Google’s New TPU Turns Raspberry Pi into a Supercomputer!

Поделиться
HTML-код
  • Опубликовано: 21 дек 2024

Комментарии • 341

  • @hitarthmodi3600
    @hitarthmodi3600 11 месяцев назад +1081

    So nobody’s gonna talk about 73% barbell and 11% dumbbell?

    • @Jblow-u2m
      @Jblow-u2m 8 месяцев назад +30

      Lol train that shit!!!

    • @tylisirn
      @tylisirn 6 месяцев назад +54

      It's a heavy metal guitar.

    • @DevilBoss56
      @DevilBoss56 4 месяца назад

      73 percent weight lifting tool lier

    • @DevilBoss56
      @DevilBoss56 4 месяца назад +2

      ​@@tylisirnlier

    • @jesushinojosa5163
      @jesushinojosa5163 2 месяца назад +2

      ​@@Jblow-u2m agree! Have it no manners, Sir?

  • @couchoclocknews
    @couchoclocknews Год назад +2097

    9% man not 91%

    • @ImStveL
      @ImStveL Год назад +273

      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.

    • @couchoclocknews
      @couchoclocknews Год назад +20

      @@ImStveL He needs to fix that man

    • @notarandom7
      @notarandom7 Год назад

      No you idiot. 9% of the entire image is the guitar, the bottom says how certain it was!

    • @kurtsaidwhat
      @kurtsaidwhat Год назад +23

      @@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

    • @hithere1219
      @hithere1219 Год назад +2

      ​@@kurtsaidwhathis explanation is also confusing, saying the pre build model is classification when the image clearly show object detection

  • @marcwmusic3477
    @marcwmusic3477 11 месяцев назад +154

    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.

    • @RazzleBloq
      @RazzleBloq 6 месяцев назад +4

      Yes. (Pin this)

  • @justanotheruseronhere-a
    @justanotheruseronhere-a Год назад +286

    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
      @Puppy__Nietzsche Год назад +1

      My iPhone 10 could do this

    • @outbakjak
      @outbakjak Год назад +30

      ​@@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.

    • @AlmightyKay02
      @AlmightyKay02 Год назад +1

      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

    • @SUPABROS
      @SUPABROS Год назад +4

      ​@@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

    • @club6525
      @club6525 Год назад +1

      ​@@Puppy__NietzscheMy S8 could do this lol

  • @HatTrex
    @HatTrex Год назад +589

    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

    • @TheHanutaXD
      @TheHanutaXD Год назад +17

      Face detection does not need to use ai. It is a "solved" Problem there are algorithmus to detect faces that use some special filters.

    • @Night_Hawk_475
      @Night_Hawk_475 Год назад +28

      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.

    • @mateng7707
      @mateng7707 Год назад +4

      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

    • @threepe0
      @threepe0 Год назад +5

      @@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

    • @poopfartlord9695
      @poopfartlord9695 10 месяцев назад +6

      ​@@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.

  • @tharanitharanm3494
    @tharanitharanm3494 Год назад +26

    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

    • @quintijnkroesbergen5611
      @quintijnkroesbergen5611 9 месяцев назад +1

      What kind of raspberry did you use? I’m trying to do the same with YOLO Tiny

    • @openthinker1251
      @openthinker1251 4 месяца назад +1

      You totally can but how else are shitty RUclips’s gonna make content?

  • @ZeronimeYT
    @ZeronimeYT 3 месяца назад +10

    Ah yes. 73% Barbell.

  • @akbarkhan656
    @akbarkhan656 Год назад +82

    When his voice started sounding off I thought he was gonna do a reveal where he processed the video off of a raspberry Pi.

    • @bongs4921
      @bongs4921 Год назад +3

      i also noticed his voice

    • @Jorghhhh
      @Jorghhhh 11 месяцев назад +3

      Gotta be AI

  • @ALifeLivedFully
    @ALifeLivedFully Год назад +46

    You can easily run image recognition on an ESP32, i would have loved to see an actual challenge.

    • @realSkyfr
      @realSkyfr 4 месяца назад

      oh god

    • @SergieXD
      @SergieXD 4 месяца назад

      ​@@realSkyfr oh God what

    • @dmek24
      @dmek24 3 месяца назад

      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).

  • @Chris173972
    @Chris173972 Год назад +5

    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.

  • @nomad__6
    @nomad__6 Год назад +27

    73% barbell🤣🤣🤣

  • @riverjane1223
    @riverjane1223 Год назад +40

    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.

    • @duffahtolla
      @duffahtolla Год назад +4

      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.

  • @BroBroCoder
    @BroBroCoder Год назад +13

    "I totally understand this code" i can relate 🙂

  • @yewknight
    @yewknight Месяц назад

    I would love a longer breakdown of what you did here. I have been considering a hobby project like this one for a while

  • @mpty2022
    @mpty2022 Год назад +53

    "the most challenging computation" is not ML... there are many like weather prediction, protein unfolding etc.

    • @anshXR
      @anshXR Год назад +3

      protein unfolding and weather prediction also uses lot of machine learning underneath.

    • @mouli570
      @mouli570 Год назад +3

      ​@@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.

    • @christinemurray1444
      @christinemurray1444 9 месяцев назад

      Both of those qualify as ML problems

    • @BeeRich33
      @BeeRich33 21 час назад

      Protein unfolding? LOL. Folding was solved years ago by AI.

  • @JBB685
    @JBB685 8 месяцев назад +6

    Wow I didn’t realize how expensive Pis had gotten

    • @JericHouse
      @JericHouse 5 месяцев назад +1

      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.

    • @JBB685
      @JBB685 5 месяцев назад

      @@JericHouse copy that. thank you for the details.

  • @anantgupta3285
    @anantgupta3285 Месяц назад +1

    0.4 fps with coral ?

  • @Lombardini490
    @Lombardini490 11 месяцев назад +3

    6 years ago on Raspbery instaled (objects recognition) with camera instant. The software was more old.

  • @manxman8008
    @manxman8008 11 месяцев назад

    but the rz isnt doing the computing?

  • @ccyberhub
    @ccyberhub 14 дней назад

    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

  • @efexzium
    @efexzium Месяц назад

    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.

  • @PalusiYt
    @PalusiYt 11 месяцев назад

    With yolo and cv2 you can also run object detection in videos without google coral on raspberry pi 4 and 3b

  • @christianrodriguez3379
    @christianrodriguez3379 20 дней назад +1

    Where could I get that?

  • @marcombo01
    @marcombo01 3 месяца назад +1

    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.

  • @Chris.Brisson
    @Chris.Brisson Год назад +16

    "I'm sorry, Hal, I can't do that until you shave."

  • @Meninem_
    @Meninem_ Год назад +7

    Why did bro alter his voice or use an ai transcript?

  • @rxmxshg9830
    @rxmxshg9830 Год назад +1

    I've been using yolov5 on my pi 4 and it has no problem running it

  • @davidson2727what
    @davidson2727what 3 месяца назад

    Once you have the edge tpu set up does it require an internet connection to operate?

  • @LeoNux-um7tg
    @LeoNux-um7tg Год назад

    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?

  • @adamgrant3086
    @adamgrant3086 6 месяцев назад

    If you attached it to a data base of imagery could it identify a person from the list as they walked into the camera ?

  • @andresalvarez7303
    @andresalvarez7303 Год назад

    Whats the song you use towards the end of the video? Sounds good

  • @supermat1937
    @supermat1937 Год назад

    Is this different from computer vision?

  • @GregMatoga
    @GregMatoga 4 месяца назад

    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?

  • @Nate1994a
    @Nate1994a 4 месяца назад

    Iicc wasn't there an Android app that did the same thing called "tensorflow"? Or something?

  • @bra1nsen
    @bra1nsen Год назад

    Would you recommend coral tpu still?

  • @pazsion
    @pazsion Год назад

    how do you know its being used?
    thats about the same performance as the pi itself?

  • @nachoridesbikes
    @nachoridesbikes 11 месяцев назад

    I compiled opencv(took almost a whole day) in my pi 3 and its able to do realtime object detection without any tpu

  • @Scout339th
    @Scout339th 6 месяцев назад

    Im curious how well this would work if there was code for it to work like an ASIC and do crypto mining.

  • @112Famine
    @112Famine 11 месяцев назад

    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!

  • @syedijlalayub7614
    @syedijlalayub7614 11 месяцев назад

    Spot on "I totally understand this code" 😂👍🏻👍🏻

  • @korobochkaubivatochka
    @korobochkaubivatochka 10 месяцев назад

    Is audio was made by ia?

  • @stevensims3342
    @stevensims3342 Год назад

    That is honestly so fkin cool they have an AI PU like that.

  • @_drdoof_
    @_drdoof_ Год назад

    Everyone knowns calculating digits of pi is the most computational task.

  • @bobbyparihar705
    @bobbyparihar705 Год назад

    What are the use cases?

    • @meinbherpieg4723
      @meinbherpieg4723 10 месяцев назад

      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.

  • @Lp-ze1tg
    @Lp-ze1tg 6 месяцев назад

    Does it also upload whatever I do to Google?

  • @Sttreg
    @Sttreg 8 месяцев назад

    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 ?

  • @MarkMcLarenVaingit
    @MarkMcLarenVaingit 4 месяца назад

    So which AI platform is this based on again??

  • @cdenver
    @cdenver 11 месяцев назад

    Didn't someone do something similar with a Nintendo Wii body motion device or the XBox motion device?

  • @games-are-for-losers
    @games-are-for-losers 7 месяцев назад +2

    RUclipsr try not to use supercomputer incorrectly challenge (very hard)

  • @SY4Artz
    @SY4Artz 11 месяцев назад

    i took mine to the absolute limits too! i overclocked it to the absolute max, even watercooled it to play proper minecraft on it.

  • @Abou47Pandas
    @Abou47Pandas Год назад

    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.

  • @iwillgettableflipped
    @iwillgettableflipped Год назад

    I subscribed. Although, do you know of any better ai video detection packages or hardware, etc?

    • @crysiscontained4421
      @crysiscontained4421 Год назад

      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.

  • @wukiv
    @wukiv Год назад +1

    amazing video! keep it up

  • @Fanaleds-software
    @Fanaleds-software 18 дней назад

    If only the Coral was for sale anywhere (for a normal price).

  • @jellythemantella
    @jellythemantella Год назад

    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

  • @nadeemmohammedshajahan8513
    @nadeemmohammedshajahan8513 Год назад

    Didn’t this come out like 4 years ago?

  • @thymelord8353
    @thymelord8353 Год назад

    The 3D printer in me saw TPU and just had to see what was going on 🤣

  • @chrissuperhero2291
    @chrissuperhero2291 6 месяцев назад

    This should make their share price go through the roof!

  • @Diesr
    @Diesr Год назад

    What’s the music where you inserted code like Usain Bolt? 😂

  • @CrisCreator
    @CrisCreator Год назад +2

    Coral has been around for years

  • @sarjannarwan6896
    @sarjannarwan6896 8 месяцев назад

    Jetson nano's filled the rpi form factor machine learning area for a while.

  • @LennyMiller739
    @LennyMiller739 5 месяцев назад

    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

  • @johntrevy1
    @johntrevy1 4 месяца назад

    So is this just good for image recognition?

  • @blakeanderson7906
    @blakeanderson7906 4 месяца назад

    Nice PRS!

  • @dylanmannion3108
    @dylanmannion3108 Год назад +3

    You should make a magic mirror

  • @mynameisben123
    @mynameisben123 4 месяца назад

    The TPU usb accelerator is from 2017

  • @JordanMillsTracks
    @JordanMillsTracks 5 месяцев назад

    anyone else thought the thumbnail was a hand rolling a joint?

  • @andresacuna1108
    @andresacuna1108 Год назад +28

    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.

    • @SUPABROS
      @SUPABROS Год назад +1

      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

    • @felipeherrera9396
      @felipeherrera9396 Год назад

      ​@@SUPABROS 7w from tpu that do the half of 300w graphic card idk seems petty good and Fair

  • @drewgo
    @drewgo 11 месяцев назад

    Mac Miller reference with the Don’t Trip hat?

  • @anb4351
    @anb4351 Год назад

    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

    • @meinbherpieg4723
      @meinbherpieg4723 10 месяцев назад

      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?

    • @anb4351
      @anb4351 10 месяцев назад

      ​@@meinbherpieg4723You can do it on a 100 dollar cheap Android phone

  • @thomasschuler5351
    @thomasschuler5351 Год назад

    my bushitmeter just went off limit. so many things you said are just wrong

  • @kronikphase
    @kronikphase 3 месяца назад

    That s really good. Add a voice , mutiple cameras . And youd have a amazing aid for blind people . U heard it here first .

  • @chocolateoreo8384
    @chocolateoreo8384 Год назад +7

    Good content man! You just earned a sub

  • @michaelmcwhirter
    @michaelmcwhirter 9 месяцев назад

    Either way this Tech is really sweet!

  • @AndrewTSq
    @AndrewTSq 11 месяцев назад

    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.

  • @hassanbadawy481
    @hassanbadawy481 11 месяцев назад

    Awesome 👌

  • @danieljuno810
    @danieljuno810 10 месяцев назад

    91% that is definitely a barbell 😂

  • @almusfikhasan
    @almusfikhasan Год назад

    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 ☺️

  • @therob39
    @therob39 Месяц назад

    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.

  • @danny5035
    @danny5035 Год назад

    First time I've ever seen fractional FPS

  • @tobiastessmer5125
    @tobiastessmer5125 2 месяца назад

    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.

  • @everypizza
    @everypizza Год назад

    can it run sdxl

  • @twveach
    @twveach Год назад

    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.

  • @squoblat
    @squoblat 2 месяца назад

    Could I run a cluster of these?

  • @risingforce9291
    @risingforce9291 19 дней назад

    So you can connect this to a drone? then detect firearms, formations, heat signatures, vehicles, and human outlines/silhouette.

  • @ChrisAlas
    @ChrisAlas Месяц назад

    If by new you mean at least 8 years old 😂

  • @peanutygoodness
    @peanutygoodness 2 месяца назад

    But did it say “Paul Reed Smith” or “Orange Amplification”?

  • @Shadow-xe7rl
    @Shadow-xe7rl Год назад

    The product is old came out in March 2019

  • @Eniro20
    @Eniro20 Год назад

    Ah, a dedicated matrix multiplication calculator

  • @tiziomino6718
    @tiziomino6718 4 месяца назад +1

    Better than the rabbit r1

  • @max_ishere
    @max_ishere Год назад

    Can you train model on it too?

  • @_____alyptic
    @_____alyptic 7 месяцев назад

    There's dual tpu module for two of em in one

  • @mult-ifunctionalservices953
    @mult-ifunctionalservices953 Год назад

    Husky lens video please

  • @AtariWow
    @AtariWow 10 месяцев назад

    Are you using ana ai voice for this video? It sounds... Unnatural.

  • @ryanrester
    @ryanrester Месяц назад

    Got one of these in an m.2 bay in my laptop. 😁👍

  • @akfortyfo7024
    @akfortyfo7024 Месяц назад

    I thought Coral had been around for a while

  • @dreamoftranscendence4415
    @dreamoftranscendence4415 Месяц назад

    Beware any company that says "we're not evil" before anybody asked.

  • @ramana8343
    @ramana8343 Год назад +1

    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 ?????

  • @Typing.._
    @Typing.._ 7 месяцев назад +1

    That frame rate tho 🤣

  • @chickenmeatpizza
    @chickenmeatpizza Год назад +22

    bro tried to deepfake this without us noticing