roryclear

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

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

Supported runtimes list would be nice, but I don't have access to much hardware to test on. I aim to remove most dependencies and support anything that can run tinygrad + ffmpeg

Maybe my view of frigate and tensorflow (assuming frigate still uses it) is outdated then.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

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)

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.