Thank you, very good overview. You must be having thorough understanding of many object detection models to deliver this kind of overview. I have one question (only for discussion): How it is "clear" (1:22) that object detection is difficult task for machines? I think it is important to mention why the problem is difficult (challenges) to solve from computer vision point of view. You did mention a couple of challenges at 10:40 but these are w.r.to DL approach.
Difficult if you compare it to classification problem. Where an image either belongs to class 1 or classes x. I called it difficult because of 3 reasons - you have to do localization and classification and the fact that the number of objects are variable.
I am writing a report where I need to explain how object detection and then specifically how Yolo architecture works; can you please give me the references you used to make the videos because your explanation is very clear, and I would like to use the same resources as you.
If you really want to understand then debug the code of an existing open source repository. You may not be able to understand portion of code as even though the author of code is a brilliant/smart guy he/she may not be a good programmer (as is the norm in ML community). Ask your questions in issues etc or just debug it. That is the best way of learning!
Getting to see new content and learn from your videos is like waiting for the release of a blockbuster film.. Really hyped for this series of yours..
🙏
Actually pretty good introductionary video, much better than other videos that has hundreds of thousands of views
🙏
Very articulated explanations, really appreciate it! thanks!
You are back!!!!!!!!!!!!!!
😃 I never left! .... but I know I have not been good at making and publishing consistently; hoping to do a better job this time around!
@@KapilSachdeva In that case, I'm happy to have you again.
Exactly what I was looking for, thank you!
Thank you, very good overview. You must be having thorough understanding of many object detection models to deliver this kind of overview.
I have one question (only for discussion):
How it is "clear" (1:22) that object detection is difficult task for machines?
I think it is important to mention why the problem is difficult (challenges) to solve from computer vision point of view.
You did mention a couple of challenges at 10:40 but these are w.r.to DL approach.
Difficult if you compare it to classification problem. Where an image either belongs to class 1 or classes x. I called it difficult because of 3 reasons - you have to do localization and classification and the fact that the number of objects are variable.
Awesome + Quality Video!!
🙏
Well explained.
Very good video, thank you !
🙏
I am writing a report where I need to explain how object detection and then specifically how Yolo architecture works; can you please give me the references you used to make the videos because your explanation is very clear, and I would like to use the same resources as you.
If you really want to understand then debug the code of an existing open source repository. You may not be able to understand portion of code as even though the author of code is a brilliant/smart guy he/she may not be a good programmer (as is the norm in ML community). Ask your questions in issues etc or just debug it.
That is the best way of learning!
Excellent
thank you for explaining this !
🙏
this is so good
🙏
very close to represent the whole story~
🙏
the CV model has detected a good boi
awesome !
🙏
You are seriously biased about Fast RNN (similar) - the Neck is not a neural network if you train EfficientDet X (The best one)
Most of the new architectures in OD have neck but of course it is not mandatory