Blue Iris and CodeProject.AI ALPR
- Thread starter MikeLud1
- Start date
DJBWSM
n3wb
@MikeLud1 Help. Now spent 3 days ripping my hair out.
I have read the 52 pages on this post looking for answers and tried every suggestion you recommend to others. Still I cannot get APLR working with my GPU. Works fine with CPU but is slow.
This is what happens the first couple of time then nothing is found.
Status Page:
NVCC Output:
I have read the 52 pages on this post looking for answers and tried every suggestion you recommend to others. Still I cannot get APLR working with my GPU. Works fine with CPU but is slow.
This is what happens the first couple of time then nothing is found.
Server version: 2.6.5
System: Windows
Operating System: Windows (Microsoft Windows 10.0.19045)
CPUs: Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (Intel)
2 CPUs x 8 cores. 8 logical processors (x64)
GPU (Primary): GRID P100-16Q (16 GiB) (NVIDIA)
Driver: 538.33, CUDA: 11.8.89 (up to: 12.2), Compute: 6.0, cuDNN: 8.9
System RAM: 32 GiB
Platform: Windows
BuildConfig: Release
Execution Env: Native
Runtime Env: Production
Runtimes installed:
.NET runtime: 7.0.20
.NET SDK: 7.0.410
Default Python: Not found
Go: Not found
NodeJS: Not found
Rust: Not found
Video adapter info:
NVIDIA GRID P100-16Q:
Driver Version 31.0.15.3833
Video Processor GRID P100-16Q
System GPU info:
GPU 3D Usage 0%
GPU RAM Usage 2.3 GiB
Global Environment variables:
CPAI_APPROOTPATH = <root>
CPAI_PORT = 32168
System: Windows
Operating System: Windows (Microsoft Windows 10.0.19045)
CPUs: Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (Intel)
2 CPUs x 8 cores. 8 logical processors (x64)
GPU (Primary): GRID P100-16Q (16 GiB) (NVIDIA)
Driver: 538.33, CUDA: 11.8.89 (up to: 12.2), Compute: 6.0, cuDNN: 8.9
System RAM: 32 GiB
Platform: Windows
BuildConfig: Release
Execution Env: Native
Runtime Env: Production
Runtimes installed:
.NET runtime: 7.0.20
.NET SDK: 7.0.410
Default Python: Not found
Go: Not found
NodeJS: Not found
Rust: Not found
Video adapter info:
NVIDIA GRID P100-16Q:
Driver Version 31.0.15.3833
Video Processor GRID P100-16Q
System GPU info:
GPU 3D Usage 0%
GPU RAM Usage 2.3 GiB
Global Environment variables:
CPAI_APPROOTPATH = <root>
CPAI_PORT = 32168
Status Page:
ALLUSERSPROFILE=C:\ProgramData
APPDATA=C:\Users\Dan\AppData\Roaming
CLIENTNAME=DESKTOP-0S742NF
CommonProgramFiles=C:\Program Files\Common Files
CommonProgramFiles(x86)=C:\Program Files (x86)\Common Files
CommonProgramW6432=C:\Program Files\Common Files
COMPUTERNAME=BLUEIRIS-VM
ComSpec=C:\Windows\system32\cmd.exe
CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8
CUDA_PATH_V11_8=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8
DriverData=C:\Windows\System32\Drivers\DriverData
FPS_BROWSER_APP_PROFILE_STRING=Internet Explorer
FPS_BROWSER_USER_PROFILE_STRING=Default
HOMEDRIVE=C:
HOMEPATH=\Users\Dan
LOCALAPPDATA=C:\Users\Dan\AppData\Local
LOGONSERVER=\\BLUEIRIS-VM
NUMBER_OF_PROCESSORS=16
OneDrive=C:\Users\Dan\OneDrive
OS=Windows_NT
Path=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\bin;C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\libnvvp;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0\;C:\Windows\System32\OpenSSH\;C:\Program Files\dotnet\;C:\Users\Dan\AppData\Local\Microsoft\WindowsApps;C:\Users\Dan\.dotnet\tools;C:\Program Files\NVIDIA\CUDNN\v8.9\zlib\dll_x64;C:\Program Files\NVIDIA\CUDNN\v8.9\bin;C:\Users\Dan\AppData\Local\Microsoft\WindowsApps;C:\Users\Dan\.dotnet\tools
PATHEXT=.COM;.EXE;.BAT;.CMD;.VBS;.VBE;.JS;.JSE;.WSF;.WSH;.MSC
PROCESSOR_ARCHITECTURE=AMD64
PROCESSOR_IDENTIFIER=Intel64 Family 6 Model 79 Stepping 1, GenuineIntel
PROCESSOR_LEVEL=6
PROCESSOR_REVISION=4f01
ProgramData=C:\ProgramData
ProgramFiles=C:\Program Files
ProgramFiles(x86)=C:\Program Files (x86)
ProgramW6432=C:\Program Files
PROMPT=$P$G
PSModulePath=C:\Program Files\WindowsPowerShell\Modules;C:\Windows\system32\WindowsPowerShell\v1.0\Modules
PUBLIC=C:\Users\Public
SESSIONNAME=RDP-Tcp#0
SystemDrive=C:
SystemRoot=C:\Windows
TEMP=C:\Users\Dan\AppData\Local\Temp
TMP=C:\Users\Dan\AppData\Local\Temp
USERDOMAIN=BLUEIRIS-VM
USERDOMAIN_ROAMINGPROFILE=BLUEIRIS-VM
USERNAME=Dan
USERPROFILE=C:\Users\Dan
windir=C:\Windows
APPDATA=C:\Users\Dan\AppData\Roaming
CLIENTNAME=DESKTOP-0S742NF
CommonProgramFiles=C:\Program Files\Common Files
CommonProgramFiles(x86)=C:\Program Files (x86)\Common Files
CommonProgramW6432=C:\Program Files\Common Files
COMPUTERNAME=BLUEIRIS-VM
ComSpec=C:\Windows\system32\cmd.exe
CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8
CUDA_PATH_V11_8=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8
DriverData=C:\Windows\System32\Drivers\DriverData
FPS_BROWSER_APP_PROFILE_STRING=Internet Explorer
FPS_BROWSER_USER_PROFILE_STRING=Default
HOMEDRIVE=C:
HOMEPATH=\Users\Dan
LOCALAPPDATA=C:\Users\Dan\AppData\Local
LOGONSERVER=\\BLUEIRIS-VM
NUMBER_OF_PROCESSORS=16
OneDrive=C:\Users\Dan\OneDrive
OS=Windows_NT
Path=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\bin;C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\libnvvp;C:\Windows\system32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0\;C:\Windows\System32\OpenSSH\;C:\Program Files\dotnet\;C:\Users\Dan\AppData\Local\Microsoft\WindowsApps;C:\Users\Dan\.dotnet\tools;C:\Program Files\NVIDIA\CUDNN\v8.9\zlib\dll_x64;C:\Program Files\NVIDIA\CUDNN\v8.9\bin;C:\Users\Dan\AppData\Local\Microsoft\WindowsApps;C:\Users\Dan\.dotnet\tools
PATHEXT=.COM;.EXE;.BAT;.CMD;.VBS;.VBE;.JS;.JSE;.WSF;.WSH;.MSC
PROCESSOR_ARCHITECTURE=AMD64
PROCESSOR_IDENTIFIER=Intel64 Family 6 Model 79 Stepping 1, GenuineIntel
PROCESSOR_LEVEL=6
PROCESSOR_REVISION=4f01
ProgramData=C:\ProgramData
ProgramFiles=C:\Program Files
ProgramFiles(x86)=C:\Program Files (x86)
ProgramW6432=C:\Program Files
PROMPT=$P$G
PSModulePath=C:\Program Files\WindowsPowerShell\Modules;C:\Windows\system32\WindowsPowerShell\v1.0\Modules
PUBLIC=C:\Users\Public
SESSIONNAME=RDP-Tcp#0
SystemDrive=C:
SystemRoot=C:\Windows
TEMP=C:\Users\Dan\AppData\Local\Temp
TMP=C:\Users\Dan\AppData\Local\Temp
USERDOMAIN=BLUEIRIS-VM
USERDOMAIN_ROAMINGPROFILE=BLUEIRIS-VM
USERNAME=Dan
USERPROFILE=C:\Users\Dan
windir=C:\Windows
NVCC Output:
Code:
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2022 NVIDIA Corporation
Built on Wed_Sep_21_10:41:10_Pacific_Daylight_Time_2022
Cuda compilation tools, release 11.8, V11.8.89
Build cuda_11.8.r11.8/compiler.31833905_0Module 'License Plate Reader' 3.1.0 (ID: ALPR)
Valid: True
Module Path: <root>\modules\ALPR
Module Location: Internal
AutoStart: True
Queue: alpr_queue
Runtime: python3.9
Runtime Location: Local
FilePath: ALPR_adapter.py
Start pause: 3 sec
Parallelism: 0
LogVerbosity:
Platforms: all
GPU Libraries: installed if available
GPU: use if supported
Accelerator:
Half Precision: enable
Environment Variables
AUTO_PLATE_ROTATE = True
CROPPED_PLATE_DIR = <root>\Server\wwwroot
MIN_COMPUTE_CAPABILITY = 6
MIN_CUDNN_VERSION = 7
OCR_OPTIMAL_CHARACTER_HEIGHT = 60
OCR_OPTIMAL_CHARACTER_WIDTH = 30
OCR_OPTIMIZATION = True
PLATE_CONFIDENCE = 0.7
PLATE_RESCALE_FACTOR = 2
PLATE_ROTATE_DEG = 0
REMOVE_SPACES = False
ROOT_PATH = <root>
SAVE_CROPPED_PLATE = False
Status Data: {
"inferenceDevice": "GPU",
"inferenceLibrary": "CUDA",
"canUseGPU": "true",
"successfulInferences": 0,
"failedInferences": 0,
"numInferences": 0,
"averageInferenceMs": 0
}
Started: 31 May 2024 8:01:44 PM GMT Standard Time
LastSeen: 31 May 2024 8:03:15 PM GMT Standard Time
Status: Started
Requests: 42 (includes status calls)
Installation Log
2024-05-31 18:18:02: Installing CodeProject.AI Analysis Module
2024-05-31 18:18:02: ======================================================================
2024-05-31 18:18:02: CodeProject.AI Installer
2024-05-31 18:18:02: ======================================================================
2024-05-31 18:18:03: 78.5Gb of 261Gb available on
2024-05-31 18:18:03: General CodeProject.AI setup
2024-05-31 18:18:03: Creating Directories...done
2024-05-31 18:18:03: GPU support
2024-05-31 18:18:04: CUDA Present...Yes (CUDA 11.8, cuDNN 8.9)
2024-05-31 18:18:04: ROCm Present...No
2024-05-31 18:18:06: Checking for .NET 7.0...Checking SDKs...All good. .NET is 7.0.410
2024-05-31 18:18:13: Reading ALPR settings.......done
2024-05-31 18:18:13: Installing module License Plate Reader 3.1.0
2024-05-31 18:18:13: Installing Python 3.9
2024-05-31 18:18:29: Downloading Python 3.9 interpreter...Expanding...done.
2024-05-31 18:19:12: Creating Virtual Environment (Local)...done
2024-05-31 18:19:13: Confirming we have Python 3.9 in our virtual environment...present
2024-05-31 18:19:16: Downloading ALPR models...Expanding...done.
2024-05-31 18:19:16: Copying contents of ocr-en-pp_ocrv4-paddle.zip to paddleocr...done
2024-05-31 18:19:16: Installing Python packages for License Plate Reader
2024-05-31 18:19:16: [0;Installing GPU-enabled libraries: If available
2024-05-31 18:19:21: Ensuring Python package manager (pip) is installed...done
2024-05-31 18:19:56: Ensuring Python package manager (pip) is up to date...done
2024-05-31 18:19:56: Python packages specified by requirements.windows.cuda11_8.txt
2024-05-31 18:22:11: - Installing PaddlePaddle, Parallel Distributed Deep Learning...(✅ checked) done
2024-05-31 18:27:52: - Installing PaddleOCR, the OCR toolkit based on PaddlePaddle...(✅ checked) done
2024-05-31 18:28:03: - Installing imutils, the image utilities library...(✅ checked) done
2024-05-31 18:28:08: - Installing Pillow, a Python Image Library...Already installed
2024-05-31 18:28:12: - Installing OpenCV, the Computer Vision library for Python...Already installed
2024-05-31 18:28:47: - Installing NumPy, a package for scientific computing...Already installed
2024-05-31 18:28:47: Installing Python packages for the CodeProject.AI Server SDK
2024-05-31 18:28:53: Ensuring Python package manager (pip) is installed...done
2024-05-31 18:29:03: Ensuring Python package manager (pip) is up to date...done
2024-05-31 18:29:03: Python packages specified by requirements.txt
2024-05-31 18:29:08: - Installing Pillow, a Python Image Library...Already installed
2024-05-31 18:29:13: - Installing Charset normalizer...Already installed
2024-05-31 18:29:31: - Installing aiohttp, the Async IO HTTP library...(✅ checked) done
2024-05-31 18:29:43: - Installing aiofiles, the Async IO Files library...(✅ checked) done
2024-05-31 18:29:53: - Installing py-cpuinfo to allow us to query CPU info...(✅ checked) done
2024-05-31 18:29:57: - Installing Requests, the HTTP library...Already installed
2024-05-31 18:29:58: Scanning modulesettings for downloadable models...No models specified
2024-05-31 18:29:58: Executing post-install script for License Plate Reader
2024-05-31 18:29:58: Applying PaddleOCR patch
2024-05-31 18:29:58: 1 file(s) copied.
2024-05-31 18:30:49: Self test: Self-test passed
2024-05-31 18:30:49: Module setup time 00:12:41.93
2024-05-31 18:30:49: Setup complete
2024-05-31 18:30:49: Total setup time 00:12:46.69
Installer exited with code 0
Valid: True
Module Path: <root>\modules\ALPR
Module Location: Internal
AutoStart: True
Queue: alpr_queue
Runtime: python3.9
Runtime Location: Local
FilePath: ALPR_adapter.py
Start pause: 3 sec
Parallelism: 0
LogVerbosity:
Platforms: all
GPU Libraries: installed if available
GPU: use if supported
Accelerator:
Half Precision: enable
Environment Variables
AUTO_PLATE_ROTATE = True
CROPPED_PLATE_DIR = <root>\Server\wwwroot
MIN_COMPUTE_CAPABILITY = 6
MIN_CUDNN_VERSION = 7
OCR_OPTIMAL_CHARACTER_HEIGHT = 60
OCR_OPTIMAL_CHARACTER_WIDTH = 30
OCR_OPTIMIZATION = True
PLATE_CONFIDENCE = 0.7
PLATE_RESCALE_FACTOR = 2
PLATE_ROTATE_DEG = 0
REMOVE_SPACES = False
ROOT_PATH = <root>
SAVE_CROPPED_PLATE = False
Status Data: {
"inferenceDevice": "GPU",
"inferenceLibrary": "CUDA",
"canUseGPU": "true",
"successfulInferences": 0,
"failedInferences": 0,
"numInferences": 0,
"averageInferenceMs": 0
}
Started: 31 May 2024 8:01:44 PM GMT Standard Time
LastSeen: 31 May 2024 8:03:15 PM GMT Standard Time
Status: Started
Requests: 42 (includes status calls)
Installation Log
2024-05-31 18:18:02: Installing CodeProject.AI Analysis Module
2024-05-31 18:18:02: ======================================================================
2024-05-31 18:18:02: CodeProject.AI Installer
2024-05-31 18:18:02: ======================================================================
2024-05-31 18:18:03: 78.5Gb of 261Gb available on
2024-05-31 18:18:03: General CodeProject.AI setup
2024-05-31 18:18:03: Creating Directories...done
2024-05-31 18:18:03: GPU support
2024-05-31 18:18:04: CUDA Present...Yes (CUDA 11.8, cuDNN 8.9)
2024-05-31 18:18:04: ROCm Present...No
2024-05-31 18:18:06: Checking for .NET 7.0...Checking SDKs...All good. .NET is 7.0.410
2024-05-31 18:18:13: Reading ALPR settings.......done
2024-05-31 18:18:13: Installing module License Plate Reader 3.1.0
2024-05-31 18:18:13: Installing Python 3.9
2024-05-31 18:18:29: Downloading Python 3.9 interpreter...Expanding...done.
2024-05-31 18:19:12: Creating Virtual Environment (Local)...done
2024-05-31 18:19:13: Confirming we have Python 3.9 in our virtual environment...present
2024-05-31 18:19:16: Downloading ALPR models...Expanding...done.
2024-05-31 18:19:16: Copying contents of ocr-en-pp_ocrv4-paddle.zip to paddleocr...done
2024-05-31 18:19:16: Installing Python packages for License Plate Reader
2024-05-31 18:19:16: [0;Installing GPU-enabled libraries: If available
2024-05-31 18:19:21: Ensuring Python package manager (pip) is installed...done
2024-05-31 18:19:56: Ensuring Python package manager (pip) is up to date...done
2024-05-31 18:19:56: Python packages specified by requirements.windows.cuda11_8.txt
2024-05-31 18:22:11: - Installing PaddlePaddle, Parallel Distributed Deep Learning...(✅ checked) done
2024-05-31 18:27:52: - Installing PaddleOCR, the OCR toolkit based on PaddlePaddle...(✅ checked) done
2024-05-31 18:28:03: - Installing imutils, the image utilities library...(✅ checked) done
2024-05-31 18:28:08: - Installing Pillow, a Python Image Library...Already installed
2024-05-31 18:28:12: - Installing OpenCV, the Computer Vision library for Python...Already installed
2024-05-31 18:28:47: - Installing NumPy, a package for scientific computing...Already installed
2024-05-31 18:28:47: Installing Python packages for the CodeProject.AI Server SDK
2024-05-31 18:28:53: Ensuring Python package manager (pip) is installed...done
2024-05-31 18:29:03: Ensuring Python package manager (pip) is up to date...done
2024-05-31 18:29:03: Python packages specified by requirements.txt
2024-05-31 18:29:08: - Installing Pillow, a Python Image Library...Already installed
2024-05-31 18:29:13: - Installing Charset normalizer...Already installed
2024-05-31 18:29:31: - Installing aiohttp, the Async IO HTTP library...(✅ checked) done
2024-05-31 18:29:43: - Installing aiofiles, the Async IO Files library...(✅ checked) done
2024-05-31 18:29:53: - Installing py-cpuinfo to allow us to query CPU info...(✅ checked) done
2024-05-31 18:29:57: - Installing Requests, the HTTP library...Already installed
2024-05-31 18:29:58: Scanning modulesettings for downloadable models...No models specified
2024-05-31 18:29:58: Executing post-install script for License Plate Reader
2024-05-31 18:29:58: Applying PaddleOCR patch
2024-05-31 18:29:58: 1 file(s) copied.
2024-05-31 18:30:49: Self test: Self-test passed
2024-05-31 18:30:49: Module setup time 00:12:41.93
2024-05-31 18:30:49: Setup complete
2024-05-31 18:30:49: Total setup time 00:12:46.69
Installer exited with code 0
Last edited:
MikeLud1
IPCT Contributor
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.
DJBWSM
n3wb
Yes it is a P100. The "Object Detection (YOLOv5 6.2)" module works very well and quick with the GPU.
DJBWSM
n3wb
Just tried it all have similar results to before.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.
Log in
developer.nvidia.com
View attachment 195637
Any other ideas? (Please dont say replace the gpu )
DJBWSM
n3wb
Here is the log showing it giving random result and then stops and start throwing an error
00:04:14:Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command 'custom'
00:04:15:Object Detection (YOLOv5 6.2): Detecting using license-plate
00:04:15:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...86b95c) ['Found DayPlate'] took 115ms
00:04:15:Response rec'd from License Plate Reader command 'alpr' (...f8fbf8) ['Found Plate: 54310 zsqponmlkhgfedcba ZYXWVUTSRPONMLKJHGFEDCA 876543410 zyxwvutqponmlmjihgfedcba ZYXWVUTSTQPONMLKJHGFEDCBA 98765452 urqponmlkjihgfeba ZYXWVRQPONMNKJIHGFEDC 9876543210 ZYXWVUuCBA e3210 ZYXWVUTSRQPONv 9876543210 V LKJIHGFn 9876 '] took 524ms
00:04:18:Client request 'alpr' in queue 'alpr_queue' (...f03ce4)
00:04:18:Request 'alpr' dequeued from 'alpr_queue' (...f03ce4)
00:04:18:License Plate Reader: Retrieved alpr_queue command 'alpr'
00:04:18:Client request 'custom' in queue 'objectdetection_queue' (...241e39)
00:04:18:Request 'custom' dequeued from 'objectdetection_queue' (...241e39)
00:04:18:Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command 'custom'
00:04:18:Object Detection (YOLOv5 6.2): Detecting using license-plate
00:04:18:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...241e39) ['Found DayPlate'] took 92ms
00:04:18:Response rec'd from License Plate Reader command 'alpr' (...f03ce4) ['Found Plate: yxwvutsrkihgfedc ZYXWVUTSRQPONMLKJHGFEDCB 98765430 yxwvutsrqponmlihgfedeba ZYXWVUTSRQPONMLKLIHGFEDCB 98765410 mjihgfedcba ZYXWVUTSRQPONJIHGFEFCBA 5210 ZYXWVUSRQPONMm 987650 ZYXWVUTSRQPONMLKJIHGFn543210 ZYXWVNvDCBA f43210 '] took 636ms
00:04:21:Client request 'alpr' in queue 'alpr_queue' (...33c6a5)
00:04:21:Request 'alpr' dequeued from 'alpr_queue' (...33c6a5)
00:04:21:License Plate Reader: Retrieved alpr_queue command 'alpr'
00:04:21:Client request 'custom' in queue 'objectdetection_queue' (...ea564b)
00:04:21:Request 'custom' dequeued from 'objectdetection_queue' (...ea564b)
00:04:21:Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command 'custom'
00:04:21:Object Detection (YOLOv5 6.2): Detecting using license-plate
00:04:21:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...ea564b) ['Found DayPlate'] took 123ms
00:04:21:Response rec'd from License Plate Reader command 'alpr' (...33c6a5) ['Found Plate: JIHGFEDl 3210 KJIHGFEu3210 UKJIHGFuDCBA m 9876e50 MLJIHGFGDCBA 9873210 zyxwv'] took 513ms
00:04:23:Client request 'alpr' in queue 'alpr_queue' (...b5ab90)
00:04:23:Request 'alpr' dequeued from 'alpr_queue' (...b5ab90)
00:04:23:License Plate Reader: Retrieved alpr_queue command 'alpr'
00:04:23:Client request 'custom' in queue 'objectdetection_queue' (...00f28b)
00:04:23:Request 'custom' dequeued from 'objectdetection_queue' (...00f28b)
00:04:23:Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command 'custom'
00:04:23:Object Detection (YOLOv5 6.2): Detecting using license-plate
00:04:23:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...00f28b) ['Found DayPlate'] took 97ms
00:04:23:Response rec'd from License Plate Reader command 'alpr' (...b5ab90) ['Found Plate: 9876543210 zyxwvuvsrqponmlkeba ZYXWVUSRQPONM 987650 ZYXWV SRQPON KJIHGFE e3210 ZYXWV EDCBA 543210 V hgfedc YXWVUTSRQPONMLKJHGFEDCBA 8765432 zxwvutsrponmlkihgfedc YXWVUTSRKHGFEDCBA 876543410 yxwvutsrponmlkjihgfeda Z'] took 571ms
00:04:25:Client request 'alpr' in queue 'alpr_queue' (...f6699d)
00:04:25:Request 'alpr' dequeued from 'alpr_queue' (...f6699d)
00:04:25:License Plate Reader: Retrieved alpr_queue command 'alpr'
00:04:25:Client request 'custom' in queue 'objectdetection_queue' (...7fbd71)
00:04:25:Request 'custom' dequeued from 'objectdetection_queue' (...7fbd71)
00:04:25:Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command 'custom'
00:04:25:Object Detection (YOLOv5 6.2): Detecting using license-plate
00:04:25:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...7fbd71) ['Found DayPlate'] took 139ms
00:04:25:Response rec'd from License Plate Reader command 'alpr' (...f6699d) ['Found Plate: ZYXWVUT JIHGFEDl210 T KJIHGFEtD 3210 KJIHGFEtCBA l 98765e0 U zyxwvwtsrqponmlkjihgcba ZYXWVUTSRQPONL'] took 559ms
00:04:27:Client request 'alpr' in queue 'alpr_queue' (...995ed6)
00:04:27:Request 'alpr' dequeued from 'alpr_queue' (...995ed6)
00:04:27:License Plate Reader: Retrieved alpr_queue command 'alpr'
00:04:27:Client request 'custom' in queue 'objectdetection_queue' (...29583c)
00:04:27:Request 'custom' dequeued from 'objectdetection_queue' (...29583c)
00:04:27:Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command 'custom'
00:04:27:Object Detection (YOLOv5 6.2): Detecting using license-plate
00:04:27:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...29583c) ['Found DayPlate'] took 97ms
00:04:28:Response rec'd from License Plate Reader command 'alpr' (...995ed6) ['Found Plate: ZYXWVUTSRQPOKJIHGEDCBA 987643210 zyxwvutsrqponmlkjihgfdcba ZYXWUTSRQPOLKJIHGHEDCBA 743210 zyxwvutsrqponmlkjihghedcba ZYXWVUTSRQPMLKJIHIF zyvutsrqponmlkjfedcbab ZYXWQNMLKJIHGFEDCBA 9i WVUTSRQyGFEDCBq i7654321 QPONMLKJIHGFEDCBr10 Z PONMLKJB'] took 537ms
00:04:29:Client request 'alpr' in queue 'alpr_queue' (...0838e1)
00:04:29:Request 'alpr' dequeued from 'alpr_queue' (...0838e1)
00:04:29:License Plate Reader: Retrieved alpr_queue command 'alpr'
00:04:29:Client request 'custom' in queue 'objectdetection_queue' (...ad144b)
00:04:29:Request 'custom' dequeued from 'objectdetection_queue' (...ad144b)
00:04:29:Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command 'custom'
00:04:29:Object Detection (YOLOv5 6.2): Detecting using license-plate
00:04:29:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...ad144b) ['Found DayPlate'] took 87ms
00:04:30:Response rec'd from License Plate Reader command 'alpr' (...0838e1) ['Found Plate: CBA 987651 zyxwvutsrqponlkjihgfdcba ZYXWTSRQPOPMLKJIHGF 9876543210 zyxwvutsrqpopmlkjihgfdcba ZYXUTSRQPQN zyxwvutsrnmlkjijgfedcba YVUTSRQPONMLKJIGFEDCBAq0 ZY ONMLKJyGFEDCBq 910YXWVUTSRQPONMLKJz987654320 XWVUTSRJ'] took 478ms
00:04:31:Client request 'alpr' in queue 'alpr_queue' (...2572b3)
00:04:31:Request 'alpr' dequeued from 'alpr_queue' (...2572b3)
00:04:31:License Plate Reader: Retrieved alpr_queue command 'alpr'
00:04:31:Client request 'custom' in queue 'objectdetection_queue' (...2f64af)
00:04:31:Request 'custom' dequeued from 'objectdetection_queue' (...2f64af)
00:04:31:Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command 'custom'
00:04:31:Object Detection (YOLOv5 6.2): Detecting using license-plate
00:04:31:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...2f64af) ['Found DayPlate'] took 117ms
00:04:32:Connection id "0HN41OMVGHOM1", Request id "0HN41OMVGHOM1:0000000A": An unhandled exception was thrown by the application.
00:05:05:Client request 'alpr' in queue 'alpr_queue' (...ae6bac)
00:05:05:Request 'alpr' dequeued from 'alpr_queue' (...ae6bac)
00:05:05:License Plate Reader: Retrieved alpr_queue command 'alpr'
00:05:05:Client request 'custom' in queue 'objectdetection_queue' (...1f8455)
00:05:05:Request 'custom' dequeued from 'objectdetection_queue' (...1f8455)
00:05:05:Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command 'custom'
00:05:06:Object Detection (YOLOv5 6.2): Detecting using license-plate
00:05:06:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...1f8455) ['Found DayPlate'] took 98ms
00:05:06:Connection id "0HN41OMVGHON0", Request id "0HN41OMVGHON0:00000004": An unhandled exception was thrown by the application.
00:04:15:Object Detection (YOLOv5 6.2): Detecting using license-plate
00:04:15:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...86b95c) ['Found DayPlate'] took 115ms
00:04:15:Response rec'd from License Plate Reader command 'alpr' (...f8fbf8) ['Found Plate: 54310 zsqponmlkhgfedcba ZYXWVUTSRPONMLKJHGFEDCA 876543410 zyxwvutqponmlmjihgfedcba ZYXWVUTSTQPONMLKJHGFEDCBA 98765452 urqponmlkjihgfeba ZYXWVRQPONMNKJIHGFEDC 9876543210 ZYXWVUuCBA e3210 ZYXWVUTSRQPONv 9876543210 V LKJIHGFn 9876 '] took 524ms
00:04:18:Client request 'alpr' in queue 'alpr_queue' (...f03ce4)
00:04:18:Request 'alpr' dequeued from 'alpr_queue' (...f03ce4)
00:04:18:License Plate Reader: Retrieved alpr_queue command 'alpr'
00:04:18:Client request 'custom' in queue 'objectdetection_queue' (...241e39)
00:04:18:Request 'custom' dequeued from 'objectdetection_queue' (...241e39)
00:04:18:Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command 'custom'
00:04:18:Object Detection (YOLOv5 6.2): Detecting using license-plate
00:04:18:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...241e39) ['Found DayPlate'] took 92ms
00:04:18:Response rec'd from License Plate Reader command 'alpr' (...f03ce4) ['Found Plate: yxwvutsrkihgfedc ZYXWVUTSRQPONMLKJHGFEDCB 98765430 yxwvutsrqponmlihgfedeba ZYXWVUTSRQPONMLKLIHGFEDCB 98765410 mjihgfedcba ZYXWVUTSRQPONJIHGFEFCBA 5210 ZYXWVUSRQPONMm 987650 ZYXWVUTSRQPONMLKJIHGFn543210 ZYXWVNvDCBA f43210 '] took 636ms
00:04:21:Client request 'alpr' in queue 'alpr_queue' (...33c6a5)
00:04:21:Request 'alpr' dequeued from 'alpr_queue' (...33c6a5)
00:04:21:License Plate Reader: Retrieved alpr_queue command 'alpr'
00:04:21:Client request 'custom' in queue 'objectdetection_queue' (...ea564b)
00:04:21:Request 'custom' dequeued from 'objectdetection_queue' (...ea564b)
00:04:21:Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command 'custom'
00:04:21:Object Detection (YOLOv5 6.2): Detecting using license-plate
00:04:21:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...ea564b) ['Found DayPlate'] took 123ms
00:04:21:Response rec'd from License Plate Reader command 'alpr' (...33c6a5) ['Found Plate: JIHGFEDl 3210 KJIHGFEu3210 UKJIHGFuDCBA m 9876e50 MLJIHGFGDCBA 9873210 zyxwv'] took 513ms
00:04:23:Client request 'alpr' in queue 'alpr_queue' (...b5ab90)
00:04:23:Request 'alpr' dequeued from 'alpr_queue' (...b5ab90)
00:04:23:License Plate Reader: Retrieved alpr_queue command 'alpr'
00:04:23:Client request 'custom' in queue 'objectdetection_queue' (...00f28b)
00:04:23:Request 'custom' dequeued from 'objectdetection_queue' (...00f28b)
00:04:23:Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command 'custom'
00:04:23:Object Detection (YOLOv5 6.2): Detecting using license-plate
00:04:23:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...00f28b) ['Found DayPlate'] took 97ms
00:04:23:Response rec'd from License Plate Reader command 'alpr' (...b5ab90) ['Found Plate: 9876543210 zyxwvuvsrqponmlkeba ZYXWVUSRQPONM 987650 ZYXWV SRQPON KJIHGFE e3210 ZYXWV EDCBA 543210 V hgfedc YXWVUTSRQPONMLKJHGFEDCBA 8765432 zxwvutsrponmlkihgfedc YXWVUTSRKHGFEDCBA 876543410 yxwvutsrponmlkjihgfeda Z'] took 571ms
00:04:25:Client request 'alpr' in queue 'alpr_queue' (...f6699d)
00:04:25:Request 'alpr' dequeued from 'alpr_queue' (...f6699d)
00:04:25:License Plate Reader: Retrieved alpr_queue command 'alpr'
00:04:25:Client request 'custom' in queue 'objectdetection_queue' (...7fbd71)
00:04:25:Request 'custom' dequeued from 'objectdetection_queue' (...7fbd71)
00:04:25:Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command 'custom'
00:04:25:Object Detection (YOLOv5 6.2): Detecting using license-plate
00:04:25:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...7fbd71) ['Found DayPlate'] took 139ms
00:04:25:Response rec'd from License Plate Reader command 'alpr' (...f6699d) ['Found Plate: ZYXWVUT JIHGFEDl210 T KJIHGFEtD 3210 KJIHGFEtCBA l 98765e0 U zyxwvwtsrqponmlkjihgcba ZYXWVUTSRQPONL'] took 559ms
00:04:27:Client request 'alpr' in queue 'alpr_queue' (...995ed6)
00:04:27:Request 'alpr' dequeued from 'alpr_queue' (...995ed6)
00:04:27:License Plate Reader: Retrieved alpr_queue command 'alpr'
00:04:27:Client request 'custom' in queue 'objectdetection_queue' (...29583c)
00:04:27:Request 'custom' dequeued from 'objectdetection_queue' (...29583c)
00:04:27:Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command 'custom'
00:04:27:Object Detection (YOLOv5 6.2): Detecting using license-plate
00:04:27:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...29583c) ['Found DayPlate'] took 97ms
00:04:28:Response rec'd from License Plate Reader command 'alpr' (...995ed6) ['Found Plate: ZYXWVUTSRQPOKJIHGEDCBA 987643210 zyxwvutsrqponmlkjihgfdcba ZYXWUTSRQPOLKJIHGHEDCBA 743210 zyxwvutsrqponmlkjihghedcba ZYXWVUTSRQPMLKJIHIF zyvutsrqponmlkjfedcbab ZYXWQNMLKJIHGFEDCBA 9i WVUTSRQyGFEDCBq i7654321 QPONMLKJIHGFEDCBr10 Z PONMLKJB'] took 537ms
00:04:29:Client request 'alpr' in queue 'alpr_queue' (...0838e1)
00:04:29:Request 'alpr' dequeued from 'alpr_queue' (...0838e1)
00:04:29:License Plate Reader: Retrieved alpr_queue command 'alpr'
00:04:29:Client request 'custom' in queue 'objectdetection_queue' (...ad144b)
00:04:29:Request 'custom' dequeued from 'objectdetection_queue' (...ad144b)
00:04:29:Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command 'custom'
00:04:29:Object Detection (YOLOv5 6.2): Detecting using license-plate
00:04:29:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...ad144b) ['Found DayPlate'] took 87ms
00:04:30:Response rec'd from License Plate Reader command 'alpr' (...0838e1) ['Found Plate: CBA 987651 zyxwvutsrqponlkjihgfdcba ZYXWTSRQPOPMLKJIHGF 9876543210 zyxwvutsrqpopmlkjihgfdcba ZYXUTSRQPQN zyxwvutsrnmlkjijgfedcba YVUTSRQPONMLKJIGFEDCBAq0 ZY ONMLKJyGFEDCBq 910YXWVUTSRQPONMLKJz987654320 XWVUTSRJ'] took 478ms
00:04:31:Client request 'alpr' in queue 'alpr_queue' (...2572b3)
00:04:31:Request 'alpr' dequeued from 'alpr_queue' (...2572b3)
00:04:31:License Plate Reader: Retrieved alpr_queue command 'alpr'
00:04:31:Client request 'custom' in queue 'objectdetection_queue' (...2f64af)
00:04:31:Request 'custom' dequeued from 'objectdetection_queue' (...2f64af)
00:04:31:Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command 'custom'
00:04:31:Object Detection (YOLOv5 6.2): Detecting using license-plate
00:04:31:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...2f64af) ['Found DayPlate'] took 117ms
00:04:32:Connection id "0HN41OMVGHOM1", Request id "0HN41OMVGHOM1:0000000A": An unhandled exception was thrown by the application.
00:05:05:Client request 'alpr' in queue 'alpr_queue' (...ae6bac)
00:05:05:Request 'alpr' dequeued from 'alpr_queue' (...ae6bac)
00:05:05:License Plate Reader: Retrieved alpr_queue command 'alpr'
00:05:05:Client request 'custom' in queue 'objectdetection_queue' (...1f8455)
00:05:05:Request 'custom' dequeued from 'objectdetection_queue' (...1f8455)
00:05:05:Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command 'custom'
00:05:06:Object Detection (YOLOv5 6.2): Detecting using license-plate
00:05:06:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...1f8455) ['Found DayPlate'] took 98ms
00:05:06:Connection id "0HN41OMVGHON0", Request id "0HN41OMVGHON0:00000004": An unhandled exception was thrown by the application.
MikeLud1
IPCT Contributor
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 work you may need CUDA 10.2 and cuDNN v7.6.5. I have older GPU then yours working with CUDA 10.2 and cuDNN v7.6.5.
CUDA 11.2 Link
cuDNN v8.2.1 link
Log in
developer.nvidia.com
DJBWSM
n3wb
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 work you may need CUDA 10.2 and cuDNN v7.6.5. I have older GPU then yours working with CUDA 10.2 and cuDNN v7.6.5.
CUDA 11.2 Link
cuDNN v8.2.1 link
Log in
Currently in the process of install 11.7 and 8.5 as I read on the nvidia forum this is a combo that should work. Not too hopeful but ill see if that work. If not I try 11.2
Getting CPAI to work with my GeForce 1650 GRTX has been exciting 
I have finally gotten things working on the YOLO side but ALPR has some issues. I am running CPAI 2.6.5 with LPR 3.1.0. I am getting errors every time BI fires off a request to the ALPR module. I have read through this thread and the CPAI docs that point to using specific versions of packages from NVidia to get things working.
This situation "feels" likeI just need to get something pointing at the right place or in the right place (past the installed locations) or having the right PATH element.
My CPAI System Info:
When I installed the ALPR module, here are some of the messages from the log file:
I tried copying the CUDANN files to various places in the 11.8 toolkit with no success.
When I start up the ALPR module, I get these messages:
Suggestions?
I have finally gotten things working on the YOLO side but ALPR has some issues. I am running CPAI 2.6.5 with LPR 3.1.0. I am getting errors every time BI fires off a request to the ALPR module. I have read through this thread and the CPAI docs that point to using specific versions of packages from NVidia to get things working.This situation "feels" likeI just need to get something pointing at the right place or in the right place (past the installed locations) or having the right PATH element.
My CPAI System Info:
Server version: 2.6.5
System: Windows
Operating System: Windows (Microsoft Windows 10.0.19045)
CPUs: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz (Intel)
1 CPU x 4 cores. 8 logical processors (x64)
GPU (Primary): NVIDIA GeForce GTX 1650 (4 GiB) (NVIDIA)
Driver: 522.06, CUDA: 11.8 (up to: 11.8), Compute: 7.5, cuDNN: 9.1
System RAM: 16 GiB
Platform: Windows
BuildConfig: Release
Execution Env: Native
Runtime Env: Production
Runtimes installed:
.NET runtime: 7.0.20
.NET SDK: Not found
Default Python: Not found
Go: Not found
NodeJS: Not found
Rust: Not found
Video adapter info:
Microsoft Remote Display Adapter:
Driver Version 10.0.19041.4355
Video Processor
Intel(R) HD Graphics 530:
Driver Version 27.20.100.9664
Video Processor Intel(R) HD Graphics Family
NVIDIA GeForce GTX 1650:
Driver Version 31.0.15.2206
Video Processor NVIDIA GeForce GTX 1650
System GPU info:
GPU 3D Usage 2%
GPU RAM Usage 2.2 GiB
Global Environment variables:
CPAI_APPROOTPATH = <root>
CPAI_PORT = 32168
System: Windows
Operating System: Windows (Microsoft Windows 10.0.19045)
CPUs: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz (Intel)
1 CPU x 4 cores. 8 logical processors (x64)
GPU (Primary): NVIDIA GeForce GTX 1650 (4 GiB) (NVIDIA)
Driver: 522.06, CUDA: 11.8 (up to: 11.8), Compute: 7.5, cuDNN: 9.1
System RAM: 16 GiB
Platform: Windows
BuildConfig: Release
Execution Env: Native
Runtime Env: Production
Runtimes installed:
.NET runtime: 7.0.20
.NET SDK: Not found
Default Python: Not found
Go: Not found
NodeJS: Not found
Rust: Not found
Video adapter info:
Microsoft Remote Display Adapter:
Driver Version 10.0.19041.4355
Video Processor
Intel(R) HD Graphics 530:
Driver Version 27.20.100.9664
Video Processor Intel(R) HD Graphics Family
NVIDIA GeForce GTX 1650:
Driver Version 31.0.15.2206
Video Processor NVIDIA GeForce GTX 1650
System GPU info:
GPU 3D Usage 2%
GPU RAM Usage 2.2 GiB
Global Environment variables:
CPAI_APPROOTPATH = <root>
CPAI_PORT = 32168
When I installed the ALPR module, here are some of the messages from the log file:
2024-06-02 12:03:18: ALPR: [0;39m[49mExecuting post-install script for License Plate Reader[0m
2024-06-02 12:03:19: ALPR: [0;39m[49mApplying PaddleOCR patch[0m
2024-06-02 12:03:19: ALPR: 1 file(s) copied.
cuda_info.txt [+] 25,3 Top
2024-06-02 12:03:19: ALPR: [0;39m[49mApplying PaddleOCR patch[0m
2024-06-02 12:03:19: ALPR: 1 file(s) copied.
2024-06-02 12:03:47: ALPR: W0602 12:03:47.510859 14736 dynamic_loader.cc:285] Note: [Recommend] copy cudnn into CUDA installation directory.
2024-06-02 12:03:47: ALPR: For instance, download cudnn-10.0-windows10-x64-v7.6.5.32.zip from NVIDIA's official website,
2024-06-02 12:03:47: ALPR: then, unzip it and copy it into C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.0
2024-06-02 12:03:47: ALPR: You should do this according to your CUDA installation directory and CUDNN version.
2024-06-02 12:03:47: ALPR: Traceback (most recent call last):
2024-06-02 12:03:47: ALPR: File "C:\Program Files\CodeProject\AI\modules\ALPR\ALPR_adapter.py", line 109, in <module>
2024-06-02 12:03:47: ALPR: ALPR_adapter().start_loop()
2024-06-02 12:03:47: ALPR: File "C:\Program Files\CodeProject\AI\modules\ALPR\../../SDK/Python\module_runner.py", line 278, in start_loop
2024-06-02 12:03:47: ALPR: self.initialise()
2024-06-02 12:03:47: ALPR: File "C:\Program Files\CodeProject\AI\modules\ALPR\ALPR_adapter.py", line 37, in initialise
2024-06-02 12:03:47: ALPR: if paddle.device.get_cudnn_version() / 100.0 < self.opts.min_cuDNN_version:
2024-06-02 12:03:47: ALPR: File "C:\Program Files\CodeProject\AI\modules\ALPR\bin\windows\python39\venv\lib\site-packages\paddle\device\init.py", line 179, in get
2024-06-02 12:03:47: ALPR: cudnn_version = int(core.cudnn_version())
2024-06-02 12:03:47: ALPR: RuntimeError: (PreconditionNotMet) The third-party dynamic library (cudnn64_8.dll) that Paddle depends on is not configured correctly. (error
2024-06-02 12:03:47: ALPR: Suggestions:
2024-06-02 12:03:47: ALPR: 1. Check if the third-party dynamic library (e.g. CUDA, CUDNN) is installed correctly and its version is matched with paddlepaddle you inst
2024-06-02 12:03:47: ALPR: 2. Configure third-party dynamic library environment variables as follows:
2024-06-02 12:03:47: ALPR: - Linux: set LD_LIBRARY_PATH by
2024-06-02 12:03:47: ALPR: - Windows: set PATH by `set PATH=XXX; (at ..\paddle\phi\backends\dynload\dynamic_loader.cc:312)
2024-06-02 12:03:47: ALPR: [0;39m[49mSelf test: [0m[0;32m[49mSelf-test passed[0m
2024-06-02 12:03:47: ALPR: [0;95m[49mModule setup time 00:06:03.12[0m
2024-06-02 12:03:47: ALPR: [0;97m[42mSetup complete [0m
2024-06-02 12:03:47: ALPR: [0;95m[49mTotal setup time 00:06:04.72[0m
2024-06-02 12:03:19: ALPR: [0;39m[49mApplying PaddleOCR patch[0m
2024-06-02 12:03:19: ALPR: 1 file(s) copied.
cuda_info.txt [+] 25,3 Top
2024-06-02 12:03:19: ALPR: [0;39m[49mApplying PaddleOCR patch[0m
2024-06-02 12:03:19: ALPR: 1 file(s) copied.
2024-06-02 12:03:47: ALPR: W0602 12:03:47.510859 14736 dynamic_loader.cc:285] Note: [Recommend] copy cudnn into CUDA installation directory.
2024-06-02 12:03:47: ALPR: For instance, download cudnn-10.0-windows10-x64-v7.6.5.32.zip from NVIDIA's official website,
2024-06-02 12:03:47: ALPR: then, unzip it and copy it into C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.0
2024-06-02 12:03:47: ALPR: You should do this according to your CUDA installation directory and CUDNN version.
2024-06-02 12:03:47: ALPR: Traceback (most recent call last):
2024-06-02 12:03:47: ALPR: File "C:\Program Files\CodeProject\AI\modules\ALPR\ALPR_adapter.py", line 109, in <module>
2024-06-02 12:03:47: ALPR: ALPR_adapter().start_loop()
2024-06-02 12:03:47: ALPR: File "C:\Program Files\CodeProject\AI\modules\ALPR\../../SDK/Python\module_runner.py", line 278, in start_loop
2024-06-02 12:03:47: ALPR: self.initialise()
2024-06-02 12:03:47: ALPR: File "C:\Program Files\CodeProject\AI\modules\ALPR\ALPR_adapter.py", line 37, in initialise
2024-06-02 12:03:47: ALPR: if paddle.device.get_cudnn_version() / 100.0 < self.opts.min_cuDNN_version:
2024-06-02 12:03:47: ALPR: File "C:\Program Files\CodeProject\AI\modules\ALPR\bin\windows\python39\venv\lib\site-packages\paddle\device\init.py", line 179, in get
2024-06-02 12:03:47: ALPR: cudnn_version = int(core.cudnn_version())
2024-06-02 12:03:47: ALPR: RuntimeError: (PreconditionNotMet) The third-party dynamic library (cudnn64_8.dll) that Paddle depends on is not configured correctly. (error
2024-06-02 12:03:47: ALPR: Suggestions:
2024-06-02 12:03:47: ALPR: 1. Check if the third-party dynamic library (e.g. CUDA, CUDNN) is installed correctly and its version is matched with paddlepaddle you inst
2024-06-02 12:03:47: ALPR: 2. Configure third-party dynamic library environment variables as follows:
2024-06-02 12:03:47: ALPR: - Linux: set LD_LIBRARY_PATH by
export LD_LIBRARY_PATH=...2024-06-02 12:03:47: ALPR: - Windows: set PATH by `set PATH=XXX; (at ..\paddle\phi\backends\dynload\dynamic_loader.cc:312)
2024-06-02 12:03:47: ALPR: [0;39m[49mSelf test: [0m[0;32m[49mSelf-test passed[0m
2024-06-02 12:03:47: ALPR: [0;95m[49mModule setup time 00:06:03.12[0m
2024-06-02 12:03:47: ALPR: [0;97m[42mSetup complete [0m
2024-06-02 12:03:47: ALPR: [0;95m[49mTotal setup time 00:06:04.72[0m
I tried copying the CUDANN files to various places in the 11.8 toolkit with no success.
When I start up the ALPR module, I get these messages:
2024-06-02 15:55:21: *** Restarting License Plate Reader to apply settings change
2024-06-02 15:55:21: Running module using: C:\Program Files\CodeProject\AI\modules\ALPR\bin\windows\python39\venv\Scripts\python
2024-06-02 15:55:21:
2024-06-02 15:55:21: Attempting to start ALPR with C:\Program Files\CodeProject\AI\modules\ALPR\bin\windows\python39\venv\Scripts\python "C:\Program Files\CodeProject\AI\modules\ALPR\ALPR_adapter.py"
2024-06-02 15:55:21: Starting C:\Program Files...ws\python39\venv\Scripts\python "C:\Program Files...\modules\ALPR\ALPR_adapter.py"
2024-06-02 15:55:21:
2024-06-02 15:55:21: ** Module 'License Plate Reader' 3.1.0 (ID: ALPR)
2024-06-02 15:55:21: ** Valid: True
2024-06-02 15:55:21: ** Module Path: <root>\modules\ALPR
2024-06-02 15:55:21: ** Module Location: Internal
2024-06-02 15:55:21: ** AutoStart: True
2024-06-02 15:55:21: ** Queue: alpr_queue
2024-06-02 15:55:21: ** Runtime: python3.9
2024-06-02 15:55:21: ** Runtime Location: Local
2024-06-02 15:55:21: ** FilePath: ALPR_adapter.py
2024-06-02 15:55:21: ** Start pause: 3 sec
2024-06-02 15:55:21: ** Parallelism: 0
2024-06-02 15:55:21: ** LogVerbosity:
2024-06-02 15:55:21: ** Platforms: all
2024-06-02 15:55:21: ** GPU Libraries: installed if available
2024-06-02 15:55:21: ** GPU: use if supported
2024-06-02 15:55:21: ** Accelerator:
2024-06-02 15:55:21: ** Half Precision: enable
2024-06-02 15:55:21: ** Environment Variables
2024-06-02 15:55:21: ** AUTO_PLATE_ROTATE = True
2024-06-02 15:55:21: ** CROPPED_PLATE_DIR = <root>\Server\wwwroot
2024-06-02 15:55:21: ** MIN_COMPUTE_CAPABILITY = 6
2024-06-02 15:55:21: ** MIN_CUDNN_VERSION = 7
2024-06-02 15:55:21: ** OCR_OPTIMAL_CHARACTER_HEIGHT = 60
2024-06-02 15:55:21: ** OCR_OPTIMAL_CHARACTER_WIDTH = 30
2024-06-02 15:55:21: ** OCR_OPTIMIZATION = True
2024-06-02 15:55:21: ** PLATE_CONFIDENCE = 0.7
2024-06-02 15:55:21: ** PLATE_RESCALE_FACTOR = 2
2024-06-02 15:55:21: ** PLATE_ROTATE_DEG = 0
2024-06-02 15:55:21: ** REMOVE_SPACES = False
2024-06-02 15:55:21: ** ROOT_PATH = <root>
2024-06-02 15:55:21: ** SAVE_CROPPED_PLATE = False
2024-06-02 15:55:21:
2024-06-02 15:55:21: Started License Plate Reader module
2024-06-02 15:55:25: ALPR_adapter.py: W0602 15:55:25.500015 14428 dynamic_loader.cc:285] Note: [Recommend] copy cudnn into CUDA installation directory.
2024-06-02 15:55:25: ALPR_adapter.py: For instance, download cudnn-10.0-windows10-x64-v7.6.5.32.zip from NVIDIA's official website,
2024-06-02 15:55:25: ALPR_adapter.py: Running init for License Plate Reader
2024-06-02 15:55:25: ALPR_adapter.py: then, unzip it and copy it into C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.0
2024-06-02 15:55:25: ALPR_adapter.py: An exception occurred initialising the module: (PreconditionNotMet) The third-party dynamic library (cudnn64_8.dll) that Paddle depends on is not configured correctly. (error code is 126)
2024-06-02 15:55:25: ALPR_adapter.py: You should do this according to your CUDA installation directory and CUDNN version.
2024-06-02 15:55:25: ALPR_adapter.py: Suggestions:
2024-06-02 15:55:25: ALPR_adapter.py: 1. Check if the third-party dynamic library (e.g. CUDA, CUDNN) is installed correctly and its version is matched with paddlepaddle you installed.
2024-06-02 15:55:25: ALPR_adapter.py: 2. Configure third-party dynamic library environment variables as follows:
2024-06-02 15:55:25: ALPR_adapter.py: - Linux: set LD_LIBRARY_PATH by
2024-06-02 15:55:25: ALPR_adapter.py: - Windows: set PATH by `set PATH=XXX; (at ..\paddle\phi\backends\dynload\dynamic_loader.cc:312)
2024-06-02 15:55:21: Running module using: C:\Program Files\CodeProject\AI\modules\ALPR\bin\windows\python39\venv\Scripts\python
2024-06-02 15:55:21:
2024-06-02 15:55:21: Attempting to start ALPR with C:\Program Files\CodeProject\AI\modules\ALPR\bin\windows\python39\venv\Scripts\python "C:\Program Files\CodeProject\AI\modules\ALPR\ALPR_adapter.py"
2024-06-02 15:55:21: Starting C:\Program Files...ws\python39\venv\Scripts\python "C:\Program Files...\modules\ALPR\ALPR_adapter.py"
2024-06-02 15:55:21:
2024-06-02 15:55:21: ** Module 'License Plate Reader' 3.1.0 (ID: ALPR)
2024-06-02 15:55:21: ** Valid: True
2024-06-02 15:55:21: ** Module Path: <root>\modules\ALPR
2024-06-02 15:55:21: ** Module Location: Internal
2024-06-02 15:55:21: ** AutoStart: True
2024-06-02 15:55:21: ** Queue: alpr_queue
2024-06-02 15:55:21: ** Runtime: python3.9
2024-06-02 15:55:21: ** Runtime Location: Local
2024-06-02 15:55:21: ** FilePath: ALPR_adapter.py
2024-06-02 15:55:21: ** Start pause: 3 sec
2024-06-02 15:55:21: ** Parallelism: 0
2024-06-02 15:55:21: ** LogVerbosity:
2024-06-02 15:55:21: ** Platforms: all
2024-06-02 15:55:21: ** GPU Libraries: installed if available
2024-06-02 15:55:21: ** GPU: use if supported
2024-06-02 15:55:21: ** Accelerator:
2024-06-02 15:55:21: ** Half Precision: enable
2024-06-02 15:55:21: ** Environment Variables
2024-06-02 15:55:21: ** AUTO_PLATE_ROTATE = True
2024-06-02 15:55:21: ** CROPPED_PLATE_DIR = <root>\Server\wwwroot
2024-06-02 15:55:21: ** MIN_COMPUTE_CAPABILITY = 6
2024-06-02 15:55:21: ** MIN_CUDNN_VERSION = 7
2024-06-02 15:55:21: ** OCR_OPTIMAL_CHARACTER_HEIGHT = 60
2024-06-02 15:55:21: ** OCR_OPTIMAL_CHARACTER_WIDTH = 30
2024-06-02 15:55:21: ** OCR_OPTIMIZATION = True
2024-06-02 15:55:21: ** PLATE_CONFIDENCE = 0.7
2024-06-02 15:55:21: ** PLATE_RESCALE_FACTOR = 2
2024-06-02 15:55:21: ** PLATE_ROTATE_DEG = 0
2024-06-02 15:55:21: ** REMOVE_SPACES = False
2024-06-02 15:55:21: ** ROOT_PATH = <root>
2024-06-02 15:55:21: ** SAVE_CROPPED_PLATE = False
2024-06-02 15:55:21:
2024-06-02 15:55:21: Started License Plate Reader module
2024-06-02 15:55:25: ALPR_adapter.py: W0602 15:55:25.500015 14428 dynamic_loader.cc:285] Note: [Recommend] copy cudnn into CUDA installation directory.
2024-06-02 15:55:25: ALPR_adapter.py: For instance, download cudnn-10.0-windows10-x64-v7.6.5.32.zip from NVIDIA's official website,
2024-06-02 15:55:25: ALPR_adapter.py: Running init for License Plate Reader
2024-06-02 15:55:25: ALPR_adapter.py: then, unzip it and copy it into C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.0
2024-06-02 15:55:25: ALPR_adapter.py: An exception occurred initialising the module: (PreconditionNotMet) The third-party dynamic library (cudnn64_8.dll) that Paddle depends on is not configured correctly. (error code is 126)
2024-06-02 15:55:25: ALPR_adapter.py: You should do this according to your CUDA installation directory and CUDNN version.
2024-06-02 15:55:25: ALPR_adapter.py: Suggestions:
2024-06-02 15:55:25: ALPR_adapter.py: 1. Check if the third-party dynamic library (e.g. CUDA, CUDNN) is installed correctly and its version is matched with paddlepaddle you installed.
2024-06-02 15:55:25: ALPR_adapter.py: 2. Configure third-party dynamic library environment variables as follows:
2024-06-02 15:55:25: ALPR_adapter.py: - Linux: set LD_LIBRARY_PATH by
export LD_LIBRARY_PATH=...2024-06-02 15:55:25: ALPR_adapter.py: - Windows: set PATH by `set PATH=XXX; (at ..\paddle\phi\backends\dynload\dynamic_loader.cc:312)
Suggestions?
Last edited:
I am also seeing this as well:
2024-06-02 16:12:06: License Plate Reader: [AttributeError] : Error during main_loop: Traceback (most recent call last):
File "C:\Program Files\CodeProject\AI\modules\ALPR\../../SDK/Python\module_runner.py", line 618, in main_loop
self.update_statistics(output)
File "C:\Program Files\CodeProject\AI\modules\ALPR\ALPR_adapter.py", line 96, in update_statistics
self._num_items_found += len(predictions)
AttributeError: 'ALPR_adapter' object has no attribute '_num_items_found'
in License Plate Reader
MikeLud1
IPCT Contributor
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
Only CUDA 11.8 installed:
Ouptut from set:
ALLUSERSPROFILE=C:\ProgramData
APPDATA=C:\Users\scottm\AppData\Roaming
CLIENTNAME=Guavabrain
CommonProgramFiles=C:\Program Files\Common Files
CommonProgramFiles(x86)=C:\Program Files (x86)\Common Files
CommonProgramW6432=C:\Program Files\Common Files
COMPUTERNAME=HOME-NVR
ComSpec=C:\windows\system32\cmd.exe
CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8
CUDA_PATH_V11_8=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8
DriverData=C:\Windows\System32\Drivers\DriverData
HOMEDRIVE=C:
HOMEPATH=\Users\scottm
LOCALAPPDATA=C:\Users\scottm\AppData\Local
LOGONSERVER=\\HOME-NVR
NUMBER_OF_PROCESSORS=8
NVTOOLSEXT_PATH=C:\Program Files\NVIDIA Corporation\NvToolsExt\
OneDrive=C:\Users\scottm\OneDrive
OneDriveConsumer=C:\Users\scottm\OneDrive
OS=Windows_NT
Path=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8;C:\Program Files\NVIDIA\CUDNN\v9.1\bin;C:\windows\system32;C:\windows;C:\windows\System32\Wbem;C:\windows\System32\WindowsPowerShell\v1.0\;C:\windows\System32\OpenSSH\;C:\Program Files\dotnet\;C:\Users\scottm\Scripts;C:\Program Files\PowerShell\7\;C:\Program Files\NVIDIA Corporation\Nsight Compute 2022.3.0\;C:\Users\scottm\AppData\Local\Microsoft\WindowsApps;C:\Users\scottm\AppData\Local\Programs\Microsoft VS Code\bin;C:\Users\scottm\AppData\Local\Programs\Git\cmd
PATHEXT=.COM;.EXE;.BAT;.CMD;.VBS;.VBE;.JS;.JSE;.WSF;.WSH;.MSC
POWERSHELL_DISTRIBUTION_CHANNEL=MSI:Windows 10 Pro
PROCESSOR_ARCHITECTURE=AMD64
PROCESSOR_IDENTIFIER=Intel64 Family 6 Model 94 Stepping 3, GenuineIntel
PROCESSOR_LEVEL=6
PROCESSOR_REVISION=5e03
ProgramData=C:\ProgramData
ProgramFiles=C:\Program Files
ProgramFiles(x86)=C:\Program Files (x86)
ProgramW6432=C:\Program Files
PROMPT=$P$G
PSModulePath=C:\Program Files\WindowsPowerShell\Modules;C:\windows\system32\WindowsPowerShell\v1.0\Modules
PUBLIC=C:\Users\Public
SESSIONNAME=RDP-Tcp#2
SystemDrive=C:
SystemRoot=C:\windows
TEMP=C:\Users\scottm\AppData\Local\Temp
TMP=C:\Users\scottm\AppData\Local\Temp
USERDOMAIN=HOME-NVR
USERDOMAIN_ROAMINGPROFILE=HOME-NVR
USERNAME=scottm
USERPROFILE=C:\Users\scottm
windir=C:\windows
ZES_ENABLE_SYSMAN=1
APPDATA=C:\Users\scottm\AppData\Roaming
CLIENTNAME=Guavabrain
CommonProgramFiles=C:\Program Files\Common Files
CommonProgramFiles(x86)=C:\Program Files (x86)\Common Files
CommonProgramW6432=C:\Program Files\Common Files
COMPUTERNAME=HOME-NVR
ComSpec=C:\windows\system32\cmd.exe
CUDA_PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8
CUDA_PATH_V11_8=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8
DriverData=C:\Windows\System32\Drivers\DriverData
HOMEDRIVE=C:
HOMEPATH=\Users\scottm
LOCALAPPDATA=C:\Users\scottm\AppData\Local
LOGONSERVER=\\HOME-NVR
NUMBER_OF_PROCESSORS=8
NVTOOLSEXT_PATH=C:\Program Files\NVIDIA Corporation\NvToolsExt\
OneDrive=C:\Users\scottm\OneDrive
OneDriveConsumer=C:\Users\scottm\OneDrive
OS=Windows_NT
Path=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8;C:\Program Files\NVIDIA\CUDNN\v9.1\bin;C:\windows\system32;C:\windows;C:\windows\System32\Wbem;C:\windows\System32\WindowsPowerShell\v1.0\;C:\windows\System32\OpenSSH\;C:\Program Files\dotnet\;C:\Users\scottm\Scripts;C:\Program Files\PowerShell\7\;C:\Program Files\NVIDIA Corporation\Nsight Compute 2022.3.0\;C:\Users\scottm\AppData\Local\Microsoft\WindowsApps;C:\Users\scottm\AppData\Local\Programs\Microsoft VS Code\bin;C:\Users\scottm\AppData\Local\Programs\Git\cmd
PATHEXT=.COM;.EXE;.BAT;.CMD;.VBS;.VBE;.JS;.JSE;.WSF;.WSH;.MSC
POWERSHELL_DISTRIBUTION_CHANNEL=MSI:Windows 10 Pro
PROCESSOR_ARCHITECTURE=AMD64
PROCESSOR_IDENTIFIER=Intel64 Family 6 Model 94 Stepping 3, GenuineIntel
PROCESSOR_LEVEL=6
PROCESSOR_REVISION=5e03
ProgramData=C:\ProgramData
ProgramFiles=C:\Program Files
ProgramFiles(x86)=C:\Program Files (x86)
ProgramW6432=C:\Program Files
PROMPT=$P$G
PSModulePath=C:\Program Files\WindowsPowerShell\Modules;C:\windows\system32\WindowsPowerShell\v1.0\Modules
PUBLIC=C:\Users\Public
SESSIONNAME=RDP-Tcp#2
SystemDrive=C:
SystemRoot=C:\windows
TEMP=C:\Users\scottm\AppData\Local\Temp
TMP=C:\Users\scottm\AppData\Local\Temp
USERDOMAIN=HOME-NVR
USERDOMAIN_ROAMINGPROFILE=HOME-NVR
USERNAME=scottm
USERPROFILE=C:\Users\scottm
windir=C:\windows
ZES_ENABLE_SYSMAN=1
I finally got things squared away in my installation. The CUDA/CUDNN installation isn't really an issue. It is the fiddlyness of paddle. I tracked the error message of Note: [Recommend] copy cudnn into CUDA installation directory. down to code in Paddle. The file is paddle/phi/backends/dynload/dynamic_loader.cc and the helpful code bits were:
Totally removed the ALPR module and re-installed it. Prior to this I was just running ..\..\setup.bat from the module. Now, no message about CUDNN, AttributeError: 'ALPR_adapter' object has no attribute '_num_items_found' error has disappeared and the CPAI dashboard shows the module using GPU. So progress.
But, ALPR processing always returns nothing found
Any suggestions?
Code:
void* GetCUDNNDsoHandle() {
#if defined(__APPLE__) || defined(__OSX__)
std::string mac_warn_meg(
"Note: [Recommend] copy cudnn into /usr/local/cuda/ \n "
"For instance, sudo tar -xzf "
"cudnn-7.5-osx-x64-v5.0-ga.tgz -C /usr/local \n sudo "
"chmod a+r /usr/local/cuda/include/cudnn.h "
"/usr/local/cuda/lib/libcudnn*");
return GetDsoHandleFromSearchPath(
FLAGS_cudnn_dir, "libcudnn.dylib", false, {}, mac_warn_meg);
#elif defined(_WIN32) && defined(PADDLE_WITH_CUDA)
std::string win_warn_meg(
"Note: [Recommend] copy cudnn into CUDA installation directory. \n "
"For instance, download cudnn-10.0-windows10-x64-v7.6.5.32.zip from "
"NVIDIA's official website, \n"
"then, unzip it and copy it into C:\\Program Files\\NVIDIA GPU Computing "
"Toolkit\\CUDA\\v10.0\n"
"You should do this according to your CUDA installation directory and "
"CUDNN version.");
if (CUDA_VERSION >= 11000 && CUDA_VERSION < 12030) {
#ifdef PADDLE_WITH_PIP_CUDA_LIBRARIES
return GetDsoHandleFromSearchPath(
FLAGS_cuda_dir, "cudnn64_8.dll", true, {cuda_lib_path}, win_warn_meg);
#else
return GetDsoHandleFromSearchPath(
FLAGS_cuda_dir, win_cudnn_lib, true, {cuda_lib_path}, win_warn_meg);
#endif
} else if (CUDA_VERSION >= 12030) {
#ifdef PADDLE_WITH_PIP_CUDA_LIBRARIES
return GetDsoHandleFromSearchPath(
FLAGS_cuda_dir, "cudnn64_9.dll", true, {cuda_lib_path}, win_warn_meg);
#else
return GetDsoHandleFromSearchPath(
FLAGS_cuda_dir, win_cudnn_lib, true, {cuda_lib_path}, win_warn_meg);
#endif
}
#elif defined(PADDLE_WITH_HIP)
return GetDsoHandleFromSearchPath(FLAGS_miopen_dir, "libMIOpen.so", false);
#else
#ifdef PADDLE_WITH_PIP_CUDA_LIBRARIES
if (CUDA_VERSION >= 12030) {
return GetDsoHandleFromSearchPath(
FLAGS_cudnn_dir, "libcudnn.so.9", false, {cuda_lib_path});
} else {
return GetDsoHandleFromSearchPath(
FLAGS_cudnn_dir, "libcudnn.so.8", false, {cuda_lib_path});
}
#else
return GetDsoHandleFromSearchPath(
FLAGS_cudnn_dir, "libcudnn.so", false, {cuda_lib_path});
#endif
#endif
}But, ALPR processing always returns nothing found
Any suggestions?
morikplay
n3wb
@MikeLud1
Thank you for the incredible support you provide in addition to advancing the development of these AI-based models.
I have a BI+CPAI setup on Windows 11 Pro machine w/ RTX43080. FaceProcessing and ALPR are working fabulously using GPU(CUDA) 12.4 + cuDNN 9.0. Now, I'd like to employ one of the my servers with NVIDIA A100 to take over the AI parts. CPAI install on Ubuntu 22.04 is complete with both FaceProcessing + ObjectDetectionYolo work fine using GPU(CUDA) 12.4 + cuDNN 9.2. ALPR only uses CPU.
A100 grid license (vGPU) on ubuntu 22.04 is active: nvidia-smi -q
nvcc is fine as well. nvcc --version
CPAI info
ALPR install log
I'm unable to set installGPU to true via POST API. Changing modulesettings.linux.json also has no effect. A similar outcome when using libcuDNN8.9. Switching between the two cuDNNs is done using ubuntu's native library mgmt
Any thoughts on how might I cross this hump?
Thank you for the incredible support you provide in addition to advancing the development of these AI-based models.
I have a BI+CPAI setup on Windows 11 Pro machine w/ RTX43080. FaceProcessing and ALPR are working fabulously using GPU(CUDA) 12.4 + cuDNN 9.0. Now, I'd like to employ one of the my servers with NVIDIA A100 to take over the AI parts. CPAI install on Ubuntu 22.04 is complete with both FaceProcessing + ObjectDetectionYolo work fine using GPU(CUDA) 12.4 + cuDNN 9.2. ALPR only uses CPU.
A100 grid license (vGPU) on ubuntu 22.04 is active: nvidia-smi -q
Code:
==============NVSMI LOG==============
Driver Version : 550.54.15
CUDA Version : 12.4
Attached GPUs : 1
GPU 00000000:02:01.0
Product Name : GRID A100D-1-10C
Product Brand : NVIDIA Virtual Compute Server
Product Architecture : Ampere
Display Mode : Enabled
Display Active : Disabled
Persistence Mode : Enabled
Addressing Mode : None
MIG Mode
Current : Enabled
Pending : Enabled
...
GPU Virtualization Mode
Virtualization Mode : VGPU
vGPU Software Licensed Product
Product Name : NVIDIA <something something>
License Status : Licensed <expiry>
......
Code:
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2024 NVIDIA Corporation
Built on Thu_Mar_28_02:18:24_PDT_2024
Cuda compilation tools, release 12.4, V12.4.131
Build cuda_12.4.r12.4/compiler.34097967_0
Code:
Server version: 2.6.5
System: Linux
Operating System: Linux (Ubuntu 22.04)
CPUs: Intel(R) Xeon(R) Platinum 8351N CPU @ 2.40GHz (Intel)
8 CPUs x 1 core. 1 logical processors (x64)
GPU (Primary): (NVIDIA), CUDA: 12.4 (up to: 12.4), Compute: 8.0, cuDNN: 9.2.0
System RAM: 63 GiB
Platform: Linux
Code:
13:58:27:Preparing to install module 'ALPR'
13:58:27:Downloading module 'ALPR'
13:58:28:Installing module 'ALPR'
13:58:28:ALPR: Setting verbosity to loud
13:58:28:ALPR: Installing CodeProject.AI Analysis Module
13:58:28:ALPR: ======================================================================
13:58:28:ALPR: CodeProject.AI Installer
13:58:28:ALPR: ======================================================================
13:58:28:ALPR: 82.00 GiB of 148.06 GiB available on linux
13:58:28:ALPR: os, name, arch = linux ubuntu x86_64
13:58:28:ALPR: systemName, platform = linux, linux
13:58:28:ALPR: edgeDevice =
13:58:28:ALPR: SSH = false
13:58:28:ALPR: setupMode = SetupModule
13:58:28:ALPR: executionEnvironment = Production
13:58:28:ALPR: rootDirPath = /usr/bin/codeproject.ai-server-2.6.5
13:58:28:ALPR: appRootDirPath = /usr/bin/codeproject.ai-server-2.6.5
13:58:28:ALPR: setupScriptDirPath = /usr/bin/codeproject.ai-server-2.6.5
13:58:28:ALPR: sdkScriptsDirPath = /usr/bin/codeproject.ai-server-2.6.5/SDK/Scripts
13:58:28:ALPR: runtimesDirPath = /usr/bin/codeproject.ai-server-2.6.5/runtimes
13:58:28:ALPR: modulesDirPath = /usr/bin/codeproject.ai-server-2.6.5/modules
13:58:28:ALPR: externalModulesDirPath = /usr/bin/codeproject.ai-server-2.6.5/../CodeProject.AI-Modules
13:58:28:ALPR: downloadDirPath = /usr/bin/codeproject.ai-server-2.6.5/downloads
13:58:28:ALPR: Installing xz-utils...
13:58:29:ALPR: General CodeProject.AI setup
13:58:29:ALPR: Setting permissions on runtimes folder...done
13:58:29:ALPR: Setting permissions on downloads folder...done
13:58:29:ALPR: Setting permissions on modules download folder...done
13:58:29:ALPR: Setting permissions on models download folder...done
13:58:29:ALPR: Setting permissions on persisted data folder...done
13:58:29:ALPR: GPU support
13:58:29:ALPR: Searching for installed dependencies:
13:58:29:ALPR: -> nvidia-cuda-toolkit done
13:58:29:ALPR: Installing missing dependencies:
13:58:29:ALPR: -> nvidia-cuda-toolkit
13:58:30:ALPR: Reading package lists...
13:58:30:ALPR: CUDA (NVIDIA) Present: Yes (CUDA 12.4, cuDNN 9.2.0)
13:58:30:ALPR: ROCm (AMD) Present: No
13:58:30:ALPR: MPS (Apple) Present: No
13:58:31:ALPR: Reading module settings.......done
13:58:31:ALPR: Processing module ALPR 3.1.0
13:58:31:ALPR: moduleName = License Plate Reader
13:58:31:ALPR: moduleId = ALPR
13:58:31:ALPR: moduleVersion = 3.1.0
13:58:31:ALPR: runtime = python3.8
13:58:31:ALPR: runtimeLocation = Local
13:58:31:ALPR: installGPU = false
13:58:31:ALPR: pythonVersion = 3.8
13:58:31:ALPR: virtualEnvDirPath = /usr/bin/codeproject.ai-server-2.6.5/modules/ALPR/bin/linux/python38/venv
13:58:31:ALPR: venvPythonCmdPath = /usr/bin/codeproject.ai-server-2.6.5/modules/ALPR/bin/linux/python38/venv/bin/python3.8
13:58:31:ALPR: packagesDirPath = /usr/bin/codeproject.ai-server-2.6.5/modules/ALPR/bin/linux/python38/venv/lib/python3.8/site-packages/
13:58:31:ALPR: Installing Python 3.8
13:58:31:ALPR: Python install path is /usr/bin/codeproject.ai-server-2.6.5/modules/ALPR/bin/linux/python38
13:58:31:ALPR: Python 3.8 is already installed
13:58:32:ALPR: Ensuring PIP in base python install...Reading package lists...
13:58:33:ALPR: Building dependency tree...
13:58:33:ALPR: Reading state information...
13:58:33:ALPR: The following packages were automatically installed and are no longer required:
13:58:33:ALPR: adwaita-icon-theme gtk-update-icon-cache hicolor-icon-theme
13:58:33:ALPR: humanity-icon-theme libaccinj64-11.5 libbabeltrace1 libboost-regex1.74.0
13:58:33:ALPR: libcub-dev libcublas11 libcublaslt11 libcudart11.0 libcufft10 libcufftw10
13:58:33:ALPR: libcupti-dev libcupti-doc libcupti11.5 libcurand10 libcusolver11
13:58:33:ALPR: libcusolvermg11 libcusparse11 libdebuginfod-common libdebuginfod1 libegl-dev
13:58:33:ALPR: libgail-common libgail18 libgl-dev libgl1-mesa-dev libgles-dev libgles1
13:58:33:ALPR: libglvnd-core-dev libglvnd-dev libglx-dev libgtk2.0-0 libgtk2.0-bin
13:58:33:ALPR: libgtk2.0-common libipt2 libnvblas11 libnvjpeg11 libnvrtc-builtins11.5
13:58:33:ALPR: libnvrtc11.2 libnvtoolsext1 libnvvm4 libopengl-dev libpthread-stubs0-dev
13:58:33:ALPR: libsource-highlight-common libsource-highlight4v5 libtbb-dev libtbb12
13:58:33:ALPR: libtbbmalloc2 libthrust-dev libvdpau-dev libx11-dev libxau-dev libxcb1-dev
13:58:33:ALPR: libxdmcp-dev node-html5shiv nvidia-cuda-gdb nvidia-cuda-toolkit-doc
13:58:33:ALPR: opencl-c-headers opencl-clhpp-headers openjdk-8-jre ubuntu-mono x11proto-dev
13:58:33:ALPR: xorg-sgml-doctools xtrans-dev
13:58:33:ALPR: Use 'sudo apt autoremove' to remove them.
13:58:33:ALPR: debconf: unable to initialize frontend: Dialog
13:58:33:ALPR: debconf: (Dialog frontend will not work on a dumb terminal, an emacs shell buffer, or without a controlling terminal.)
13:58:33:ALPR: debconf: falling back to frontend: Readline
13:58:33:ALPR: debconf: unable to initialize frontend: Readline
13:58:33:ALPR: debconf: (This frontend requires a controlling tty.)
13:58:33:ALPR: debconf: falling back to frontend: Teletype
....
13:59:39:ALPR: Executing post-install script for License Plate Reader
13:59:39:ALPR: Applying PaddleOCR patch
13:59:39:ALPR: SELF TEST START ======================================================
13:59:42:ALPR: Running verify PaddlePaddle program ...
13:59:42:ALPR: PaddlePaddle works well on 1 CPU.
13:59:42:ALPR: PaddlePaddle is installed successfully! Let's start deep learning with PaddlePaddle now.
13:59:42:ALPR: Self-test passed
13:59:42:ALPR: SELF TEST END ======================================================
13:59:42:ALPR: Module setup time 00:01:12
13:59:42:ALPR: Setup complete
13:59:42:ALPR: Total setup time 00:01:14
13:59:42:Module ALPR installed successfully.
13:59:42:Installer exited with code 0
13:59:42:
13:59:42:Module 'License Plate Reader' 3.1.0 (ID: ALPR)
13:59:42:Valid: True
13:59:42:Module Path: <root>/modules/ALPR
13:59:42:Module Location: Internal
13:59:42:AutoStart: True
13:59:42:Queue: alpr_queue
13:59:42:Runtime: python3.8
13:59:42:Runtime Location: Local
13:59:42:FilePath: ALPR_adapter.py
13:59:42:Start pause: 3 sec
13:59:42:Parallelism: 0
13:59:42:LogVerbosity:
13:59:42:Platforms: all
13:59:42:GPU Libraries: not installed
13:59:42:GPU: do not use
13:59:42:Accelerator:
13:59:42:Half Precision: enable
13:59:42:Environment Variables
13:59:42:AUTO_PLATE_ROTATE = True
13:59:42:CROPPED_PLATE_DIR = <root>/Server/wwwroot
13:59:42:MIN_COMPUTE_CAPABILITY = 6
13:59:42:MIN_CUDNN_VERSION = 7
13:59:42:OCR_OPTIMAL_CHARACTER_HEIGHT = 60
13:59:42:OCR_OPTIMAL_CHARACTER_WIDTH = 30
13:59:42:OCR_OPTIMIZATION = True
13:59:42:PLATE_CONFIDENCE = 0.7
13:59:42:PLATE_RESCALE_FACTOR = 2
13:59:42:PLATE_ROTATE_DEG = 0
13:59:42:REMOVE_SPACES = False
13:59:42:ROOT_PATH = <root>
13:59:42:SAVE_CROPPED_PLATE = False
13:59:42:
13:59:42:Started License Plate Reader module
13:59:45:Module ALPR started successfully.
Code:
sudo update-alternatives --config libcudnn