Although it wasn’t showed in the video, the top of the screen is what percentage of the item fills the frame. He is getting 91% from the number at the bottom of the screen where you can see the console. It is a bit cropped but you can see 91 then quickly changes to 90. Mostly his fault for not showing the correct percentage more.
@@ImStveLlol don’t know what you’re smoking. The screen is displaying 1 result, and the bottom is displaying 1 result when the program in his full video is classifying every frame. Not sure what drugs the video maker is doing to say 91% though, when that was the maximum result. The classifier was hovering around 70% most the time as electric guitar
Image recognition can be classified as a lazy learning algorithm. It takes a fast gpu and lots of ram to train, but after the model has been trained, the usage is very lightweight.
All of this hardware is almost half a decade old now and you need to run an old version of tflite to guarantee models run mostly on the TPU as most modern architectures including any form of transformer are completely unsupported.
@@Puppy__Nietzsche I mean sure, BUT.. your iPhone 10/"X" had a dedicated AI algorithm-crunching chip in it's very powerful (at the time) A11 processor. A Raspberry Pi is (supposed to be, if they weren't scalped constantly) a $35 SBC for hobbyists and students, not a $700-$1000 palm sized supercomputer. The point of this TPU, as he explains in the video, is to make a very cheap computer capable of doing some cool things you'd normally have to buy a much more powerful device for.
@@outbakjakThe Raspberry Pi can already do ~5fps live detection in camera. it ain't good but it's still very usable, especially if you use SSD mobilenet
Image recognition has been possible on low end devices for decades, without using tpus. I remember seeing a face detection python library run perfectly smoot on a rpbi2
You're conflating two things. Face detection and image recognition are very different things. Facial detection is much simpler because we have pattern recognition algorithms that are very generic which have been known for several decades. Old phones had this tech on them. However, looking at a high rez photo of anything and being able to name what object is featured in the photo is a wayyy more complicated problem.
@@TheHanutaXDthis isn’t “ai” either. It’s a machine learning model that has come up with… drum roll… an algorithm. This algorithm happens to be more capable in that it can identify a broader set of objects. But the underlying algorithm is pretty similar to the “decades old” one you knobs are yammering about. So you can save your neck-bearding
@@threepe0 you clearly don't understand what AI is or means. I suggest you do a bit of research before embarrassing yourself any further. ML, especially DL is AI.
I do use ESP32 for ai-on-the-edge project, but it take 5min to process single image. Coral TPU is better for real-time recognition in my frigate NVR (90ms).
Been using Frigate for my CCTV for years with the exact same USB TPU. They have a PCI version too incase you don't want the dongle dangling everywhere. First used it on a Mini PC. Moved to a pi 4 years ago. Recently upgraded to pi5 to run even more along side.
TensorFlow lite has been able to do this on ARM microcontrollers like the pi or even a teensy for years. It works by offloading the training onto a more capable machine so the actual embedded device only needs to be able to execute the output. The Coral is basically only there for the training portion and once that's done, it's kind of unnecessary.
Google's Coral is an Edge TPU. It's a dedicated "low power" device designed for accelerating local ML inferencing. It's not meant for training. A Rasp Pi with TF-lite will do the same thing, but it will be slower and eat more power than a Raspberry Pi with a coral device.
@@anshXRThey can run on a ML based algorithm, but protein folding and weather folding can be run as a raw simulation (MD for Protein folding as an example) which is a very demanding algorithm. ML algorithms learn patterns and utilise them , it's kinda like using approximations. Even raw simulations use approximations, but there are levels of approximations. A low level approximation is highly computationally intensive, but high level approximation like ML easier to compute.
The ones you're used to buying cheap are still available and for similar low price but newer raspberry Pi's have gotten more powerful as well, so like everything else, you have to pay more for the more you're getting, as the hardware increases its capabilities. Raspberry pi is a company has also brought forth a lot of new offerings that are low power and cheaper and not necessarily less powerful than a more expensive pi, depending on the task you want to utilize it for. I think the last one I got was $15 retail to be used for its small form factor and it's dependability for a repetitious task.
So we could use this to scan an fps game for example, highlight enemies and make it so mouse makes subtle move towards it, I could be undetectable in theory because it could be connected via capture card and back to pc as keyboard
I think RPi5 is able to perform realtime object recognition in real time without the help of an external accelerator like this one. So I don't know what is the point of Coral in this case.
I have a slow computer and i'm learning machine learning, no budget for upgrade, can coral tpu enough for me to atleast get a grasp on machine learning fundamentals?
After years of being hit with object detection ads, still have no clue what is it even for. You can buy cameras wth built in object detection, so whats this tpu is ever used for?
This would be very useful if you have Security Cameras connected to it to make sure there's no skunks, raccoons, bears, or mountain Lions in your backyard before leaving your dog out at night to pee!
Security cameras. Feeding description information into a development pipeline to do something more with what the AI recognized. Home automation. Car mods. Entertainment? Games? It's literally up to you to create something cool. This isn't an entertainment product. It's a tool.
Wait, so you are telling me that if I take a rpi zero w 2, or rpi 4, and I design a neural network to recognize a specific animal on a live video feed, I won't be able to without this ?
Yeah-- Try NP-Hard/Complete problems. Such as the The Traveling Salesman Problem, The Knapsack Problem, Boolean Satisfiability Problem, Graph Coloring Problem, Hamiltonian Path Problem, Subset Sum Problem.
cv2 and a good ol' fashion GPU. My 15 year old lenovo can run object detection with no problems. Shit, an android phone can run it. Training the model is what is time and power consuming. As long as the model is trained virtually anything can run it.
I've done this with a plain old pi3, it was slow, about 5fps, but could still identify things. Not smooth but not new and i reckon a pi4 would fair much better
That's awesome man, real time camera recognition will take a step further with this, you don't need a powerful not portable system to that, and thanks for the don't trip hat reference of Mac Miller, love his music.
I am an Android app developer This is being done on smartphones since probably 5+ years (Both Ios and Android) Yes locally on smartphones not cloud. I am talking about complex object detection, not just face detection etc
Hi, Im trying to install pytorch/torch in my raspberry pi 3 Model B+ (For my face recognition project) But it is not installing Can you help me please 🥺 Thanks advance ☺️
Image recognition is absolutely not out of the question on a pi. If you have a trained model, object recognition is relatively light weight. For real world comparison: eufy‘s security cam base station runs on quad-core a55 that is slower and has less ram than most pis. And it does it with 4 cameras streaming simultaneously. You don‘t need a TPU for the trained model.
Hi @DataSlayerMedia, Thanks a lot for sharing the info. currently I am working on a project to develop a prototype for autonomous ground vehicle that can navigate on it's own and make decisions based on real life updates around it. For that I need to deploy image processing in my micro controller so I would appreciate it u can answer these questions 1. which micro controller is best for this ? raspberry pi (or) anything else? ( considering budget as a factor ) 2. once deploying my code to the rasp.... does it need any connection from laptop or can it compute on it's own ? 3. can i use edge impulse for image processing ? if yes then how to get the code in python ? since I am dealing with raspberry pi 4. Any references ?????
So nobody’s gonna talk about 73% barbell and 11% dumbbell?
Lol train that shit!!!
It's a heavy metal guitar.
73 percent weight lifting tool lier
@@tylisirnlier
@@Jblow-u2m agree! Have it no manners, Sir?
9% man not 91%
Although it wasn’t showed in the video, the top of the screen is what percentage of the item fills the frame. He is getting 91% from the number at the bottom of the screen where you can see the console. It is a bit cropped but you can see 91 then quickly changes to 90. Mostly his fault for not showing the correct percentage more.
@@ImStveL He needs to fix that man
No you idiot. 9% of the entire image is the guitar, the bottom says how certain it was!
@@ImStveLlol don’t know what you’re smoking. The screen is displaying 1 result, and the bottom is displaying 1 result when the program in his full video is classifying every frame. Not sure what drugs the video maker is doing to say 91% though, when that was the maximum result. The classifier was hovering around 70% most the time as electric guitar
@@kurtsaidwhathis explanation is also confusing, saying the pre build model is classification when the image clearly show object detection
Image recognition can be classified as a lazy learning algorithm. It takes a fast gpu and lots of ram to train, but after the model has been trained, the usage is very lightweight.
Yes. (Pin this)
All of this hardware is almost half a decade old now and you need to run an old version of tflite to guarantee models run mostly on the TPU as most modern architectures including any form of transformer are completely unsupported.
My iPhone 10 could do this
@@Puppy__Nietzsche I mean sure, BUT.. your iPhone 10/"X" had a dedicated AI algorithm-crunching chip in it's very powerful (at the time) A11 processor. A Raspberry Pi is (supposed to be, if they weren't scalped constantly) a $35 SBC for hobbyists and students, not a $700-$1000 palm sized supercomputer. The point of this TPU, as he explains in the video, is to make a very cheap computer capable of doing some cool things you'd normally have to buy a much more powerful device for.
I know this is old but the coral came out in 2019 that's not a decade I currently use for objects and face detection on a nuc
@@outbakjakThe Raspberry Pi can already do ~5fps live detection in camera. it ain't good but it's still very usable, especially if you use SSD mobilenet
@@Puppy__NietzscheMy S8 could do this lol
Image recognition has been possible on low end devices for decades, without using tpus.
I remember seeing a face detection python library run perfectly smoot on a rpbi2
Face detection does not need to use ai. It is a "solved" Problem there are algorithmus to detect faces that use some special filters.
You're conflating two things. Face detection and image recognition are very different things. Facial detection is much simpler because we have pattern recognition algorithms that are very generic which have been known for several decades. Old phones had this tech on them. However, looking at a high rez photo of anything and being able to name what object is featured in the photo is a wayyy more complicated problem.
I implemented it on a small scale robotic arm on my last year of school. Tiny shit followed you across the room using a raspberry Pi 2
@@TheHanutaXDthis isn’t “ai” either. It’s a machine learning model that has come up with… drum roll… an algorithm. This algorithm happens to be more capable in that it can identify a broader set of objects. But the underlying algorithm is pretty similar to the “decades old” one you knobs are yammering about. So you can save your neck-bearding
@@threepe0 you clearly don't understand what AI is or means. I suggest you do a bit of research before embarrassing yourself any further. ML, especially DL is AI.
You could use YOLO tiny for that. I used in my project and it absolutely ran in raspberry pi itself. You don't need any other devices attached to it
What kind of raspberry did you use? I’m trying to do the same with YOLO Tiny
You totally can but how else are shitty RUclips’s gonna make content?
Ah yes. 73% Barbell.
When his voice started sounding off I thought he was gonna do a reveal where he processed the video off of a raspberry Pi.
i also noticed his voice
Gotta be AI
You can easily run image recognition on an ESP32, i would have loved to see an actual challenge.
oh god
@@realSkyfr oh God what
I do use ESP32 for ai-on-the-edge project, but it take 5min to process single image. Coral TPU is better for real-time recognition in my frigate NVR (90ms).
Been using Frigate for my CCTV for years with the exact same USB TPU. They have a PCI version too incase you don't want the dongle dangling everywhere.
First used it on a Mini PC. Moved to a pi 4 years ago. Recently upgraded to pi5 to run even more along side.
73% barbell🤣🤣🤣
TensorFlow lite has been able to do this on ARM microcontrollers like the pi or even a teensy for years. It works by offloading the training onto a more capable machine so the actual embedded device only needs to be able to execute the output. The Coral is basically only there for the training portion and once that's done, it's kind of unnecessary.
Google's Coral is an Edge TPU. It's a dedicated "low power" device designed for accelerating local ML inferencing. It's not meant for training.
A Rasp Pi with TF-lite will do the same thing, but it will be slower and eat more power than a Raspberry Pi with a coral device.
"I totally understand this code" i can relate 🙂
This is the comment I was lookin for
I would love a longer breakdown of what you did here. I have been considering a hobby project like this one for a while
"the most challenging computation" is not ML... there are many like weather prediction, protein unfolding etc.
protein unfolding and weather prediction also uses lot of machine learning underneath.
@@anshXRThey can run on a ML based algorithm, but protein folding and weather folding can be run as a raw simulation (MD for Protein folding as an example) which is a very demanding algorithm. ML algorithms learn patterns and utilise them , it's kinda like using approximations.
Even raw simulations use approximations, but there are levels of approximations. A low level approximation is highly computationally intensive, but high level approximation like ML easier to compute.
Both of those qualify as ML problems
Protein unfolding? LOL. Folding was solved years ago by AI.
Wow I didn’t realize how expensive Pis had gotten
The ones you're used to buying cheap are still available and for similar low price but newer raspberry Pi's have gotten more powerful as well, so like everything else, you have to pay more for the more you're getting,
as the hardware increases its capabilities.
Raspberry pi is a company has also brought forth a lot of new offerings that are low power and cheaper and not necessarily less powerful than a more expensive pi, depending on the task you want to utilize it for.
I think the last one I got was $15 retail to be used for its small form factor and it's dependability for a repetitious task.
@@JericHouse copy that. thank you for the details.
0.4 fps with coral ?
6 years ago on Raspbery instaled (objects recognition) with camera instant. The software was more old.
but the rz isnt doing the computing?
So we could use this to scan an fps game for example, highlight enemies and make it so mouse makes subtle move towards it, I could be undetectable in theory because it could be connected via capture card and back to pc as keyboard
Object detection is a very small model doesn’t require a lot of compute. It could probably run with out coral on a raspberry pi.
With yolo and cv2 you can also run object detection in videos without google coral on raspberry pi 4 and 3b
Where could I get that?
I think RPi5 is able to perform realtime object recognition in real time without the help of an external accelerator like this one. So I don't know what is the point of Coral in this case.
"I'm sorry, Hal, I can't do that until you shave."
Why did bro alter his voice or use an ai transcript?
I've been using yolov5 on my pi 4 and it has no problem running it
Once you have the edge tpu set up does it require an internet connection to operate?
I have a slow computer and i'm learning machine learning, no budget for upgrade, can coral tpu enough for me to atleast get a grasp on machine learning fundamentals?
If you attached it to a data base of imagery could it identify a person from the list as they walked into the camera ?
Whats the song you use towards the end of the video? Sounds good
Is this different from computer vision?
After years of being hit with object detection ads, still have no clue what is it even for. You can buy cameras wth built in object detection, so whats this tpu is ever used for?
Iicc wasn't there an Android app that did the same thing called "tensorflow"? Or something?
Would you recommend coral tpu still?
how do you know its being used?
thats about the same performance as the pi itself?
I compiled opencv(took almost a whole day) in my pi 3 and its able to do realtime object detection without any tpu
Im curious how well this would work if there was code for it to work like an ASIC and do crypto mining.
This would be very useful if you have Security Cameras connected to it to make sure there's no skunks, raccoons, bears, or mountain Lions in your backyard before leaving your dog out at night to pee!
Spot on "I totally understand this code" 😂👍🏻👍🏻
Is audio was made by ia?
That is honestly so fkin cool they have an AI PU like that.
Everyone knowns calculating digits of pi is the most computational task.
What are the use cases?
Security cameras. Feeding description information into a development pipeline to do something more with what the AI recognized. Home automation. Car mods. Entertainment? Games? It's literally up to you to create something cool. This isn't an entertainment product. It's a tool.
Does it also upload whatever I do to Google?
Wait, so you are telling me that if I take a rpi zero w 2, or rpi 4, and I design a neural network to recognize a specific animal on a live video feed, I won't be able to without this ?
So which AI platform is this based on again??
Didn't someone do something similar with a Nintendo Wii body motion device or the XBox motion device?
RUclipsr try not to use supercomputer incorrectly challenge (very hard)
i took mine to the absolute limits too! i overclocked it to the absolute max, even watercooled it to play proper minecraft on it.
Yeah-- Try NP-Hard/Complete problems. Such as the The Traveling Salesman Problem, The Knapsack Problem, Boolean Satisfiability Problem, Graph Coloring Problem, Hamiltonian Path Problem, Subset Sum Problem.
I subscribed. Although, do you know of any better ai video detection packages or hardware, etc?
cv2 and a good ol' fashion GPU. My 15 year old lenovo can run object detection with no problems. Shit, an android phone can run it. Training the model is what is time and power consuming. As long as the model is trained virtually anything can run it.
amazing video! keep it up
If only the Coral was for sale anywhere (for a normal price).
I've done this with a plain old pi3, it was slow, about 5fps, but could still identify things.
Not smooth but not new and i reckon a pi4 would fair much better
Didn’t this come out like 4 years ago?
Yes
The 3D printer in me saw TPU and just had to see what was going on 🤣
This should make their share price go through the roof!
What’s the music where you inserted code like Usain Bolt? 😂
Coral has been around for years
Jetson nano's filled the rpi form factor machine learning area for a while.
I've seen that thing used in a bunch of videos and never knew what it was. I thought it was some pico/zero or something
So is this just good for image recognition?
Nice PRS!
You should make a magic mirror
The TPU usb accelerator is from 2017
anyone else thought the thumbnail was a hand rolling a joint?
That's awesome man, real time camera recognition will take a step further with this, you don't need a powerful not portable system to that, and thanks for the don't trip hat reference of Mac Miller, love his music.
You can already do this with a standard pi 4, and if you have a basic NVidia LP Graphics Card like the 1650 you can get like 4x more performance
@@SUPABROS 7w from tpu that do the half of 300w graphic card idk seems petty good and Fair
Mac Miller reference with the Don’t Trip hat?
I am an Android app developer
This is being done on smartphones since probably 5+ years (Both Ios and Android)
Yes locally on smartphones not cloud. I am talking about complex object detection, not just face detection etc
Ok but why would you spend 1000 on a phone to use as a security camera? You realize different hardware and formfactors have different use cases yeah?
@@meinbherpieg4723You can do it on a 100 dollar cheap Android phone
my bushitmeter just went off limit. so many things you said are just wrong
That s really good. Add a voice , mutiple cameras . And youd have a amazing aid for blind people . U heard it here first .
Good content man! You just earned a sub
Either way this Tech is really sweet!
This was not released recently. Its a 4 year old product. But its been out of stock forever. Also comes as PCIE card if you want.
Awesome 👌
91% that is definitely a barbell 😂
Hi,
Im trying to install pytorch/torch in my raspberry pi 3 Model B+ (For my face recognition project)
But it is not installing
Can you help me please 🥺
Thanks advance ☺️
this thing does according to the internets 4 tops. there is an ai hat for rpi5, which does 13 / 26 tops!! cost are very close.
First time I've ever seen fractional FPS
Image recognition is absolutely not out of the question on a pi. If you have a trained model, object recognition is relatively light weight. For real world comparison: eufy‘s security cam base station runs on quad-core a55 that is slower and has less ram than most pis. And it does it with 4 cameras streaming simultaneously. You don‘t need a TPU for the trained model.
can it run sdxl
This is only on my feed for the machines to make fun of me because they know I took my life in the wrong direction.
Could I run a cluster of these?
So you can connect this to a drone? then detect firearms, formations, heat signatures, vehicles, and human outlines/silhouette.
If by new you mean at least 8 years old 😂
But did it say “Paul Reed Smith” or “Orange Amplification”?
The product is old came out in March 2019
Ah, a dedicated matrix multiplication calculator
Better than the rabbit r1
Can you train model on it too?
There's dual tpu module for two of em in one
Husky lens video please
Are you using ana ai voice for this video? It sounds... Unnatural.
Got one of these in an m.2 bay in my laptop. 😁👍
I thought Coral had been around for a while
Beware any company that says "we're not evil" before anybody asked.
Hi @DataSlayerMedia, Thanks a lot for sharing the info.
currently I am working on a project to develop a prototype for autonomous ground vehicle that can navigate on it's own and make decisions based on real life updates around it.
For that I need to deploy image processing in my micro controller so I would appreciate it u can answer these questions
1. which micro controller is best for this ? raspberry pi (or) anything else? ( considering budget as a factor )
2. once deploying my code to the rasp.... does it need any connection from laptop or can it compute on it's own ?
3. can i use edge impulse for image processing ? if yes then how to get the code in python ? since I am dealing with raspberry pi
4. Any references ?????
That frame rate tho 🤣
bro tried to deepfake this without us noticing