Search results

Hey all, I've been out of the loop over the past year on all the updates and new features of BI/CPAI. I've recently added a GPU to my system and updated BI/CPAI to the latest versions, and I'm noticing that in the AI analysis that CPAI is continuing to analyze every snapshot asked of it...

Ah, I see. I'll check back in another year or so. I guess I'll rely on my remote GPU server solution until then.

Hey guys, I haven't really checked these forums in over a year or so. I've got a spare USB Coral adapter from another project and I see now that CPAI now supports Coral TPUs. At the moment, my BI server is using a GPU which is connected to another PC running CPAI in a docker container. So...

Thanks so much for the detailed response. This is exactly what I did to revert to 2.1.9, and as predicted, it's all working flawlessly. My question is, how will I ever be able to update to a newer version, given that they'll all likely contain the same bug? The developer on the CP.ai forums...

Thanks so much, I'll try it out

I would love to, but I can't find a way on Unraid to do this. Can you tell me how?

Guys, I keep seeing 'AI error 500' in BI ever since I updated CP.ai to the latest version. I've tried reinstalling an disabling half precision, but no effect. Restarting the docker container works temporarily, then keeps failing after a few hours. Am I the only one with this problem? CP.ai...

That's what I meant. It doesn't work. I previously unticked it because someone here told me it took up significant storage space. Is this correct?

The problem is that my BI machine doesn't have a GPU. It struggles so much that it frequently times out and gives error 500 on AI alerts anyway, which is why I offloaded it to a machine that has a GPU in the first place. Do you have a docker-compose.yml file? Or are you kicking off docker from...

Ok, what about the lack of CTRL+click functionality?

Guys, Getting some recurring errors after I updated CP.ai on my Unraid box (it's an external setup that my BI box offloads AI processing to). No other changes were made. Here's part of the log. Basically, BI will fail to register any AI events. Restarting the CP.ai docker works for a while...

If it goes through all the snapshots it takes until it finds the best one, why would it require that it burn the image onto the label? Why wouldn't it just dumb that 'best' image straight to a thumbnail? Especially if they remain as thumnail alerts after you delete them.

Ok done. I'm not sure why I ever checked that. Maybe it was left on from early troubleshooting when I first built the system. Ok unchecked. What does 'burn label onto images' do anyway? Which label? Use what? And how does this show the vehicle and not the headlight shine? Sounds interesting...

Aren't these the mainstream clips? I need these. Won't turning this feature off get rid of them? How would I even turn this off? No particular reason. Aren't these automatically generated for alert thumbnails? How do I turn them off?

Ok so I'm back to square one and not having a clue then. @wittaj any ideas?

Are your cameras also set to 'continuous + alerts', recording in mainstream only when alerted and continuously recording on substream otherwise?

Ok I'm STILL having problems with my database. I changed absolutely nothing since my last update here where everything was working fine. I go to log in today, and checked the little calendar icon to see how many days of alerts my HDD is successfully capturing - and it only has red dots on today...

Thanks, I changed the Alerts folder to 1GB and ran a compact/repair - now the DB status window is not showing any issues. Thanks again for your valuable help!

Well my new folder which contains all my clips is only over 5000 items and comprises 90% of my allocated storage, so that shouldn't be a problem, right? So no suggestions as far as my cut/combine settings go?

I don't get it though. Even if I had the 'right' settings which minimized the amount of clips, wouldn't the large size of the drive eventually accumulate over 200,000 clips anyway on a long enough timeframe? Otherwise what is the point of having a large drive? Here is my cut and combine...

Hey guys, I'm on 5.7.2.4 and upon logging into my BI machine, I noticed the new DB status window, however I get the following error message. Here's my allocation: And here are my storage settings: My 6TB HDD is a WD Purple CCTV drive. Basically I'm just saving all the clips there and...

Happy to write an email to support. I guess my question is: Has the developer said that they can reproduce the issue on their end? Also, why does my BI status keep saying that my drive is overallocated when the issue happens? Are my settings wrong?

That's really disappointing, since you'd think that 'latest stable version' would intuitively mean that it would have no obvious bugs that make it unusable. This system does use CPAI, so it needs to be on a stable version that is at least compatible with it. Considering this seems to be a...

Anyone??

Tried this (as above) and it only fixes things temporarily. P.S. I was on the 'latest' version after you suggested it to me earlier in this thread. Can you suggest a permanent fix please? This system is my father's and I don't want to have to keep logging in to regenerate the database every week.

Guys, It happened again. I'm not sure how long this has been going on for because I haven't had to check clips in quite some time. I've noticed that the BI stats shows that store is 'overallocated' whenever this happens, however whenever I regenerate the DB after I've deleted the db folder, all...

It's the only GPU on the system, and I'm assuming it'll be quicker than just using the CPU?

What CPU are you running it on? Whenever I try CPU only mode on my i5-11500 I get times of more than 9000ms.

I've offloaded my CPAI to another computer on my LAN that has a GTX1050Ti and getting times of ~40-80ms. Still can't use custom models though for some reason.

That's stupid. So your camera pretty much has to be placed over the road in order to get the car driving straight into it? Lol.