explanation!

  • @listenbyheart5552
    @listenbyheart5552 3 роки тому

    really awesome explanation it was! thanks a lot

  • @apurbaroy8411
    @apurbaroy8411 3 роки тому

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

  • @SM--wb4vg
    @SM--wb4vg 3 роки тому

    Very well explained

  • @Alpha-hj2ss
    @Alpha-hj2ss 3 роки тому

    Great Video! Can you please come with more videos

  • @shannondoyle5143
    @shannondoyle5143 3 роки тому

    Really great detailed explanation. I don't get exactly what the ground truth values are determined for grid cells close to the centre grid cell of an object. Would you be able to explain this ?

  • @sumitbali9194
    @sumitbali9194 3 роки тому

    I have seen lot of videos on CNN, mostly crap. But your video is a gem. Appreciate the effort you have put into making this video. Diagrams are a great help in understanding the architecture. Thanks again

  • @pascalschluchter209
    @pascalschluchter209 3 роки тому

    Hey, can someone explain to me, why the detection is happening in Layer 82, 94 and 106. Is there any mathmatical background or is it like a fix parameter of YOLOv3?

  • @m5a1stuart83
    @m5a1stuart83 3 роки тому

    I was code in YoloV3 from Indian UA-camr, and now here I am learning the true nature of Yolo. It helps alot for this OCR Project where I can ignore the image that did not intended to be uploaded to Server.

  • @rlb5261
    @rlb5261 3 роки тому

    Thank. It is excellent!

  • @fatiah541
    @fatiah541 3 роки тому

    Thanks 🌹🌹🌹🌹

  • @fatiah541
    @fatiah541 3 роки тому

    🍀🍀🍀🍀🍀🇮🇶

  • @adithyanarayan9976
    @adithyanarayan9976 3 роки тому

    Spent multiple hours trying to read through various papers in order to understand some of the topics. Should've stumbled upon your channel and the video much earlier. Love the fact that everything is explained to the point. You've earned yourself a subscriber in me. Can't stress this enough, but please put out more videos like these, along the lines of Computer Vision. Well done mate and once again, THANK YOU SO MUCH!

  • @Stilbrech3rin
    @Stilbrech3rin 3 роки тому

    I can just follow the others. This video is very helpful. Did you publish a paper? I would like to cite you for my project.

  • @abdshomad
    @abdshomad 3 роки тому

    ~ Timeline for watching again later ~ 00:01 Intro 01:17 What is YOLO? 03:13 Architecture of YOLO v3 05:28 Input 07:27 Detections at 3 Scales 09:28 Detection Kernels 12:02 Grid Cells 14:23 Anchor Boxes 18:25 Predicted Bounding Boxes 21:41 Objectness Score Conclusion

  • @bakervhaigaming9746
    @bakervhaigaming9746 3 роки тому

    I regret why I haven't found this gem earlier! I had to go through 5-6 papers and hours of reading to understand these topics but your video made it very clear and specific. Please make more quality content like this. Thanks a lot.

  • @iProFIFA
    @iProFIFA 3 роки тому

    Legitmely the clearest video I could find on this topic, amazing! Thanks a lot and keep up the great work Valentyn! :-)

  • @shubhanubanerjee2098
    @shubhanubanerjee2098 3 роки тому

    Can you please make a video on darknet53.conv.74 model ....

  • @azmyin
    @azmyin 3 роки тому

    This is one of the simplest and most articulated explanation of YOLOv3. Thank you very much for this video and please keep up the good work.

  • @kondurusrikanth7620
    @kondurusrikanth7620 3 роки тому

    nice explaination

  • @mitultandon5227
    @mitultandon5227 4 роки тому

    one of the best explanations of YOLO!

  • @fujiawang4326
    @fujiawang4326 4 роки тому

    very well explained

  • @aasishkc1799
    @aasishkc1799 4 роки тому

    Well explained 👍

  • @naufalramadhani9166
    @naufalramadhani9166 4 роки тому

    thank you for thorough explanation sir, much appreciated it, keep it this way it is great.. cheers sir

  • @hanglethithu2873
    @hanglethithu2873 4 роки тому

    Great. Thank you, it helps me a lot!

  • @shubhanubanerjee2098
    @shubhanubanerjee2098 4 роки тому

    Thank you very helpful . Can you make a series on deep learning please ?

    • @valentynsichkar
      @valentynsichkar 4 роки тому

      Thanks for the feedback! For sure, will do!

  • @travel7517
    @travel7517 4 роки тому

    Nicely explained

  • @mmshafique8491
    @mmshafique8491 4 роки тому

    hats off sir. thank you very much for such a nice briefing.

  • @akhilraj2091
    @akhilraj2091 4 роки тому

    great video, thanks for this..

  • @hima-220
    @hima-220 4 роки тому

    This video really contains the details of yolov3! It helps me a lot! Thx!

  • @fadouaamraniidrissi819
    @fadouaamraniidrissi819 4 роки тому

    thank you