Search results

Confirmed, it's not enabled

I have the same. It starts up with CPU with the ObjectDetectionYOLOv5Net process using CPU, it then reports that it lost contact & comes back using GPU for the ObjectDetectionYOLOv5Net process. During this startup phase, BI reports AI not responding. Usually takes about 5 minutes to sort itself...

I get this on every restart but it settles after a couple of minutes. Very high CPU and memory usage for the CPAI process while it happens (100% CPU and 2Gb+ memory usage for the process). Runs smoothly with GPU DirectML thereafter using 250Mb memory and less than 5% CPU. The 30 second duration...

It took me a while to get it going but have it running using GPU (DirecML) on Windows 11 without any issues. What worked for me was to update to the latest Graphics drivers and then install using "Option 1 with a vengeance" in the section "How to install a module" CodeProject.AI Discussions -...

Correct, the last install I did was with "Option 1 with a vengeance". Before that, I reinstalled the module using "Option 1" a couple of times. Although it installed the module successfully, I noticed errors like "customs-model" folder does not exist and Timeouts during the installation.

I updated to the latest available graphics driver but still could not get it to work. Reinstalling using "Option 1 with a vengeance" under "How to reinstall a module" seem to have done the trick: CodeProject.AI Discussions - CodeProject

I can't seem to get CPAI 2.1.8 to run YOLOv5 .NET using GPU (DirectML). No errors are being reported in the CPAI logs, console shows "Connection Lost" and then restarts in CPU mode. I followed the advice to do a clean install, clean up folders, restart & wait it out. Rolling back to 2.0.8...

5.7.6.2 resolves this issue for me

Release 5.7.0.3 addresses an issue where CPAI service may be restarted multiple times with the below configuration: (1) Auto Stop/Start with Blue Iris Enabled and (2) Very active AI Processing and (3) A Low AI Timout value is in use (default 30 seconds?)

Thanks, very detailed information! Any outliers that can be identified using the BI & CPAI logs at the time the issue happens? A specific camera/model trigger combination?

ObjectDetectionNet will only show if you are running YOLOv5 .NET, You will see Python processes for YOLOv5 6.2

It would be interesting to see what CPU/GPU load is when this happens. I've seen similar symptoms when AI processing overwhelms the CPU/GPU - it starts spawning new ObjectDetectionNet processes, each using memory and CPU. Do you have details of the processes & memory allocation for each when...

@MikeLud1 Any idea when the "ipcam-combined" model will be available to run on GPU (Intel Imbedded) with YOLOv5 .NET?

I'm running an i7-11700 CPU with Intel UHD 750 Graphics, ipcam-general model on Medium. I'm getting 80-160ms with the GPU & YOLOv5 .NET, 250-400ms with the CPU & YOLOv5 6.2

What a great feature!

5.6.0.5 resolves this issue

5.6.0.5 resolves this issue

The issue with UI becoming unresponsive is still there in 5.6.0.2 (affects UI3 too). Seem to be related to using the "Alerts" clip list filter for any camera with a large number of Alerts. Provided the same feedback to Ken...

Same here, you may also notice similar errors to the ones below. I sent the details to Ken. 1 17/08/2022 7:43:36.806 AM B2 Alert image not created 2 17/08/2022 7:43:36.902 AM B2 AddToBIDB failed 1

I'm using the new CPU version without any issues

Yeah, substream @ 1912x1080, default DS model only and Medium mode

Averaging 200-250ms on a 11th Gen i7-11700

5.5.25 fixes it for me (DS CPU version). The only issue I'm still observing is the yellow motion overlay is not added for analysis for the second sample (T-76msec) however object detection is processed as expected

@Dave Lonsdale You may have seen it already but some useful information in relation to main- & substream motion detection & deepstack analysis in this thread: https://blueirissoftware.com/forum/viewtopic.php?f=16&t=2535

I had the same issue. Rolled back to 5.5.1.20

I just downloaded and installed the September release: DeepStack September Update

Similar to this thread? https://ipcamtalk.com/threads/deepstack-only-analyzes-3-images-each-time-regardless-of-setting.58375/

I had the same issue. Ken suggested using the substream for DS. Camera Properties > Trigger > Artificial Intelligence > Unselect "Üse main stream if available". Resolved the issue in my case....

5.4.9.14 added tooltips for alert profile numbers & Macros for CPU & Memory usage

Yeah, hit and miss for me too. Also running on iOS and similar configuration activating additional cams when we are out.