Search results

  1. harleyl7

    CodeProject.AI Version 2.0

    shouldnt this say License Plate Reader?
  2. harleyl7

    CodeProject.AI Version 2.0

    I restarted the server, and 11.8 is installing now. guessing it needed a restart after the geforce experience drivers update going to reinstall LPR module.
  3. harleyl7

    CodeProject.AI Version 2.0

    Hmm.. all I did driver wise was use geforce experience to update to the newest drivers.
  4. harleyl7

    CodeProject.AI Version 2.0

    I was trying to install the toolkit, but says other installations are running. However, on system info on CPAI I see this: Also on the dashboard it shows CUDA. so do I still need CUDA toolkit and the cuDNN? is the 3GB 1060 enough or should I hook up the 1080?
  5. harleyl7

    CodeProject.AI Version 2.0

    Okay last question haha where do I get those?
  6. harleyl7

    CodeProject.AI Version 2.0

    Thank you! Next on my list is LPR. Does LPR only use CUDA? So I need to get the CUDA drivers?
  7. harleyl7

    CodeProject.AI Version 2.0

    Sweet thank you. I'll stick with .NET then. Will it also be listed as directML? Do you have a picture of your dashboard recently? Also, setting from the main AI tab on BI.
  8. harleyl7

    CodeProject.AI Version 2.0

    Which module do I use for a GTX 1060?
  9. harleyl7

    CodeProject.AI Version 2.0

    Yeah I found some screenshots you posted and implemented those settings. Maybe the i5-6500 just isn't up to the task for faster detection times.
  10. harleyl7

    CodeProject.AI Version 2.0

    Just doing a little testing and it seems my docker container with E2176G .NET, no iGPU running does much better than i5-6500 iGPU (DirectML). I dont have the exact response time from the CPU from docker on unraid. but on directml w/ i5-6500 its like this: 18:36:42:Client request 'custom' in...
  11. harleyl7

    CodeProject.AI Version 2.0

    this seems to be passing through to VMs - I just think DirectML doesn't work with Linux
  12. harleyl7

    CodeProject.AI Version 2.0

    ahh directML might only be available via windows/windows docker with WSL. Time to break out the 3080... only if I could fit it in the 2u server rack lol
  13. harleyl7

    CodeProject.AI Version 2.0

    I believe so, really hard to confirm that it worked unless I'm missing something on CPAI dashboard
  14. harleyl7

    CodeProject.AI Version 2.0

    Tried this and walked around my cameras, detection worked, but didn't switch to DirectML
  15. harleyl7

    CodeProject.AI Version 2.0

    Doing this on docker. Confirmed on unRAID that it's seeing my igpu from my e2176g. Passed it through to the container by adding a device to the docker container /dev/dri/
  16. harleyl7

    CodeProject.AI Version 2.0

    @MikeLud1 passed it through, but doesn't seem to be switching from CPU to directML. Anything I need to do to force it? Or should try and good ole uninstall reinstall module?
  17. harleyl7

    CodeProject.AI Version 2.0

    Awesome thanks. Gonna try passing it through now to the container - using this for the time being until they get the coral stuff more refined/custom models for it. Gotta use the MikeLud Models!
  18. harleyl7

    CodeProject.AI Version 2.0

    Anyway to confirm that it's using the igpu?
  19. harleyl7

    CodeProject.AI Version 2.0

    Does YOLO work with igpu on Intel CPUs?
  20. harleyl7

    To virtualize or not

    Substreams yes. I will go through the optimization guide again. Never felt the need because it does so well. Mainly was just trying to save power haha but it seems the baremetal is so efficient that it might not matter.
  21. harleyl7

    To virtualize or not

    So I had some time today and I'm trying to figure out if I should put Blue iris on a VM or keep it baremetal VM is 4vCPUs from an E2176G w/ 8GB ram allocated Baremetal is i5-6500 with 16gb RAM. Here's my little test: VM 4 vCPUs: Idle: 10-11% All cams ui3: 11-15% One cam ui3: 24-40% Power...
  22. harleyl7

    Coral Accelerator unRAID Docker with CodeProject.AI Guide

    I made a little guide on GitHub so I can keep it updated in one spot as fixes come out. https://github.com/HarleyL7/unRAID-CoralTPU-Guide Hope this helps anyone trying to host CPAI on unRAID via Docker. If this post isn't allowed, feel free to remove it.
  23. harleyl7

    CodeProject.AI Version 2.0

    Just got it working as I saw this notification haha. I'm gonna do a write up on it since there doesn't seem to be clear instructions out there for the most part. Note: it hasn't been tested yet, but I have the m.2 tpu being detected by the unRAID docker CPAI
  24. harleyl7

    CodeProject.AI Version 2.0

    @CCTVCam Are you running CPAI in docker? I am on unraid and I cant seem to get the docker container to identify the TPU. However, UnRaid can see it. on CPAI Dashboard will it be listed in the system info?
  25. harleyl7

    CodeProject.AI Version 2.0

    I'd appreciate it. I know some people have shared pictures of their settings and which custom models to use.
  26. harleyl7

    CodeProject.AI Version 2.0

    Ah gotcha. I meant settings for using my i5-6500 for the time being. It's been awhile since I updated BI/CPAI and seems what people use for settings changes a lot.
  27. harleyl7

    CodeProject.AI Version 2.0

    anyone want to share their settings? I have an i5-6500. What module do I use and which models/settings do I use in BI? Any help would be appreciated.
  28. harleyl7

    CodeProject.AI Version 2.0

    How was your edge set up?
  29. harleyl7

    CodeProject.AI Version 2.0

    Ordered a m.2 coral today. Should be here tomorrow hopefully. I need to update BI and CPAI before I get started. I am going to try first moving my BI to a Windows 10 VM on unRAID. Should I run CPAI on the windows 10 VM or on docker via unRAID? Anything else I should know about getting the...
  30. harleyl7

    Working combo, Asrock Deskmini A300 (AMD) and m.2 Coral TPU

    Just purchased an m.2 in the US via eBay for 69 bucks. Birthday gift from someone else so they didn't mind paying the high fee. Excited to test it out with CPAI on my unRAID server via a VM vs adding it to my BI baremetal server