Skip to content
  • Categories
  • Recent
  • Tags
  • Popular
  • World
  • Users
  • Groups
Skins
  • Light
  • Cerulean
  • Cosmo
  • Flatly
  • Journal
  • Litera
  • Lumen
  • Lux
  • Materia
  • Minty
  • Morph
  • Pulse
  • Sandstone
  • Simplex
  • Sketchy
  • Spacelab
  • United
  • Yeti
  • Zephyr
  • Dark
  • Cyborg
  • Darkly
  • Quartz
  • Slate
  • Solar
  • Superhero
  • Vapor

  • Default (No Skin)
  • No Skin
Collapse
Code Project
  1. Home
  2. Feature Forums
  3. - Uncategorised posts -
  4. Blue Iris, CPU Detection working, GPU causing it to crash and be unresponsive.

Blue Iris, CPU Detection working, GPU causing it to crash and be unresponsive.

Scheduled Pinned Locked Moved - Uncategorised posts -
helpperformancetutoriallounge
6 Posts 6 Posters 10 Views 1 Watching
  • Oldest to Newest
  • Newest to Oldest
  • Most Votes
Reply
  • Reply as topic
Log in to reply
This topic has been deleted. Only users with topic management privileges can see it.
  • J Offline
    J Offline
    Jordan Reardon
    wrote on last edited by
    #1

    I have one instance set up and working on another computer I did all the same steps (at least I think) to set it up on another computer, it works with CPU detection, but since it's an i3 I am trying to get the GPU detection working I am using an EVGA 1070 and I get this error on the log screen. Object Detection (YOLO): (General Exception) : CUDA error: an illegal memory access was encountered :confused: I am not sure how to troubleshoot the issue, I cloned the hard-drive from the working machine downloaded the 1070 driver and still received the same error. I appreciate any help you have to give.

    Richard DeemingR S A 3 Replies Last reply
    0
    • J Jordan Reardon

      I have one instance set up and working on another computer I did all the same steps (at least I think) to set it up on another computer, it works with CPU detection, but since it's an i3 I am trying to get the GPU detection working I am using an EVGA 1070 and I get this error on the log screen. Object Detection (YOLO): (General Exception) : CUDA error: an illegal memory access was encountered :confused: I am not sure how to troubleshoot the issue, I cloned the hard-drive from the working machine downloaded the 1070 driver and still received the same error. I appreciate any help you have to give.

      Richard DeemingR Offline
      Richard DeemingR Offline
      Richard Deeming
      wrote on last edited by
      #2

      Assuming this question relates to CodeProject.AI, there's a specific forum for discussing it: CodeProject.AI Discussions[^]


      "These people looked deep within my soul and assigned me a number based on the order in which I joined." - Homer

      "These people looked deep within my soul and assigned me a number based on the order in which I joined" - Homer

      P T 2 Replies Last reply
      0
      • J Jordan Reardon

        I have one instance set up and working on another computer I did all the same steps (at least I think) to set it up on another computer, it works with CPU detection, but since it's an i3 I am trying to get the GPU detection working I am using an EVGA 1070 and I get this error on the log screen. Object Detection (YOLO): (General Exception) : CUDA error: an illegal memory access was encountered :confused: I am not sure how to troubleshoot the issue, I cloned the hard-drive from the working machine downloaded the 1070 driver and still received the same error. I appreciate any help you have to give.

        S Offline
        S Offline
        Sean Ewington
        wrote on last edited by
        #3

        Do you have the CUDA drivers installed and the GPU enabled? CodeProject.AI Server: AI the easy way.[^]

        Thanks, Sean Ewington CodeProject

        1 Reply Last reply
        0
        • Richard DeemingR Richard Deeming

          Assuming this question relates to CodeProject.AI, there's a specific forum for discussing it: CodeProject.AI Discussions[^]


          "These people looked deep within my soul and assigned me a number based on the order in which I joined." - Homer

          P Offline
          P Offline
          Provident Ecopolitan Bagalur
          wrote on last edited by
          #4

          I'm not able to edit.

          1 Reply Last reply
          0
          • Richard DeemingR Richard Deeming

            Assuming this question relates to CodeProject.AI, there's a specific forum for discussing it: CodeProject.AI Discussions[^]


            "These people looked deep within my soul and assigned me a number based on the order in which I joined." - Homer

            T Offline
            T Offline
            Th o Nguyen Sep2023
            wrote on last edited by
            #5

            Thank you very much for the information you have provided. Hope you will have more interesting information
            https://drallen.com.vn/
            https://saigonsmilespa.com.vn/

            1 Reply Last reply
            0
            • J Jordan Reardon

              I have one instance set up and working on another computer I did all the same steps (at least I think) to set it up on another computer, it works with CPU detection, but since it's an i3 I am trying to get the GPU detection working I am using an EVGA 1070 and I get this error on the log screen. Object Detection (YOLO): (General Exception) : CUDA error: an illegal memory access was encountered :confused: I am not sure how to troubleshoot the issue, I cloned the hard-drive from the working machine downloaded the 1070 driver and still received the same error. I appreciate any help you have to give.

              A Offline
              A Offline
              Ashley Madison
              wrote on last edited by
              #6

              It seems like you're encountering a CUDA error related to GPU detection while setting up an instance on a computer with an EVGA 1070 graphics card. This error message, "CUDA error: an illegal memory access was encountered," can be frustrating, but there are steps you can take to troubleshoot and resolve the issue.

              1. **Driver Installation**: It's good that you've downloaded the 1070 driver, but make sure you've installed it correctly. Sometimes, issues can arise if the driver installation is not complete. Ensure that you've installed the latest and compatible GPU driver for your EVGA 1070.

              2. **CUDA Toolkit**: CUDA errors often indicate problems with the CUDA Toolkit installation. Make sure you have the appropriate CUDA Toolkit version installed for your GPU. You might need to uninstall the current CUDA Toolkit and reinstall it to ensure it's properly configured.

              3. **Check GPU Compatibility**: Confirm that your EVGA 1070 is compatible with the deep learning framework or software you're using for object detection. Some older GPUs may not be fully supported by certain frameworks, leading to compatibility issues.

              4. **CUDA Version**: Ensure that the version of CUDA you're using is compatible with your GPU and the software you're running. Mismatched versions can cause problems. Make sure you've installed a CUDA version that is known to work well with your hardware and software.

              5. **Memory Issues**: The error message mentions "illegal memory access." It's possible that there could be issues with your GPU's memory or the way it's being utilized. Check if there are any memory-related problems with your EVGA 1070, such as overheating or faulty RAM.

              6. **Library Dependencies**: Sometimes, CUDA errors can be related to missing or incorrect library dependencies. Ensure that all the necessary libraries and dependencies are correctly installed and up to date.

              7. **Software Configuration**: Review your software's configuration settings, especially those related to GPU usage. Double-check that you've configured the software to utilize the GPU for object detection properly.

              8. **Log Analysis**: Take a closer look at the error log for any additional details that might pinpoint the issue more precisely. Sometimes, specific error codes or messages within the log can provide valuable insights into what's going wrong.

              9. **Community Support**: If you've tried all the above steps and are still facing issues, consider seeking help from online forums or communities

              1 Reply Last reply
              0
              Reply
              • Reply as topic
              Log in to reply
              • Oldest to Newest
              • Newest to Oldest
              • Most Votes


              • Login

              • Don't have an account? Register

              • Login or register to search.
              • First post
                Last post
              0
              • Categories
              • Recent
              • Tags
              • Popular
              • World
              • Users
              • Groups