Check our Deep Learning Course (in PyTorch) with Latest, Industry Relevant Content: tinyurl.com/4p9vmmds Check out our premium machine learning course with 2 Industry projects: codebasics.io/courses/machine-learning-for-data-science-beginners-to-advanced
Such a great communication happening in this video. The awareness of your audience at 8:15 is amazing. While it's true that "communication is what the listener does", to be a communicator, you must have empathy. Be proud of yourself for this.
What an awesome video! You really know how a student thinks. You answered all my questions - even the ones that I didn't realize I had! This was some excellent video format and pacing. I have liked and subscribed.
4 роки тому+23
please make a full project on this from code to deploying
Awesome work Sir, You explain such complicated things in a way, it feels like cakewalk to understand. Thanks alot . Please make full python yolo implementation for video inputs.
At 6:48 - Bh seems correct (1.3), but why is Bw=2? If Bw is the proportion of the grid cell's width, it looks like it should be ~1.5. At 7:28 - Here the dimensions seem like they should be Bw=2, and Bh=1.7, but they are shown in the vector as Bw=3 and By=2. Am I missing something, or are these meant to just be rough estimates for the demo?
thank you sir .. you have explained the content in very good manner. . with coding from scratch and i like it ... have a very nice moring..and many many best wishes from me to you !
sir i saw this video many times but i cant understand one point i.e iou and max probablity both are same what is the diffrence betwwen these 2 both give the same result
I honestly don't get the IOU, but the max propability, just selects he bounding box with highest confidence threshold. Propabbly not elevant anwser after 3 years but maybe someone finds it helpful xd
Thank you so much for creating this video! You really explained everything clearly. I was looking for an explanation about YOLO on other platforms but no one could explain this as clearly as you have. May I ask if I can translate your video into Chinese and share it on a Chinese video platform for all the people who are interested in learning YOLO but failed to find an excellent video like this one? Really appreciate your effort in making this video.
Hi sir i have a doubt. You explained that the grid is considered to have an object only if the center of the bounding box is in that grid.But how do we find the boundung box and center, then?
Doubt : after the model predictions non maximum suppression happens with respect to each grid (which is 4*4 here) IOU with predicted boxes... maximum prediction maintained..right
The issue is that in multiple image classification, you assumed the center of the two objects (human and dog) as given. However, if I am correct, based on what you mentioned prior this point in the video, their center can be calculated after they are detected! Isn't this create a loop?
I think center information is only provided during the training when we have the ground truth. During inference, model just predicts the bounding boxes
Thank you for the practical tutorials.🙏🙏🙏 I have the following questions: Can we use the saved weights from YOLOv7 instance segmentation for a classification problem? We have a binary classification problem with 500 images, one class having only 30 images and the rest belonging to the other class. Can we extract features using instance segmentation on the images with fewer samples and then use all the features for classification?
Check our Deep Learning Course (in PyTorch) with Latest, Industry Relevant Content: tinyurl.com/4p9vmmds
Check out our premium machine learning course with 2 Industry projects: codebasics.io/courses/machine-learning-for-data-science-beginners-to-advanced
Gyyiwygoyswyywoywiywowhiywiwiyiywgoywwoywiywoykgoywiwyoogwiygowiowgowowoiwgowyiwieyieiwiwyoywowyogiigwoyeiwyiwoywiksowwiiewyiyiywwiieiwiwiywiyigywiwiiwykwiyiwgwoywiuwiyeiwyowyiwyywiowiigeiyewiowiiywoywwowkiywiwwgoyswiywoywgkieiiiioiegkiywièiegèwwwwwwwewèwywgywywwygwyywwgywywegwywwgywwwwwgywywwywwywywwtwgywywywywwwgywewwwgywywwgyweyiwygwywywywgwwywgygywyggwywywwgwywygyygwgwwywygywygwwygyeyweyjywwwywywygwgwwywwywwweygywywyywwwygwywywywgy1wgywwywwywywywgywwtgywygwgeywwyywggyhgyihŵyhyygg 4:01 gyhiyirgi 4:03 yi 4:04 ooyhi 4:06 fhi 4:07 hriygghihyyiiẁggygggwigyyyyoywyywowyiwiwwwygywiyeh 4:29 88upg80😂uf
Among all the yolov explaining videos this one makes the most sense! Thanks
My Deep Learning teacher couldn't explain this in 3 weeks the same way you did in 16 minutes, thank you very much.
so true
I think you didn't concentrate to your teacher lecture like you did in this video
@@Abraham33286yes..
Inki mind class me present rhti nhi hai.
Yaha akele dekh rha hai n.
To islie samjh gya 😂😂
Such a perfect introduction to YOLO. Thanks!
The best explanation for YOLO! It's really helpful. Thank you.
I watched a hour long video earlier and understood nothing, and now in just 16 min, I understood everything. Thanks a lot!
Glad you enjoyed it.
Beginners Deep learning playlist: ua-cam.com/play/PLeo1K3hjS3uu7CxAacxVndI4bE_o3BDtO.html
Beginners Machine learning playlist: ua-cam.com/play/PLeo1K3hjS3uvCeTYTeyfe0-rN5r8zn9rw.html
Data science 6 months learning roadmap: ua-cam.com/video/H4YcqULY1-Q/v-deo.html
This is the best explanation that I have not seen any where
Only once I watched and got knowledge on yolo
Thank you so much for this knowledge sharing
I really like your style of explanation. It's very clear and informative.
Glad it was helpful!
Perfect and Clear Introduction to YOLO
Glad it was helpful!
Such a great communication happening in this video. The awareness of your audience at 8:15 is amazing. While it's true that "communication is what the listener does", to be a communicator, you must have empathy. Be proud of yourself for this.
My God which kind of perfect explanation is this wow I don’t what to say bro just God bless you
Yes.. there is no details about network!, its only about box encoding
I used YOLO before I understood what it was, thank you for helping me understand how YOLO works
thanks mate, went through a couple of videos and your's the one that explain it the best
The amount of good information and dogs in this video make me happy :)
What an awesome video! You really know how a student thinks. You answered all my questions - even the ones that I didn't realize I had! This was some excellent video format and pacing. I have liked and subscribed.
please make a full project on this from code to deploying
At 7:28, that looks more like 2 x the width of the grid cell. Why is it 3?
excelente tutorial
You clear the concept in 16 min thanks bro..
man, this was such a good explanation to YOLO!
Awesome work Sir, You explain such complicated things in a way, it feels like cakewalk to understand. Thanks alot . Please make full python yolo implementation for video inputs.
the best explanation honestly you are a master
Best explanation till date
Excellent introduction to YOLO. Looking forward for code deployment video
Brilliant explanation, thank you so much!
I am new to ML but still i understand what you have said bout YOLO great work
You are really awesome, explained it clearly
The best Explanation of Yolo thank you very much
I like this video very much. You explained the working of YOLO very simple , crystal and clear way. Thank you very much. Expect more.
well worth watching. thanks for this. i had to pause where you said to as well. then I got it.
Glad it was helpful!
it my first time around and i have already got a good level on YOLO...thanks for explanation///
תודה!
At 6:48 - Bh seems correct (1.3), but why is Bw=2? If Bw is the proportion of the grid cell's width, it looks like it should be ~1.5.
At 7:28 - Here the dimensions seem like they should be Bw=2, and Bh=1.7, but they are shown in the vector as Bw=3 and By=2.
Am I missing something, or are these meant to just be rough estimates for the demo?
I agree - that really putted me off, lol
Thank you very much sir !!! Egarly waiting for next part
thank you for the presentation, it is easier for me to understand compared to the paper
Yeah! Very clear explanation.
Glad it was helpful!
11:22 IOU was performed over a pair of rectangles. How do you know which one of the two to "discard"? It is not clear at all.
Basically, you use Yolo non-max suppression for that. It discards values not meeting threshold and other criteria.
This was amazing! love it
I like it bro clear and simple explanations
thank you sir .. you have explained the content in very good manner. . with coding from scratch and i like it ... have a very nice moring..and many many best wishes from me to you !
Glad I watched ur video ❤❤❤
Sir your explanation is amazing in the field of data science
Very nice, excellent description. Thank you!
Thanks for sharing your knowledge
best explanation... you are doing a great job.
Nice work. You deserve more than one upvote. Sadly I can only give one.
Thank you alot this explanation is all i ever needed
Every software engineers should subscribe this best channel omg you are just fire 🔥 wow
Waiting for more videos on yolo👏👏
yup next one will cover coding part
This video was fantastic. Thank you
Great explaination of NMS.
Glad it was helpful!
Helpful. Nice work. Thank you so much.
Glad it was helpful!
Cool explanation, thanks!!
1:40 Why do we need Pc anyway when it is completely depend on C1 and C2? What's the point of probability when it can only be 0 or 1?
Great explanation of YOLO. And I need to say thank you for all your tutorials. I learnt a lot from you. Keep it up!
sir i saw this video many times but i cant understand one point i.e iou and max probablity both are same what is the diffrence betwwen these 2 both give the same result
he says at the beginning that prob isn't taken into account... and at last he says it is the criteria... so I'm confused!!!
I honestly don't get the IOU, but the max propability, just selects he bounding box with highest confidence threshold. Propabbly not elevant anwser after 3 years but maybe someone finds it helpful xd
Really good explanation. I just have one doubt. How are bounding box measures calculated in yolo algo?
yes, it is the million dollar question :)
Excellent 👍
Thank you so much for creating this video! You really explained everything clearly. I was looking for an explanation about YOLO on other platforms but no one could explain this as clearly as you have. May I ask if I can translate your video into Chinese and share it on a Chinese video platform for all the people who are interested in learning YOLO but failed to find an excellent video like this one? Really appreciate your effort in making this video.
you made our life easier
Exceptional.
Good Video. However, I still have no idea how CNN can handle multiple anchors. Is there any paper that illustrates this technique?
Thankyou Sir that was a very good and simple explanation of a complex algorithm :) Thankyousomuch sir
The best video!!
Excellent explanation
amazing content and good explanation
thank you so much for this, very easy to understand !
Tks a lot sir, perfect explanation....
Amazing as always! Thank you for providing this information and helping unravel important topics
Nice explanation!
Glad it was helpful!
Amazing explanation as always..
great video.. salute !
احسنت الشرح والتفصيل شكرا لك
Nicely explained everything Thank you sir
Hi sir i have a doubt. You explained that the grid is considered to have an object only if the center of the bounding box is in that grid.But how do we find the boundung box and center, then?
Great video!
Great Explanation. Thank you
Thanks for the explanation. It's help me alot to understand yolo 👍
Great explainaition
Best explanation
Brilliant!!!!!!!!!
I really loved this video! Thank you!
Doubt : after the model predictions non maximum suppression happens with respect to each grid (which is 4*4 here) IOU with predicted boxes... maximum prediction maintained..right
The issue is that in multiple image classification, you assumed the center of the two objects (human and dog) as given. However, if I am correct, based on what you mentioned prior this point in the video, their center can be calculated after they are detected! Isn't this create a loop?
I think center information is only provided during the training when we have the ground truth. During inference, model just predicts the bounding boxes
wonderful video very informative
Great Sir
Sir
The explanation was very clear
And can I get the ppt that you used in the explanation
Thanks in advance
very nice explanation , btw either it will help to detect either brand logo is fake or not?
Thank you 😇
Nicely explain
Is it possible to use it for regression and not clasification?
Splendid!
Today's best face detection algorithm?yoko also used in face detection?
Can I give same image multiple times when train the model ?
What if we want to detect am object when the Input given is a video? How to determine the bounding box location because the object itself is moving,
Great explanation
Thank you for the practical tutorials.🙏🙏🙏
I have the following questions:
Can we use the saved weights from YOLOv7 instance segmentation for a classification problem?
We have a binary classification problem with 500 images, one class having only 30 images and the rest belonging to the other class. Can we extract features using instance segmentation on the images with fewer samples and then use all the features for classification?
Thanks, it's an excellent explanation, just what I needed.
Excellent explanation, you teach these topics in such a way that even a layman can understand