Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

unihiker.com

Post reply on HN
Print view View original

161–170 of 241 posts

Re: Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

#161

Post by Eisenstein »

schreiaj wrote: post #148
chaxor wrote: post #124

Earlier quoted context omitted.

Why on earth would you run ML on a potato?

What should we run it on if we want to deploy it on mobile systems with limited access to network and extremely restricted power budgets? For a hobby project I'm trying to find a solution - Power budget for multiple is sub 200w. Need to run inference on a lower resolution video stream (or multiple, that be nice) to do object detection. Cost is a factor because I need to have multiple angles to determine where in rela…

Check out the Luxonis Oak products. I use an Oak-1 Lite to do real time 2 stage object detection and recognition (~23FPS at 1080P inference on device with two custom yolov5n models). With a bit of python and a Pi (or a Rock64 or similar) you can get it up and running in a day. They also have a decent community and are actively developing the API/SDK and hardware.

Re: Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

#162

Post by joshmarinacci »

jedberg wrote: post #104

This seems like a somewhat related place to ask this: Does anyone know where I can get a 3" round screen? I have a Star Wars clock from the 1970s that has a ton of empty space in the base. I want to put a small computer in it and replace the 3" clock face with a round screen, so it can show the time and maybe some fun Star Wars animations. But I just don't know how to find a 3" round screen without buying 1000 of the…

I think Waveshare has some. I've been messing with their 1.28 in round ones and I like it. Just be aware that they will use SPI (think Arduino level) for the connection, not something video oriented like HDMI. Thus they can be used on a Raspberry Pi with a custom driver, but you won't be getting 60fps.

Re: Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

#163

Post by schreiaj »

Eisenstein wrote: post #161
schreiaj wrote: post #148

Earlier quoted context omitted.

What should we run it on if we want to deploy it on mobile systems with limited access to network and extremely restricted power budgets? For a hobby project I'm trying to find a solution - Power budget for multiple is sub 200w. Need to run inference on a lower resolution video stream (or multiple, that be nice) to do object detection. Cost is a factor because I need to have multiple angles to determine where in rela…

Check out the Luxonis Oak products. I use an Oak-1 Lite to do real time 2 stage object detection and recognition (~23FPS at 1080P inference on device with two custom yolov5n models). With a bit of python and a Pi (or a Rock64 or similar) you can get it up and running in a day. They also have a decent community and are actively developing the API/SDK and hardware.

Thanks, I've got one of their depth cameras that's been ok. I didn't realize they'd expanded their line so much. Glad to hear about the API/SDK improving, last time I mucked with it a year or so ago it seemed like it was underdeveloped.

Going to have to dig into the sensors they use - had passable luck with non ML tasks using dirt cheap camera modules from laptops running at low resolutions right up until I started moving the cameras at all and then it became a blurry mess because they were so small their exposure times were high. (I'm trying to also avoid having to put a bunch of illumination near the cameras so it doesn't entirely look like a biblically accurate angel)

Re: Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

#164

Post by oneplane »

jancsika wrote: post #135
oneplane wrote: post #100

Earlier quoted context omitted.

You're actually answering your own question here ;-) Because a SoC with limited CPU-core resources can't do everything in software, the chip contains many system components (hence System-on-Chip or System-on-a-Chip) that handle things the CPU cores then no longer need to do. Think protocol handling or memory; instead of spending many clock cycles on handling the USB bus, you can leave that to the USB controller and o…

Is this in the purview of the panfrost driver stack?

I think that's only for ARM's own GPU IP, not for the VOP (it's more of a LCD driver than an actual GPU -- I'd compare the VOP to say, GameBoy-color level of graphics capabilities, which is cool but not even close to a bare-bones VESA or UEFI framebuffer).

Re: Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

#165

Post by Eisenstein »

schreiaj wrote: post #163
Eisenstein wrote: post #161

Earlier quoted context omitted.

Check out the Luxonis Oak products. I use an Oak-1 Lite to do real time 2 stage object detection and recognition (~23FPS at 1080P inference on device with two custom yolov5n models). With a bit of python and a Pi (or a Rock64 or similar) you can get it up and running in a day. They also have a decent community and are actively developing the API/SDK and hardware.

Thanks, I've got one of their depth cameras that's been ok. I didn't realize they'd expanded their line so much. Glad to hear about the API/SDK improving, last time I mucked with it a year or so ago it seemed like it was underdeveloped. Going to have to dig into the sensors they use - had passable luck with non ML tasks using dirt cheap camera modules from laptops running at low resolutions right up until I started m…

Well, you can control the camera ISP and they use very decent IMX modules, so it really shouldn't an issue like it was with the cheapos, as long as you can do the coding to your needs.

EDIT:

* https://docs.luxonis.com/projects/api/en/latest/samples/Colo...

Re: Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

#166

Post by oneplane »

chaxor wrote: post #124
sosodev wrote: post #97

Earlier quoted context omitted.

Inferencing neural networks is a big one. It's hard to get near real-time performance without it. Depending on the use case of course.

Why on earth would you run ML on a potato?

It would probably not run on this potato directly, but on an accelerator (be it in-SoC or a separate thing like a Google Coral). The management and control of a Coral needs to happen on a CPU somewhere, but the actual work doesn't involve the CPU much, if at all.

So if you have a thing that has all the data and all the work done on an engine elsewhere and you just need to have a SoC to turn the thing on and off and get the data in and out, that's where a potato-SoC could work. Of course, the potato would need good distro support with up-to-date kernel, drivers, python, libraries etc. and if you're connecting it to the network, best make sure it's also getting patched consistently.

So, as far as ML Potatoes go, that's about it. It is a totally valid question by the way, even if asked in jest.

Re: Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

#167

Post by cooljacob204 »

markstos wrote: post #132
Retr0id wrote: post #9

Earlier quoted context omitted.

I'm incredibly curious what the experience of trying to write code with ChatGPT is like, if you have no prior knowledge. Obviously, it's impossible for me (and most others reading this) to un-know everything and approach it with fresh eyes. Are there any good real-time videos of non-programmers using ChatGPT to write code? (seems like the best way to understand what it's like)

I don't know Rust well and was having trouble the finding the docs I needed, so I asked AI for help. Google Bard, I think. It had real difficulty producing code that ran and worked. The problem was that there were breaking API changes across versions of the library, but it was just using probabilities of method names being correct, and it didn't ask me or tell me which version of the library it was targeting, so it w…

Google Bard isn't the best when it comes to writing code in my experience. Try GPT, you should get very different results.

Re: Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

#168

Post by WheatMillington »

lostgame wrote: post #123
isoprophlex wrote: post #88

You flash the OS (okay, admittedly, debian which is nice) onto it from windows with some lugubrious .exe https://www.unihiker.com/wiki/burner No linux/macos tool available. No thanks.

Hah. Way too misread the room, are they serious? Who even develops Windows-exclusive apps these days, anyway? Even the average user these days seems to find it simply abhorrent. It's so simple to create cross-platform applications these days, there's literally no excuse. I can't imagine the thought process that went behind this beyond greed and profit, a little mind-numbing.

Greed and profit? You can't honestly believe these were the motivation behind this decision, can you? That is honestly your most generous take?

Re: Unihiker, an $80 single-board PC with 2.8“ touchscreen, quad-core ARM Cortex-A35

#170

Post by Eisenstein »

rostakagmfun wrote: post #140
theamk wrote: post #17

My usual question for small cheap boards is: what will happen to OS support in 3 years? Is it using regular distro or is this a custom fork which will likely be never updated? The website says: > The UNIHIKER comes with a Linux operating system based on Debian and various built-in features, which will be upgraded from time to time. ... don't expect OS upgrades here. If you want to play with it for a while then put it…

Slightly unrelated, but I wonder what is a preferred OS for similar boards: a buildroot or yocto -based system vs a full-blown Debian-based distribution with desktop and package managers? When I looked into (now deprecated) Jetson Nano I was surprised to find out there was no straightforward and documented way to build your own system and cross-compile for it. Is that because for many people using SBCs means doing ev…

Armbian or DietPi.
Post reply on HN