Recent content by tedrpi

I upgraded the graphics card in my gaming system which meant my BI system got an upgrade too. I have my old GeForce GTX 1650 Low Profile 4G graphics card that I pulled. It's still one of the best low profile cards that doesn't need external power supply. Great for minimalist, mini-itx, or low...

Anyone try the 2.5.5 update? I tired and couldn't get the status page (localhost:32168) to load, reverting to 2.5.4 now.

You can get adapters that convert regular wire conductors to Ethernet POE, speeds are 100 mbps but for just one camera they work great. The 2wire to POE adapters can be expensive, I found one used on eBay. See my post here: New Reolink Wired POE Doorbell Cam ?

Sent a DM

@MikeLud1 - thank you so much for this info, didn't see it anywhere in the documentation or CPAI forums. Not sure what fixed what but manually installing cuDNN for Windows 12.2, installing CPAI 2.5.1, switching to Yolo .NET, and disabling BI start stop control of CPAI has resulted in a much more...

I upgraded my gaming box, with the old becoming my new BI host. Selling my old BI box. I was able to easily run 8 camera's recording full time, with CPAI doing object classification on all camera's using the large model. The low profile 1030 graphics card works with both DeepStack and CPAI...

For anyone wondering you still need to install the cuDUNN install script after installing the CUDA drivers and toolkit. CPAI buries the link on the GPU page that still links to 2.3.2 here: GPUs, TPUs, NPUs - CodeProject.AI Server v2.3.2

Just did that again, sent you a DM with full logs.

C:\Users\tedrpi>nvcc --version nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2023 NVIDIA Corporation Built on Fri_Sep__8_19:56:38_Pacific_Daylight_Time_2023 Cuda compilation tools, release 12.3, V12.3.52 Build cuda_12.3.r12.3/compiler.33281558_0

Just one version of CUDA installed, 12.3. I uninstalled CUDA and made sure all Nvidia folders were deleted prior to the re-install I did yesterday. The error message for v.10 has been there since initial install, I never had v.10 installed. Any idea why LPR thinks otherwise? Yolo is working fine...

Yup, 2.3.4, see below. Server version: 2.3.4-Beta System: Windows Operating System: Windows (Microsoft Windows 11 version 10.0.22631) CPUs: 11th Gen Intel(R) Core(TM) i5-11400F @ 2.60GHz (Intel) 1 CPU x 6 cores. 12 logical processors (x64) GPU...

Still no luck, also tried completely removing CPAI, CUDA and reinstalling. @ChrisMaunder mentioned a potential issue with PaddlePaddle updated to v2.5.2 (up from 2.5.1) causing issues with GPU support, has that been resolved? Under ALPR info I see: Module 'License Plate Reader' 2.7.2 (ID...

Server version: 2.3.4-Beta System: Windows Operating System: Windows (Microsoft Windows 11 version 10.0.22631) CPUs: 11th Gen Intel(R) Core(TM) i5-11400F @ 2.60GHz (Intel) 1 CPU x 6 cores. 12 logical processors (x64) GPU: NVIDIA GeForce GTX...

@ChrisMaunder - Any updates on when LPR will be GPU enabled again? I'm seeing this in the logs if it helps: 08:16:01:Object Detection (YOLOv5 6.2): Rec'd request for Object Detection (YOLOv5 6.2) command 'list-custom' (...7ec8f1) took 2ms 08:16:02:ALPR_adapter.py: W1110 08:16:02.295920 12708...

This looks to be the issue, I tried using the json @MikeLud1 posted with out luck, and did a fresh install on a new box with a 1660 card and LPR is still using the CPU. I'll keep an eye out for a new version of ALPR. Thanks for the updates.