|
I've been troubleshooting your error, and based on what I've been reading VIDEO TDR FAILURE nvlddmkm.sys could be anything from a driver issue, to a hardware issue. Unfortunately, updating your drivers is one of the suggested fixes, and you may have some issues with CodeProject.AI Server and the latest drivers (or not, possibly).
Of all the threads and sites I looked at, this looked like the most helpful:
https://www.makeuseof.com/easy-ways-fix-nvlddmkm-sys-error-in-windows-10/[^]
Though, upgrading Windows to solve an issue is preposterous to me and I don't recommend it.
As for the error logs you shared, I would try uninstalling and reinstalling any Object Detection modules that seem to be failing you.
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
hi
i have all work fine. but not continuous like i want
i want that blue iris will triggered almost in continuous time with face recognition
i use it like door locked
so lot people walk into the door
so i want when it detects face that is register it will confirm and send http commands
all work except the part of the continuity
its work every few minutes of break
i also play with the break time, trigger time, send pics per ms
i didn’t get it work
can it been done ?
thanks
yossi
|
|
|
|
|
If I'm understanding correctly, yes, that should be possible. Could you please share your System Info tab from the CodeProject.AI Server dashboard, and the logs from when there are breaks or errors?
Is CodeProject.AI Server, through Blue Iris, at least recognizing the face profiles you've established?
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
hi
1. i’m use blue iris yes
2. its does do the detective and recognize face. but as i say inly few time slowly. and inly when is one person
if its few it cant
3. i mange to do it faster in bi. i put the trigger every 1 sec and without brake time. maybe it will help
p.s. in car plate example of 55-555-55
it confirm it only if inout “ 55 555 55 “
space between the numbers
its bad. because its hard to put list of plates like that’s
if sometimes you will have time for teamviewr. it will be great
also i have gtx 1060 turbo. and since the last updates. its stop to work as gpu.
only the *.net work as gpu
thanks
yossi
|
|
|
|
|
I can't get any recognition.
I attach image.
I attach output from AI server.
Can anyone tell me where I'm wrong?
20:51:58:System: Windows
20:51:58:Operating System: Windows (Microsoft Windows 10.0.19045)
20:51:58:CPUs: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz (Intel)
20:51:58: 1 CPU x 4 cores. 8 logical processors (x64)
20:51:58:GPU: NVIDIA GeForce GT 730 (2 GiB) (NVIDIA)
20:51:58: Driver: 10.18.13.6839
20:51:58:System RAM: 8 GiB
20:51:58:Target: Windows
20:51:58:BuildConfig: Release
20:51:58:Execution Env: Native
20:51:58:Runtime Env: Production
20:51:58:.NET framework: .NET 7.0.14
20:51:58:App DataDir: C:\ProgramData\CodeProject\AI
20:51:58:Video adapter info:
20:51:58: NVIDIA GeForce GT 730:
20:51:58: Driver Version 10.18.13.6839
20:51:58: Video Processor GeForce GT 730
20:51:58:STARTING CODEPROJECT.AI SERVER
20:51:58:RUNTIMES_PATH = d:\Program Files\CodeProject\AI\runtimes
20:51:58:PREINSTALLED_MODULES_PATH = d:\Program Files\CodeProject\AI\preinstalled-modules
20:51:58:MODULES_PATH = d:\Program Files\CodeProject\AI\modules
20:51:58:PYTHON_PATH = \bin\windows\%PYTHON_DIRECTORY%\venv\Scripts\python
20:51:58:Data Dir = C:\ProgramData\CodeProject\AI
20:51:58:Server version: 2.3.4-Beta
20:52:01:
20:52:01:Module 'Object Detection (YOLOv5 6.2)' 1.7.1 (ID: ObjectDetectionYolo)
20:52:01:Module Path: d:\Program Files\CodeProject\AI\modules\ObjectDetectionYolo
20:52:01:AutoStart: True
20:52:01:Queue: objectdetection_queue
20:52:01:Platforms: all
20:52:01:GPU Libraries: installed if available
20:52:01:GPU Enabled: enabled
20:52:01:Parallelism: 0
20:52:01:Accelerator:
20:52:01:Half Precis.: enable
20:52:01:Runtime: python3.7
20:52:01:Runtime Loc: Shared
20:52:01:FilePath: detect_adapter.py
20:52:01:Pre installed: False
20:52:01:Start pause: 1 sec
20:52:01:LogVerbosity:
20:52:01:Valid: True
20:52:01:Environment Variables
20:52:01:APPDIR = %CURRENT_MODULE_PATH%
20:52:01:CUSTOM_MODELS_DIR = %CURRENT_MODULE_PATH%/custom-models
20:52:01:MODELS_DIR = %CURRENT_MODULE_PATH%/assets
20:52:01:MODEL_SIZE = Medium
20:52:01:USE_CUDA = True
20:52:01:YOLOv5_AUTOINSTALL = false
20:52:01:YOLOv5_VERBOSE = false
20:52:01:
20:52:01:Started Object Detection (YOLOv5 6.2) module
20:52:02:
20:52:02:Module 'Face Processing' 1.8.1 (ID: FaceProcessing)
20:52:02:Module Path: d:\Program Files\CodeProject\AI\modules\FaceProcessing
20:52:02:AutoStart: True
20:52:02:Queue: faceprocessing_queue
20:52:02:Platforms: windows,linux,linux-arm64,macos,macos-arm64
20:52:02:GPU Libraries: installed if available
20:52:02:GPU Enabled: enabled
20:52:02:Parallelism: 0
20:52:02:Accelerator:
20:52:02:Half Precis.: enable
20:52:02:Runtime: python3.7
20:52:02:Runtime Loc: Shared
20:52:02:FilePath: intelligencelayer\face.py
20:52:02:Pre installed: False
20:52:02:Start pause: 3 sec
20:52:02:LogVerbosity:
20:52:02:Valid: True
20:52:02:Environment Variables
20:52:02:APPDIR = %CURRENT_MODULE_PATH%\intelligencelayer
20:52:02:DATA_DIR = %DATA_DIR%
20:52:02:MODE = MEDIUM
20:52:02:MODELS_DIR = %CURRENT_MODULE_PATH%\assets
20:52:02:PROFILE = desktop_gpu
20:52:02:USE_CUDA = True
20:52:02:YOLOv5_AUTOINSTALL = false
20:52:02:YOLOv5_VERBOSE = false
20:52:02:
20:52:02:Started Face Processing module
20:52:22:Server: This is the latest version
15:22:44:Module FaceProcessing has shutdown
15:22:44:Module ObjectDetectionYolo has shutdown
15:22:44:detect_adapter.py: has exited
15:22:44:face.py: has exited
Paolo
|
|
|
|
|
Before installing Codeproject.AI did you install CUDA 11.8 and cuDNN for CUDA 11.x
|
|
|
|
|
|
I found the same thing, it says CUDA drivers are there, then says it's not present.
|
|
|
|
|
I didn't update any graphics drivers and it worked fine until version 2.2.4.
Now the installation of version 2.3.4 claims that CUDA isn't available and GPU mode can't be activated any longer.
Any ideas? Unfortunately I must restore the last version now, but would appreciate if I could update to the newest one.
|
|
|
|
|
After updating to 2.3.4 did you update the modules?
Also can you provide more details, which module and install log for the module.
|
|
|
|
|
|
Any idea how to solve this? If necessary I repeat the installation and safe the log but as I already mentioned the only difference is the detection result for CUDA 2.3.4 -> false and 2.2.4 -> true. All other settings and drivers are unchanged.
|
|
|
|
|
Maybe try CUDA 11.7? It's working for me with an RTX 3060 and AIServer 2.3.4.
|
|
|
|
|
At a terminal window, can you run the nvidia-smi command and then the nvcc --version command and let me know what it shows?
cheers
Chris Maunder
|
|
|
|
|
"nvcc --version" is unknown
|
|
|
|
|
Since nvcc --version did not work it looks like you do not have CUDA installed.
Post a screenshot of Windows Apps & features searching CUDA
|
|
|
|
|
Very interesting. You are right. But I wonder why it works without any issue with version 2.2.4 and older. I thought, all parts were installed with the NVidia driver.
and
I'm downloading the current version and try it again.
|
|
|
|
|
I am having the same issue upgrading from 2.1 to 2.3.4. GPU was working great with 2.1 and now I am unable to see GPU as an option. I have a GTX 1050 in this Windows 11 system.
After seeing that GPU wasn't there for 2.3.4 I updated the NVIDIA drivers to the current version (546.17). Finding this thread I also downloaded and installed NVIDIA CUDA Toolkit 12.3 which forced a reboot and I still don't see GPU as an option. Using the Install Modules tab I uninstalled Face Processing and all of the Object Detection modules, then re-installed YOLOv5 6.2. In the logs I also see "07:13:56:ObjectDetectionYolo: CUDA Present...No".
nvidia-smi gives me this:
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 546.17 Driver Version: 546.17 CUDA Version: 12.3 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name TCC/WDDM | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 NVIDIA GeForce GTX 1050 WDDM | 00000000:01:00.0 Off | N/A |
| N/A 45C P8 N/A / ERR! | 0MiB / 3072MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
+---------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
| No running processes found |
+---------------------------------------------------------------------------------------+
nvcc command isn't found and NVIDA CUDA Toolkit 12.3 is installed.
|
|
|
|
|
Try rebooting then run nvcc - version
|
|
|
|
|
I was initially forced to reboot by the CUDA installation and have rebooted twice since, nvcc is still not there. This is on my BlueIris machine so I do not have Visual Studio installed. When installing CUDA it did give a warning that some things may not work due to not having Visual Studio, but it doesn't seem like that should be a requirement for running the AI server.
After a complete uninstall of 2.3.4 and re-installing 2.1.11 (the latest version I had working) during the YOLO module installation I do get
10:31:59:ObjectDetectionYolo: CUDA Present...True in the logs and GPU works fine.
|
|
|
|
|
That's same for me. The issue appears after reinstalling (I always remove the old version) with version 2.3.4. Downgrading (same way, complete reinstall) to 2.2.4 as my last stable version it detects CUDA and works.
It seems that there was a change in detection of CUDA version between 2.2.4 and 2.3.4. Later I retry the installation of 2.3.4. Hopefully it works, because I don't want to freeze version 2.2.4 as last running version, especially because BI may cause issues with newer versions thereafter.
|
|
|
|
|
I was now able to get 2.3.4 working with CUDA on my GTX 1050 machine. Since the CUDA install warned me that Visual Studio wasn't installed and nvcc wasn't found I decided to go back and install Visual Studio Community first. I then re-installed CUDA 12.3 which no longer warned me about missing VS and reported some addition items installed when it completed. Running nvcc from the command line was now found and reported some details.
I then uninstalled and deleted the remaining files from my CodeProject.AI install, rebooted, then re-installed the server. CUDA Present...Yes (version 12.3) was reported in the status logs this time and Face and Object Detection are now able to use the GPU.
So something certainly changed between versions and there is some requirement missing.
|
|
|
|
|
I've pinned down the reason and it's an issue where we're assuming nvcc will always be available in Windows when CUDA is installed, which isn't the case. This issue doesn't affect Linux (we check nvcc and nvidia-smi).
For those who can't wait:
In C:\Program Files\CodeProject\AI\SDK\Scripts is a file utils.bat . In that is a method :GetCudaVersion. Replace what you have with this:
:GetCudaVersion
where nvcc >nul 2>&1
if !errorlevel! == 0 (
for /f "tokens=*" %%i in ('nvcc --version ^| findstr /C:"release"') do set cudaLine=%%i
for /f "tokens=5 delims=, " %%a in ("!cudaLine!") do set cuda_version=%%a
) else (
where nvidia-smi >nul 2>&1
if !errorlevel! == 0 (
for /f "tokens=*" %%i in ('nvidia-smi ^| findstr /C:"CUDA Version"') do set cudaLine=%%i
for /f "tokens=9 delims= " %%a in ("!cudaLine!") do set cuda_version=%%a
) else (
)
)
if "!cuda_version!" neq "" (
for /f "tokens=1,2 delims=." %%a in ("!cuda_version!") do (
set "cuda_major_version=%%a"
exit /b
)
)
exit /b
cheers
Chris Maunder
modified 30-Nov-23 9:43am.
|
|
|
|
|
Thank you for troubleshooting. I wait for the fix in next version.
|
|
|
|
|
I edited my previous message to include the fix in case you wanted to try that immediately
cheers
Chris Maunder
|
|
|
|