I'm at about 1.6GB of both normal RAM and GPU RAM with the built-in AI on the medium model running 8cams - as I said before I've deleted all the other models so impossible for them to load regardless of BI settings.
don't delete them, disable them with a hyphen, like this (do this for all of them you don't want to use, my example below only person and car are enabled.
person
-bicycle
car
-motorbike
-aeroplane
-bus
-train
-truck
I'm running the latest 6.0.1.3 version and have disabled my CP.AI service in favor of testing the new built-in AI - I'm using the medium model (yolov8m) and so far things seem to be working well and at decent speeds. One thing I don't like is there are no options to fully disable faces, plates...
Wow, after all these years of using BI I never knew that, all my cams are 15FPS - but I had a mix of BI defaults between 20FPS and 30FPS - Should change them all to 15FPS to match my cams or is there a need to go a little higher of say 16FPS?
I can't help with the 1st question as I upgraded a few days before the option was in v5 (using manual download/install method) - I didn't lose any settings/config or recordings/alerts. The only very minor issue I had was that the first install did not correctly add/unpack the UI3 web folder...
A headless OCI/LXC/Docker container version of BI that you then connect to via web GUI or remote connect Windows BI client (all with support for GPU passthru) would be very nice indeed! - It would be a huge amount of work for the Ken thought.
Are you running a supercomputer at home? :) - I'm no Yolo expert, but I thought Yolo11 was the reserve of smart cars and robots that needed super high accuracy with dedicated AI HW. I find Yolo5L perfect for my needs, maybe I might go Yolo8M, but that would be it for home CCTV automation.
As part of my CUDA/DirectML testing I also included Yolo8 but didn't see any improvement in detection(using Standard Large model), but I did see increased processing and large increases in GPU/memory consumption - I much prefer the smaller footprint of .NET with DIrectML. I want superfast...
Is the issue BI talking to CI.AP or do you have an actual issue with CP.AI? Easy way to tell is access to the CP.AI local web GUI and see what's running and perform some tests. FYI I had Nvidia/CUDA working very well for years and recently after a huge amount of testing for performance I moved...
Is the issue BI talking to CI.AP or do you have an actual issue with CP.AI? Easy way to tell is access to the CP.AI local web GUI and see what's running and perform some tests. FYI I had Nvidia/CUDA working very well for years and recently after a huge amount of testing for performance I moved...