@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.
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 ua-cam.com/video/0X6yTkXn-qQ/v-deo.html
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.
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.
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.
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!
7 років тому+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 !!!
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.
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!
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.
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.
The Magic V, do you want to have a tutorial on Google Speech API, i.e., convert your speech into text! Watch this: ua-cam.com/video/jc_-AIYvfKs/v-deo.html
Gradient from HOG and BackPropagation are the same thing... Is a mathematical value given where a function increase or decrease. So Gradient may be where things get darker (less light), or whether you get less error.
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.
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! :))
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.... :)
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.
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
"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
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
😂😂 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 😤😤😤
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.
would be great to see this from scratch. For ex. I have a live video feed of a concert and I want to classify the guitar the person is using. How would one 1. Set up the environment - don't skip over anything that you think people may know. 2. Train it on a set of images of guitar types to 3. Test the model with some video feeds 4. Then test live
In R-CNN, if we are using CNNs to extract features for the proposed regions then why not use some dense layers for the classification rather than using an SVM? What are the trade-offs?
Thanks, but I still have some questions that i do not understant,. In yolo, where the 13*13*5 bounding box come from? Those are given data?or need to generate randomly?
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
I literally just sat down to do an assignment on this. Siraj, your timing is impeccable
thanks!
@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.
I just liked this comment to bring the total to 69 :D
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
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
ua-cam.com/video/0X6yTkXn-qQ/v-deo.html
You sir, are the reason my company is headed into softwsee development, coding, and programming. This video is worth more than gold.
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.
yeah I was surprised that Siraj didn't know that this was identical to a gradient.
I think he meant the gradients don’t have the same function as they do in backprop, i.e. representing an error value
So pretty much like a vector in physics.
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.
Yes one is gradient as in describing a slope, the other is gradient as in color. I think thats what he means by different :)
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.
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.
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.
Gotta send a link of this to my ex-wife! Maybe she can finally detect that I am a person.
Way to much info to much but it's good your venting.
Never marry a lizard person
haha wow thats real af
#LIZARD PERSON REALLY?/@#
Lol, i wish in future it can detect and read mind
I love this video!
Never expect any but the best from Siraj.
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!
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 !!!
CNN works this time
1- Computation
2- Large Amount of Image available
Waoh, it's like passing from electrical signals to file processing. This is a technology miracle.
It seems that there's a faster algorithm called ssd multibox object detection, even works somewhat fast in android
yes.. ssd is faster than the yolo. and better suit for real-time applications.
@@kevaldholu7366 well yes. But the yolo is more favored because its simplicity than the latter.
Man! You are amazing. your kind of presentation makes me stay completely focused!
This is crazy I graduated back in 2012 and things have changed a lot.
Bro you might not know this...but you're pretty good at this UA-cam thing lol. Thanks man you're the best
The secret is use deeplearning to improve the video
Watch me man!
ua-cam.com/video/jc_-AIYvfKs/v-deo.html
Thanks George lots of practice
teaching is the best way to learn
wahh !!!!! what an explanation man ??? mind blown for 30 mins straight
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.
thanks Carl noted
THE BEST DESCRIBTION I SAW. REALY NDERSTANDABLE
Siraj, can you do a video showing how to install YOLO, please? Thank you so much
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.
@siraj, at 0:50; And we are going to build our own model as well....". But, when did we build our own model???
I was looking for this just a few days ago and was a great coincidence that you decided to upload this video , thanks!!
0:41 i'm still searching for the train!
Dude your channel is pure gold
Anyone got any opinions/warnings regarding YOLOv3? About to start a project and dont wanna make my life more difficult than it already is
Yolo V3 is really simple. I have some experience with it :)
Thanks for your work it is the first time i find proper and clear explanations about how to interpreter the network output.
Oh how I miss 2018 machine learning.
i love how siraj's videos are understandable until the last quarter or so and then it's a freaking downhill
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!
Its been five years. How about now?
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.
That was an excellent description of a topic that has been confusing the heck out of me for many hours. Thank you!
Object detection made easy
plz tell me how to implement this on my Windows PC ..plz tell me some way out for this bro.. ....
Buy a MAC
Bro this isn't a valid solution..
The dark net has also windows version.. but i haven't know complete knowledge to set environment on Windows
Use VoTT and CNTK docs.microsoft.com/en-us/cognitive-toolkit/object-detection-using-faster-r-cnn
Thanks so much for this video Siraj, I really enjoy that it doesn't have as many cuts as usual
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.
Thanks for your work it is the first time I find proper and clear explanations about how to interpret the network output!
I'm a genius now, thx
@Xingming Pinyin this will make you genius, xigishihiwifisidirixieitiyiuiiy
I was about to do my assignment on YOLO on Deep Learning Specialization by Andrew Ng, and this pops out right on time!
I think it's developed by Joseph Redmon ...... YOLO i've seen his TED talk. and also he made it as open source.
Where can I find the documentation of this video on the explanation of object detection history?
Yeeeee I waited for so long for yolo
The Magic V, do you want to have a tutorial on Google Speech API, i.e., convert your speech into text!
Watch this:
ua-cam.com/video/jc_-AIYvfKs/v-deo.html
I LOVE THE FUTURE!!! YOU R A ROCKSTAR Siraj!!
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
you are such an awesome human being Siraj
hi siraj,
when I doing the YOLO I encountered: AssertionError: Over-read tiny-yolo.weights.
the env is win7 and python 3.6.3.
Gradient from HOG and BackPropagation are the same thing... Is a mathematical value given where a function increase or decrease. So Gradient may be where things get darker (less light), or whether you get less error.
wow it detects MP4 recorded files and in "Real Time" cooooool
Any ideas why image jpgs work fine and mp4s don't on my mac?? thanks!
Great Tutorial will train to recognize Students and Faculty and objects like weapons.
"we are going to build"?. i think you used someone else's code. 20 min of explanation and 2 of demonstration ::thinking::
L Lawliet yeah it was done by someone else
ok you can do 20 min of demo and 2 min explanation, but you wont. So why, because never believe in appreciation
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.
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! :))
Cynthia Habonimana will all laugh when theses fuckers of ai learn to code
I luv your hands-free scrolling in this video
From a guy who defined the concept of a "logic door"...
Can YOLO deal with RGB-D data from a Kinect device for example?
sure, as any cnn.
@@GUINTHERKOVALSKI How so? How can i input depth and rgb synced data in a cnn?
@@anarcominhoto concat depth with rgb channels, so that your dim is (width,height,channels)
@@GUINTHERKOVALSKI ok, but can i have a score of class, x,y and 3 bounding boxes parameteres, with that method?
Heads up, version 3 is just out: pjreddie.com/darknet/yolo/
Paper: pjreddie.com/media/files/papers/YOLOv3.pdf
Thank you sir!! Your pronunciation is very well ,amazing ! I understand without subtitles thank you this informative video and your expression
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.
he has a playlist in his youtube page where he shows how it work
See the video quick questions with siraj raval on this channel itself. You will find your answer!
my playlists
I would love to see an updated version of this, Yolo3 is out and doesn't seem to work with this code
YoloV3 is indeed quite robust for common AI-CV applications :).
I thought SSD, faster R-CNN using ResNet, and R-FCN were all more accurate than YOLOv2
you are right yolo is fast but not accurate as other architectures
will look into SSD
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.... :)
Can you show and explain SSD too? :3 I've read it should be faster then YOLO :)
Nope, it's not. YOLOv2 is the fastest object detection out there. Check their comparison here (pjreddie.com/darknet/yolo/ )
will consider ssd
Did you?
This is Brilliant. I'm actually gonna play with it. Thanks Siraj!
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.
great link!
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
Reckless Roges why not both? It's always good to crack the same problem in many ways.
Man, this is one of the best explanation for begginers I ever see !!!!! Very good. Do y have any ML course? I will pay for it.
You're just reading off from a github page that's all and for the implementation part you just flew through it......!!
Still helps.
The important part is it helps.
The reason you are here is also the same.😂
Outstanding explanation and I appreciate the way you presented your project.
Keep illustration
imagine doing this but with capsule !! new project idea !!
sprinkle capsule on everything lol
Thanks for the great explanation. I now understand the significance of YOLO.
nice video, plz make more
It would be great if you could provide reference to the papers that you are using in this lecture.
I made this few months back for my college techfest. checkout this ,it is the one that inspired me> github.com/oarriaga/face_classification
Very good work, I will fork for sure :D
very cool
Will it assume my gender??? omg im getting triggered...
I am glad to hear that :)!
is there any good website where i can find yolo implementation for java?
violo jones uses svm? omg can't you google stuff before you talk?? viola jones are famous for combining cascades of boosted classifiers...
the improved version uses SVM link.springer.com/chapter/10.1007/978-3-642-22822-3_7
"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
It is such a beautiful initiative taken by you to teach the globe about the threshold technologies. Keep the good work up.
Congrats, you know how to copy-paste. But just barely.
Needless to say, subscribe at once, a very clear and useful presentation.
his movements are irretating me :(
Hey dude thanks so much for your lengthy explanations and your enthusiasm when you make your videos. It really helps !
stop objectifying dogs siraj /jk
lmao
lol
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
Could it recognize person in hijab?
You are a GEM!
I did my phd on image segmentation around the turn of the century, and i remember waiting hours to process one image. How far we've come.
😂😂 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 😤😤😤
he spent that time to explain to you in detail what was happening you ingrate
he explained it really well but i agree
Wow! People wanna code without knowing the logic behind the code. What has the world come to? 🙈
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.
Best video yet! I like this lecturer-y style much more, keep it up!
Wow - impressive! The technology - but even more the way your way to explain it!!
Mehn!! you are a great teacher I wish I could subscribe a thousand times. Thank you for this♥️
would be great to see this from scratch. For ex. I have a live video feed of a concert and I want to classify the guitar the person is using. How would one
1. Set up the environment - don't skip over anything that you think people may know.
2. Train it on a set of images of guitar types to
3. Test the model with some video feeds
4. Then test live
Windows environment ?
Awesome video. Time to combine YOLO with my 3d printed Arduino powered robotic arm.
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
Why those energized people first invent then get energized? Reading solved problem gets you excited?
In R-CNN, if we are using CNNs to extract features for the proposed regions then why not use some dense layers for the classification rather than using an SVM? What are the trade-offs?
Siraj! Thank you so much! When you explain step by step like this I can undestand everything! Love this video!
Really amazing explanation!
how does it work? android detection algorithms with yolo
This is really awesome. You explain it in such a clear and simple way.Thank You!!!!.
great video, thorough explanation
can you explain how to build custom object detection using tensorflow
So can YOLO record the position data it finds of the items its tracks so they can be reconstructed in 3D software such as 3ds max in 3D space???? 🤔
Thanks, but I still have some questions that i do not understant,. In yolo, where the 13*13*5 bounding box come from? Those are given data?or need to generate randomly?
I Love all your videos. You are precise, fast, make mountainous task so simple to deal with... Thank.
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
@Siraj what do you mean by a grid cell can predict up to 5 bounding boxes?