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?
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?
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.
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
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
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
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
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
![[#2024MAMA] BIGBANG (빅뱅) - 뱅뱅뱅 (BANG BANG BANG) + FANTASTIC BABY | Mnet 241123 방송](http://i.ytimg.com/vi/EQsYfiPR9uM/mqdefault.jpg)
Thanks, sir. Your content helped a lot. Everybody just codes and moves on, but nobody tells how it happens. Thank You
Very lucid explanation and easy to understand. Learned a lot from this video alone, thanks and keep it coming
The best explanation on YOLO so far. Thank you.
Simple, clear and instructible. Perfect to introduce to YOLO. SO GOOD
Amazing video. Thank you for explaining everything in just one video😃
simple and clear easy to comprehend
Perfect and Crisp Explanation!
Amazing explanation with enough time thanks for saving my time
Sir👏, your teaching is just😚
Great Explanation
really good simplification of yolo part1 ..... Thankyou
@Balaji Srinivasan, Sir you explained exactly like Andrew ng in a detailed manner. Happy to come to know about your channel
Thanks balaji. You taught really well. Pls upload more videos. will be more useful
Excellent brother🎉
Thanks much balaji. This will help me in my project preparations!
Thank you 😊
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?
very nicely explained thank you.
Great explanation!
nice explaination..........really good........
Thank you so much. You are a legend!.
Nice introduction, thank you
its is an awesome video and u explained everything quite well. plz make a list of videos about opencv and neural network working.
very well explained
Thnx balaji. Your content is awesome
Thank you
1. how anchor boxes are placed(initially).
2. what is the value of ground truth at the time of inferencing
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.
thanks for this explaintion
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?
Very well explained👌
WELL EXPLAINED...
well explained , thank you much
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.
please i want to know which tensor or vector of the images saved. all I see is the bounding box and classification and probability
great work
Thanks for sharing ❤️
Excelent it really benifical for me Thank you for your guidance
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?
Great explanation thank you 😊
#Subscribed
Must thank you bro❤️
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
Those training data are manually generated by data labellers.
is it for training or identification
Hi Balaji, could you pls upload RCNN and its types. Masked RCNN also?
Sure, will upload them in a few days. Thanks for the suggestion 😊
HI SIR , Excellent Explanation
Thank you 😊
@@BalajiSrinivasan25 Are You From TAMILNADU ...Sir???
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
Is it possible to integrate the YOLO algorithm with arduino or raspberry pi using a webcam?
How program decides that how many Anchor boxes should be present for that particular image ?
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
Bro can you make aa face mask detection and social distancing using yolo
thanks
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
Nanba I'm new subscriber hope you are tamil
A GOD!!
Bro code not working arguments error came
Can someone develop project for my business using YOLO.
glad to do for you!
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
Code run agilla bro ..
Love u 3000
are able to share me slide?
#YOLO
0:27
tytytytytyty