Search results

  1. MikeLud1

    CodeProject.AI Version 2.5

    You do not need 6.2 if .NET is working.
  2. MikeLud1

    CodeProject.AI Version 2.5

    Restart Blue Iris service and the custom model list will update. Also uncheck Auto start/stop with Blue Iris:
  3. MikeLud1

    Blue Iris and CodeProject.AI ALPR

    Below are the current AI settings I am using for my ALPR camera.
  4. MikeLud1

    Blue Iris and CodeProject.AI ALPR

    Are you on version 2.8.0, there was an issue with 2.6.5 that was causing .net not to auto restart.
  5. MikeLud1

    CodeProject.AI Version 2.5

    CodeProject.AI will startup as a service so unchecking Auto start/stop with Blue Iris. The issue with modulesettings.json not being updated is fixed in version 2.8.0
  6. MikeLud1

    Blue Iris and CodeProject.AI ALPR

    With your NVIDIA 1080 you should be using CUDA 11.8. To downgrade to CUDA 11.8 you need to uninstall all versions of CUDA that are installed, uninstall cuDNN, uninstall the ALPR module. After uninstall reboot your PC then install CUDA 11.8, reboot, install cuDNN for CUDA 11, reboot, and then...
  7. MikeLud1

    Blue Iris and CodeProject.AI ALPR

    You can switch to YOLOv8 if you want, I normal use YOLOv5 .NET, I find it to be faster then YOLOv5 6.2 and YOLOv8.
  8. MikeLud1

    Blue Iris and CodeProject.AI ALPR

    Try uninstall the ALPR module then reinstall using Do not use download cache
  9. MikeLud1

    CodeProject.AI Version 2.5

    You can specify the percentage to use for the batch, I would try 0.85 or 0.90. For cache you can use the disk. Below is a link to all the training argument...
  10. MikeLud1

    CodeProject.AI Version 2.5

    For the medium model 6 minutes looks normal. Try the below settings, cache=True will help with the speed, batch=-1 will automatically adjust the batch size to maximize your GPU memory, patience=10 will stop the training early if the model does not improve for 10 epochs epochs=300 imgsz=640...
  11. MikeLud1

    CodeProject.AI Version 2.5

    When training does your GPU Utilization % go up. Also what model size are you using? I normally use model=yolov8s.yaml. Below is what I use to start the training yolo train data=plate.yaml model=yolov8s.yaml epochs=300 imgsz=640 cache=True batch=-1 patience=10 workers=8
  12. MikeLud1

    CodeProject.AI Version 2.5

    The epoch should be faster with the 3090. How are you training, using CodeProject.AI or Python command prompt
  13. MikeLud1

    CodeProject.AI Version 2.5

    Do you have an Nvidia GPU? The GPU will greatly speedup the epochs
  14. MikeLud1

    CodeProject.AI Version 2.5

    You may want to try training with about 180 to 200 epochs, with this amount of epochs the model will reach its best accuracy.
  15. MikeLud1

    Blue Iris and CodeProject.AI ALPR

    I have seen several people ask about having just OCR. It would be best to ask Blue Iris to have an OCR option that sends the imager to the OCR module.
  16. MikeLud1

    Blue Iris and CodeProject.AI ALPR

    Try the below settings
  17. MikeLud1

    Blue Iris and CodeProject.AI ALPR

    You can go with the current versions of B.I. & CPAI
  18. MikeLud1

    Blue Iris and CodeProject.AI ALPR

    For your GPU install CUDA 11.8 first and then run install_cuDNN.bat
  19. MikeLud1

    Blue Iris and CodeProject.AI ALPR

    Go with CUDA 12.4, uninstall the current CUDA version then install v12.4, after installing then reboot.
  20. MikeLud1

    Blue Iris and CodeProject.AI ALPR

    It looks like CUDA did not setup the paths. Try reinstalling CUDA then reboot.
  21. MikeLud1

    Blue Iris and CodeProject.AI ALPR

    Open a Command Prompt and run set and post the results. Also post a screenshot of the below folder
  22. MikeLud1

    Blue Iris and CodeProject.AI ALPR

    Did you reboot? so the paths get updated
  23. MikeLud1

    Blue Iris and CodeProject.AI ALPR

    It looks like you do not have cuDNN installed. Run install_cuDNN.bat then restart the PC
  24. MikeLud1

    CodeProject.AI Version 2.5

    I was just going to send the configuration file with AutoStart changed to "true". There is a bug that is not saving any setting from the default settings.
  25. MikeLud1

    Blue Iris and CodeProject.AI ALPR

    It looks like you had CUDA 10 installed at one time. Go into Apps & features and search CUDA and uninstall any app that is not CUDA 11.8. Also run set in a command prompt and post the results
  26. MikeLud1

    Blue Iris and CodeProject.AI ALPR

    I am finding older GPU are very finnicky on what version CUDA and cuDNN is installed. Try uninstalling CUDA 11.8 and install CUDA 11.2 also install cuDNN v8.2.1. After changing the CUDA and cuDNN versions uninstall the ALPR module restart CP.AI then reinstall the ALPR module. If this does not...
  27. MikeLud1

    Blue Iris and CodeProject.AI ALPR

    Try replacing the cuDNN version with the bellow version. Delete the highlighted folders and replace them with the cuDNN version in the below link. After change the cuDNN version restart CP.AI server...
  28. MikeLud1

    Blue Iris and CodeProject.AI ALPR

    It looks like you are running a VM, did you obtain a license for the GRID P100-16Q driver. I am still not sure if this is the issue, what GPU do you have, is it a P100.
  29. MikeLud1

    Waterproof Junction for 4 strings of POE?

    I mounted mine in this box https://www.amazon.com/gp/product/B085QCT543/ref=ppx_yo_dt_b_search_asin_title?ie=UTF8&th=1
  30. MikeLud1

    Waterproof Junction for 4 strings of POE?

    You do not need any POE ports just an ethernet port when using a PoE Injector https://www.amazon.com/dp/B0BCV19QJR?ref=ppx_yo2ov_dt_b_product_details&th=1&tag=ipctk-20
Top Bottom