I5 6500t igpu with a medium yolov11 model is average 270ms.
The times are on par with a gtx1660 (AI server was hosted on another pc) running blue onyx with the largest ONNX model.
However I find the accuracy significantly better. No false positives in over 3 days of running (>10000 requests)...
Sounds good.
Early days but I've never seen such strong igpu utilisation.
Openvino is impressive.
Thank you for writing this code. I didn't expect such good performance on my ancient processor. Very accurate and fast.
I'll keep an eye on how it handles load when overloaded with triggers.
looks amazing so far. using medium yolo11 model on an i5 6500T the inference times on analysis looks really good. will report back findings.
whats the best way to ensure server is always running on crash or system restart?. A task schedule with a batch script ?
Now unable to download the models, got a certificate error -> Download Fehler: <urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1035)>
CRITICAL ERROR: <urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify...
yeah I have vcredist
I am not installing the NPU driver as its an I5 6500 .
I must have messed up the openvino installation somehow. I downloaded v2025.4.1, chucked it here -> C:\Program Files (x86)\Intel\openvino_2025.4.1 and setup a whole heap of env variables. setupvars says successful...
So I've been having the same problem with android notifications for a couple of days now.
Had a question , has anyone tried triggering a test notification in the BI alert window ?. It used to say success or something and send a notification to my phone but now it says-> action skipped (disabled...