I use the PCIe for an NVMe, so how would I add this AI kit, need a splitter?
@darrenkairis973321 сағат бұрын
Love it, wish I could buy the 3D printed eye mech!
@terrykohlman735523 сағат бұрын
Great info but horrible video
@kevinmcaleer2823 сағат бұрын
Hi Terry - In what way was it horrible? Genuinely want to make better videos so please let me know
@victorial5141Күн бұрын
I'm so glad I found your channel so awesome and informative videos! keep it up
@thesimplicitylifestyleКүн бұрын
😎🤖
@cattigereyes1Күн бұрын
AI build my brain, need more power AI servers need to go nuke power supply, Microsoft, Google charging for AI. While it quickly takes over markets, companies, and minds. Enjoy…
@3dmixer5522 күн бұрын
Can it run facial recognition model?
@aecpartnersdanismanlik71173 күн бұрын
👍👍👍👍
@steaders823 күн бұрын
Can I use this chip in a standard tensorflow model? If so how? Or is it automatic?
@Adrian-hl2se3 күн бұрын
Thank you!!!
@igoraraujo75113 күн бұрын
Wow, thank you very much for sharing! Always helping! I have a question, I think your website is down!
@kevinmcaleer283 күн бұрын
Thanks - its back up!
@BlckshpWll4 күн бұрын
What about the cooling, I'm sure both the pi and ai chip will get boiling if you want to build some continuous running high-flops program
@ahmedosama74635 күн бұрын
When tried , the hailo causes issues in identification , and aside from the fps , accuracy is very low , is that accuracy lost during conversion ?, i would still use the coral for now
@galdakaMusic5 күн бұрын
Is posible remake this video with the new Hat AI Hailo 8L?
@CallousCoder5 күн бұрын
Us 50 somethings will say: Z80 or 6502 Assembly is better. Learning assembly back when I was 13, was the best thing I learned. It made me understand basic a lot more and it laid the foundation for my EE degree in micro controllers. And I still do a lot of assembly on this channel too. Because I think that only having literally a dozen or so frequently used opcodes that you need to use to build something useful is the ultimate teacher of problem solving.
@CallousCoder5 күн бұрын
Us 50 somethings will say: Z80 or 6502 Assembly is better. Learning assembly back when I was 13, was the best thing I learned. It made me understand basic a lot more and it laid the foundation for my EE degree in micro controllers. And I still do a lot of assembly on this channel too. Because I think that only having literally a dozen or so frequently used opcodes that you need to use to build something useful is the ultimate teacher of problem solving.
@galdakaMusic5 күн бұрын
Is posible Rpi5 with SSD and Halo for run Asístant and Frigate? What are the correct hat configuration for this pourpose? Thanks
@anthonyholmes13126 күн бұрын
I have struggled SO HARD with the Coral and Raspberry Pi 5. If you are telling me I don't have to create Dockers and virtual environments and whatnot to run older versions of Python I'm IN!!!
@ochanabondhu6 күн бұрын
Q:Hello..This is cool!... I was wondering if this is enough computer power to work with depth cameras with 3D object detection like the Realsesnse series?...
@janikabalin5 күн бұрын
Same question… not sure if I should go for a Jetson Nano, Orin Nano or a PI5 + AI Kit. I want to run a RealSense + RPLIDAR for object tracking and SLAM.
@bitnbrick6 күн бұрын
@kevin How do you share your screen , bench cam and video ? OBS ?
@kevinmcaleer286 күн бұрын
I use Ecamm Live for Mac
@Embassy_of_Jupiter6 күн бұрын
your light does look like a toilet with the toilet cover down
@ayenijoshua-mf5eq7 күн бұрын
I'm enjoying this course.⭐⭐⭐⭐⭐❤
@bokami34457 күн бұрын
+1 liked, for the late night dancing :-), seriously though, $70 for an entry point modest AI chip is pretty impressive. If you consider all the interesting things hobbits have done with PI's over the years, I'm looking forward to see what they come up with, when you add a NPU to the recipe
@blasterbug7 күн бұрын
I encountered a few errors following this tutorial and some configurations are just overkill for a time machine... [2024/06/06 22:26:51.140316, 0] ../../lib/param/loadparm.c:1936(lpcfg_do_service_parameter) Ignoring unknown parameter "guest"
@Yakroo1088 күн бұрын
👍👍👍
@FernandoDCDuarte8 күн бұрын
But, any actual useful uses of this AI kit?
@kevinmcaleer288 күн бұрын
What actual uses would you find useful?
@LoneStarBassPursuit5 күн бұрын
@kevinmcaleer28 anything besides imagine detection or recognition.
@alexdev4048 күн бұрын
Hi umm excuse me but where are we actually using the joysticks array other than the initialization? Since the robot isn't a multiplayer application can't we just do *pygame.joystick.Joystick(0).init()* instead since we're just using a single controller?
@ArianeQube8 күн бұрын
Can I use this AI kit to speed up my LLMs on the Raspberry Pi 5 with Ollama ?
@oksowhat4 күн бұрын
how are you running llms on a rpi?
@tinkerman17909 күн бұрын
Thx for sharing! Apart from object recognition, any other use caes be benefit with edge compute power?
@user-yr2nf9cr4v9 күн бұрын
Looking forward to a tutorial, inferencing custom trained Yolov8 object detection models using this....
@68HC0609 күн бұрын
Does openvino work with this ? (I'd like to use Audacity's openvino tools and Whisper for speech recognition).
@conorstewart22149 күн бұрын
Unfortunately a lot of AI products look good just looking at the top level specs but then once you have a deeper look they are difficult to use and not all that useful. It will be interesting to see how this ends up working. I have just bought a cheap jetson orin nano for a project of mine so I won't be buying this anytime soon but it will be interesting to see what people manage to use it for.
@kevinmcaleer289 күн бұрын
This is not like Rabbit or Humane, it actually does the work locally. I’ve made a lot of content about using object detection previously for various projects so this will take that workload off the main CPU freeing it to do other tasks.
@martyn3349 күн бұрын
got a few pi's, but just wondering what uses would this have? o.0
@MrPmribeirox9 күн бұрын
Thank you very much Kev, great video💯👌
@kevinmcaleer289 күн бұрын
You are very welcome
@armisis9 күн бұрын
I got a coral and the coral hasn't helped at all. Looking forward to working it into my fabric project.
@AlasdairAllan4 күн бұрын
Nope it won't. If you're on a Pi 5 inferencing speed on the CPU is the same performance as the Coral TPU.
@armisis9 күн бұрын
Got mine ordered.
@TheArcanis879 күн бұрын
Very informative, I was looking for an accelerator for mobile robotics and found nothing useful. The Orin is powerful but has nvidia blessed binary blobs and is really expensive. 13TOPS, PCIE1x3.0 3.0TOPS/W are promising specs. On an 8GB RPi it might be enough to run a llama3-8B-4QKM model.
@johnnydepp411410 күн бұрын
so no nvme ssd at the same time as the ai ?
@kevinmcaleer2810 күн бұрын
Not with this Hat, but you can use the Pimoroni Duo to have both at the same time.
@anthonyholmes13125 күн бұрын
@@kevinmcaleer28 could we use the Pimoroni Duo and the Hailo accelerator with the same software, etc?
@fullstack_journey10 күн бұрын
now all that's remaining is: Frigate support!!
@eelcohoogendoorn804410 күн бұрын
It great to have such a chip design with tightly integrated memory which is obvious the way to go for any inference tasks. But ive found it interesting how hailo manages to keep any information about the amount of that super useful memory 100% secret; and this product launch is no exception. Like, dont we all want to know what models we can actually run on there? Arnt we going to find out eventually what the memory limits are after we spend our money? Or is that somehow the point?
@nikobellic57010 күн бұрын
I can imagine nature watchers will want this to identify animals
@cslivedk10 күн бұрын
Hi Kevin. Is it posible to make a very small pc not much larger than an Apple TV box. It should be running Linux, and possible to connect, keyboard using USB/Bluetooth with a couple of additional usb ports 😃
@kevinmcaleer2810 күн бұрын
Yep - Raspberry Pi 5 plus a tower case (SunFounder have launched one recently)
@cslivedk10 күн бұрын
Thank You Kevin😀
@briantw9910 күн бұрын
I've had that exact 'Rainbow Book of BASIC Programs' for the past 40 years or so :-)
@kevinmcaleer289 күн бұрын
Yes! The one in the video has been in my family since 1980s. I remember typing these games in
@cassielakin10 күн бұрын
That's awesome can you still have an nvme drive
@kevinmcaleer2810 күн бұрын
You'll need a Hat that can take 2 NVMe - such as the Pimoroni NVCe Duo
@bern04710 күн бұрын
@@kevinmcaleer28 isn't the Raspberry Pi NVME hat stackable? so why cant we have two?
@kevinmcaleer2810 күн бұрын
@@bern047 The Raspberry Pi M.2 Hat has one PCIe connector and one M.2 port. The GPIO pins are stackable, but you only get one PCIe connector. Pimoroni Duo has two M.2 ports. There are other Hats available that have multiple PCIe connectors so you can daisy chain them - check out PineBoards website for more info on those.
@bern04710 күн бұрын
@@kevinmcaleer28 Thanks, Pimoroni have done it again for me, will order one thanks
@daveedwards166310 күн бұрын
Does not work with tflite?
@kevinmcaleer2810 күн бұрын
According to the specs, yes!
@eMgotcha7710 күн бұрын
OMG Yes! Google has abandoned their PyCoral package and you can't really make it run on a RP5 right now. (yes i know about feranick on github) Anyone knows how much RAM this AI module has? Neither The website nor the product brief tell it. I actually would need Whisper-Tiny to fit on it.
@eMgotcha7710 күн бұрын
Semantic Segmentation, stdc1, 1,024×1,920 with 54 FPS huuuuuuuuuu the benchmarks look promising 😮
@SandipDhakal-hc9tk10 күн бұрын
I guess you have a shitty light there!
@kevinmcaleer2810 күн бұрын
Haha
@raspberrypi10 күн бұрын
Hiiii Kev! 👋you could make your fortune telling robot EXTRA spookily accurate with this kit.
@kevinmcaleer2810 күн бұрын
Cool! Yes, if I added a camera and ollama back end it could detect a person and then say something spooky about what it sees!
@AerialWaviator10 күн бұрын
Very interesting. It would be nice to hear more about supported frameworks in future. Realize this a hardware unboxing and quick demo.
@kevinmcaleer2810 күн бұрын
Yes I’ll be following up with more info on that now that the full software stack is released