With ByteTrack or other similar algorithms I don't think it would be too difficult. If you're looking to contract the work out I could give it a go.

It's AGPL because Ultralytics requires it to use YOLO: https://github.com/blakeblackshear/frigate/pull/10717

I'd make it MIT tomorrow if you know a workaround or alternative model

Thanks!

Both for the explanation and for being a person that respects the license even if you (like me) don't particularly like it.

typo I've just fixed lol, thanks for the heads up

Yeah sorry that’s confusing, I need to change or remove it until I’ve a payment system setup.

There is an unfinished but functional APK and android project in the repo, but it’s not on the Google Play store yet, their approval process for new individual devs is long

fewer features, easier setup, with more GPUs supported. (I've not used frigate myself though, only watched videos)

Where can I find the list of supported GPUs? Frigate been able to handle everything I've tried so far, all from Nvidia and AMD GPUs to even Intel iGPUs.

same here -- it's also among one of the only things to support Coral devices and RPi video cores.

I would imagine any GPGPU compute-capable pre-CUDA thing probably won't cut it.

I have used Frigate for years, I think early on it didn't support all of those GPUs. So it might be that said videos are out of date.

Maybe my view of frigate and tensorflow (assuming frigate still uses it) is outdated then. I’m referring to tinygrad vs tensorflow when I say GPU support, of course google’s tensorflow is best for google’s TPUs. I’ve had better luck using tinygrad on my personal devices, but I am biased as it’s been a while since I’ve used tensorflow

This would be a good point of differentiation to make on your GitHub page or for a technical audience on your website. Frigate is SOTA in many folks minds, and to show that you are using tinygrad over tensorflow may be a good “modern-ness” signal for that audience.

Edit: another solution in this space shows a list of supported ML runtimes, which would be good info for folks wanting to run on specific hardware. https://github.com/boquila/boquilahub

Sorry, which one are you talking about, frigate or clear cam?

Paid features are Live and event clip viewing over the internet, and receiving iOS notifications. You're paying for use of my server in those cases though, not for features I've made closed source. You can edit the code to use your own server if you wish too.

I'm new to HN and thought shilling the paid stuff violates the rules, so I didn't mention them.

(I'm a mod here) - it's fine to talk about paid features, as long as it's clear which ones are paid and which ones not.

The only thing that wouldn't be fine is to post a Show HN with no way to try the product out (https://news.ycombinator.com/showhn.html) and you're fine on that part.

"I'm new to HN and thought shilling the paid stuff violates the rules, so I didn't mention them."

HN ain't a non profit charity, but is the forum of a venture capitalist company, so talking about paid things does not violate any rules.

Paying for things does cause some folks to champ at the bit, though, so his assessment is not unwarranted.

It mostly gets people going on and on about how they could do it themselves for free.