|
No luck
here is log of CMD
PS C:\Program Files\CodeProject\AI\AnalysisLayer\ObjectDetectionYolo> ..\..\setup.bat
Installing CodeProject.AI Analysis Module
========================================================================
CodeProject.AI Installer
========================================================================
CUDA Present...True
Allowing GPU Support: Yes
Allowing CUDA Support: Yes
General CodeProject.AI setup
Creating Directories...Done
Installing module ObjectDetectionYolo
python37 package already downloaded
Creating Virtual Environment...Python 3.7 Already present
Enabling our Virtual Environment...Done
Confirming we have Python 3.7...present
Ensuring Python package manager (pip) is installed...Done
Ensuring Python package manager (pip) is up to date...Done
Installing Python packages from requirements.windows.cuda.txt
Installing Packages into Virtual Environment...ERROR: Exception:
Traceback (most recent call last):
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_internal\cli\base_command.py", line 160, in exc_logging_wrapper
status = run_func(*args)
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_internal\cli\req_command.py", line 247, in wrapper
return func(self, options, args)
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_internal\commands\install.py", line 326, in run
session = self.get_default_session(options)
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_internal\cli\req_command.py", line 98, in get_default_session
self._session = self.enter_context(self._build_session(options))
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_internal\cli\req_command.py", line 130, in _build_session
ssl_context=ssl_context,
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_internal\network\session.py", line 343, in __init__
self.headers["User-Agent"] = user_agent()
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_internal\network\session.py", line 175, in user_agent
setuptools_dist = get_default_environment().get_distribution("setuptools")
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_internal\metadata\__init__.py", line 75, in get_default_environment
return select_backend().Environment.default()
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_internal\metadata\__init__.py", line 63, in select_backend
from . import pkg_resources
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_internal\metadata\pkg_resources.py", line 8, in <module>
from pip._vendor import pkg_resources
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 3251, in <module>
@_call_aside
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 3235, in _call_aside
f(*args, **kwargs)
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 3264, in _initialize_master_working_set
working_set = WorkingSet._build_master()
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 574, in _build_master
ws = cls()
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 567, in __init__
self.add_entry(entry)
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 623, in add_entry
for dist in find_distributions(entry, True):
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 2065, in find_on_path
for dist in factory(fullpath):
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 2127, in distributions_from_metadata
if len(os.listdir(path)) == 0:
PermissionError: [WinError 5] Access is denied: 'c:\\program files\\codeproject\\ai\\analysislayer\\bin\\windows\\python37\\venv\\lib\\site-packages\\zipp-3.11.0.dist-info'
Traceback (most recent call last):
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\Python37\lib\runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\Python37\lib\runpy.py", line 85, in _run_code
exec(code, run_globals)
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\__main__.py", line 31, in <module>
sys.exit(_main())
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_internal\cli\main.py", line 70, in main
return command.main(cmd_args)
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_internal\cli\base_command.py", line 101, in main
return self._main(args)
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_internal\cli\base_command.py", line 216, in _main
self.handle_pip_version_check(options)
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_internal\cli\req_command.py", line 187, in handle_pip_version_check
fallback_to_certifi=True,
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_internal\cli\req_command.py", line 130, in _build_session
ssl_context=ssl_context,
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_internal\network\session.py", line 343, in __init__
self.headers["User-Agent"] = user_agent()
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_internal\network\session.py", line 175, in user_agent
setuptools_dist = get_default_environment().get_distribution("setuptools")
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_internal\metadata\__init__.py", line 75, in get_default_environment
return select_backend().Environment.default()
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_internal\metadata\__init__.py", line 63, in select_backend
from . import pkg_resources
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_internal\metadata\pkg_resources.py", line 8, in <module>
from pip._vendor import pkg_resources
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 3251, in <module>
@_call_aside
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 3235, in _call_aside
f(*args, **kwargs)
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 3264, in _initialize_master_working_set
working_set = WorkingSet._build_master()
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 574, in _build_master
ws = cls()
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 567, in __init__
self.add_entry(entry)
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 623, in add_entry
for dist in find_distributions(entry, True):
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 2065, in find_on_path
for dist in factory(fullpath):
File "C:\Program Files\CodeProject\AI\AnalysisLayer\bin\windows\python37\venv\lib\site-packages\pip\_vendor\pkg_resources\__init__.py", line 2127, in distributions_from_metadata
if len(os.listdir(path)) == 0:
PermissionError: [WinError 5] Access is denied: 'c:\\program files\\codeproject\\ai\\analysislayer\\bin\\windows\\python37\\venv\\lib\\site-packages\\zipp-3.11.0.dist-info'
Success
Downloading Standard YOLO models...Checking 'C:\Program Files\CodeProject\AI\downloads\ObjectDetectionYolo\models-yolo5-pt.zip'
Access is denied.
Start-BitsTransfer : Cannot find path 'C:\Program Files\CodeProject\AI\downloads\ObjectDetectionYolo' because it does
not exist.
At line:1 char:1
+ Start-BitsTransfer -Source 'https://codeproject-ai.s3.ca-central-1.am ...
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ CategoryInfo : ObjectNotFound: (C:\Program File...ctDetectionYolo:String) [Start-BitsTransfer], ParentC
ontainsErrorRecordException
+ FullyQualifiedErrorId : PathNotFound,Microsoft.BackgroundIntelligentTransfer.Management.NewBitsTransferCommand
An error occurred that could not be resolved.
Module setup complete
PS C:\Program Files\CodeProject\AI\AnalysisLayer\ObjectDetectionYolo>
|
|
|
|
|
anything else we can try, as I can see its not doing a install at all and skips the yolo install.
|
|
|
|
|
have a new error now why it wont launch AIOHTTP
18:52:53:Module 'Object Detection (YOLOv5 6.2)' (ID: ObjectDetectionYolo)
18:52:53:Active: True
18:52:53:GPU: Support enabled
18:52:53:Parallelism: 0
18:52:53:Platforms: all
18:52:53:FilePath: detect_adapter.py
18:52:53:ModulePath: ObjectDetectionYolo
18:52:53:Install: PreInstalled
18:52:53:Runtime: python37
18:52:53:Queue: objectdetection_queue
18:52:53:Start pause: 1 sec
18:52:53:Valid: True
18:52:53:Environment Variables
18:52:53:APPDIR = %CURRENT_MODULE_PATH%
18:52:53:CPAI_CUDA_DEVICE_NUM = 0
18:52:53:CPAI_HALF_PRECISION = force
18:52:53:CPAI_MODULE_SUPPORT_GPU = True
18:52:53:CUSTOM_MODELS_DIR = %CURRENT_MODULE_PATH%/custom-models
18:52:53:MODELS_DIR = %CURRENT_MODULE_PATH%/assets
18:52:53:MODEL_SIZE = Large
18:52:53:USE_CUDA = True
18:52:53:YOLOv5_AUTOINSTALL = false
18:52:53:YOLOv5_VERBOSE = false
18:52:53:
18:52:53:Started Object Detection (YOLOv5 6.2) module
18:52:53:detect_adapter.py: Traceback (most recent call last):
18:52:53:detect_adapter.py: File "C:\Program Files\CodeProject\AI\AnalysisLayer\ObjectDetectionYolo\detect_adapter.py", line 16, in
18:52:53:detect_adapter.py: from analysis.codeprojectai import CodeProjectAIRunner
18:52:53:detect_adapter.py: File "../../SDK/Python\analysis\codeprojectai.py", line 30, in
18:52:53:detect_adapter.py: import aiohttp
18:52:53:detect_adapter.py: ModuleNotFoundError: No module named 'aiohttp'
18:52:53:Module ObjectDetectionYolo has shutdown
18:52:53:detect_adapter.py: has exited
|
|
|
|
|
ok I managed to fix it and download all the required files and have it installed so now I can start it and run it on GPU CUDA but when its selected on CUDA it still shows its using only CPU to process and GPU stays at 0%
MY issue was the network card, I replaced the network card and now the downloads don't time out anymore and it was able to download the whole 2.4GB file and the rest of the files
01:45:08:Module 'Object Detection (YOLOv5 6.2)' (ID: ObjectDetectionYolo)
01:45:08:Active: True
01:45:08:GPU: Support enabled
01:45:08:Parallelism: 0
01:45:08:Platforms: all
01:45:08:FilePath: detect_adapter.py
01:45:08:ModulePath: ObjectDetectionYolo
01:45:08:Install: PreInstalled
01:45:08:Runtime: python37
01:45:08:Queue: objectdetection_queue
01:45:08:Start pause: 1 sec
01:45:08:Valid: True
01:45:08:Environment Variables
01:45:08:APPDIR = %CURRENT_MODULE_PATH%
01:45:08:CPAI_CUDA_DEVICE_NUM = 0
01:45:08:CPAI_HALF_PRECISION = force
01:45:08:CPAI_MODULE_SUPPORT_GPU = True
01:45:08:CUSTOM_MODELS_DIR = %CURRENT_MODULE_PATH%/custom-models
01:45:08:MODELS_DIR = %CURRENT_MODULE_PATH%/assets
01:45:08:MODEL_SIZE = tiny
01:45:08:USE_CUDA = True
01:45:08:YOLOv5_AUTOINSTALL = false
01:45:08:YOLOv5_VERBOSE = false
01:45:08:
01:45:08:Started Object Detection (YOLOv5 6.2) module
01:45:15:detect_adapter.py: APPDIR: C:\Program Files\CodeProject\AI\AnalysisLayer\ObjectDetectionYolo
01:45:15:detect_adapter.py: CPAI_PORT: 32168
01:45:15:detect_adapter.py: MODEL_SIZE: tiny
01:45:15:detect_adapter.py: MODELS_DIR: C:\Program Files\CodeProject\AI\AnalysisLayer\ObjectDetectionYolo\assets
01:45:15:detect_adapter.py: support_GPU: True
01:45:15:detect_adapter.py: use_CUDA: True
01:45:15:Object Detection (YOLOv5 6.2): Running init for Object Detection (YOLOv5 6.2)
01:45:15:Request 'detect' dequeued for processing (...777051)
01:45:15:Request 'detect' dequeued for processing (...be630f)
01:45:15:Object Detection (YOLOv5 6.2): Object Detection (YOLOv5 6.2) started.
01:45:15:Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command
01:45:15:Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command
01:45:17:Object Detection (YOLOv5 6.2): Model Path is C:\Program Files\CodeProject\AI\AnalysisLayer\ObjectDetectionYolo\assets\yolov5n.pt
01:45:17:Object Detection (YOLOv5 6.2): Queue and Processing Object Detection (YOLOv5 6.2) command 'detect' (...777051) took 2185ms
01:45:17:Object Detection (YOLOv5 6.2): Queue and Processing Object Detection (YOLOv5 6.2) command 'detect' (...be630f) took 2187ms
01:45:17:Response received (...be630f)
01:45:19:Client request 'detect' in the queue (...56e329)
01:45:19:Request 'detect' dequeued for processing (...56e329)
01:45:19:Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command
01:45:20:Object Detection (YOLOv5 6.2): Queue and Processing Object Detection (YOLOv5 6.2) command 'detect' (...56e329) took 46ms
01:45:20:Response received (...56e329)
|
|
|
|
|
I'm having the same issue. I haven't seen the install complete even once. I posted my issues today in a new thread. So you finally got yours to download and install? I must've tried 50 times now and it won't complete.
|
|
|
|
|
I managed to install it, and it works. I think one of the downloads failed because I had a VPN online.
16:44:53: Performing Install on module ALPR
16:46:38: WARNING: Retrying (Retry(total=0, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ConnectTimeoutError(, 'Connection to www.paddlepaddle.org.cn timed out. (connect timeout=15)')': /whl/windows/mkl/avx/stable.html
16:46:53: ERROR: Could not find a version that satisfies the requirement paddlepaddle-gpu==2.3.2.post116 (from versions: 1.3.1, 1.3.2, 1.4.0, 1.4.1, 1.5.0.post87, 1.5.0.post97, 1.5.1.post87, 1.5.1.post97, 1.5.2.post87, 1.5.2.post97, 1.5.2.post107, 1.6.0rc0.post107, 1.6.0.post97, 1.6.0.post107, 1.6.1.post97, 1.6.1.post107, 1.6.2.post97, 1.6.2.post107, 1.6.3.post97, 1.7.0.post97, 1.7.0.post107, 1.7.1.post97, 1.7.1.post107, 1.7.2.post97, 1.7.2.post107, 1.8.0.post97, 1.8.0.post107, 1.8.1.post97, 1.8.1.post107, 1.8.2.post97, 1.8.2.post107, 1.8.3.post97, 1.8.3.post107, 1.8.4.post97, 1.8.4.post107, 1.8.5.post97, 1.8.5.post107, 2.0.0a0, 2.0.0rc1, 2.0.0, 2.0.1, 2.0.2, 2.1.0, 2.1.1, 2.1.2, 2.1.3, 2.2.0rc0, 2.2.0, 2.2.1, 2.2.2, 2.3.0rc0, 2.3.0, 2.3.1, 2.3.2, 2.4.0rc0, 2.4.0, 2.4.1)
16:46:53: ERROR: No matching distribution found for paddlepaddle-gpu==2.3.2.post116
16:46:53: Installing Packages into Virtual Environment...Success
16:46:54: Ensuring Python package manager (pip) is installed...Done
16:46:54: Ensuring Python package manager (pip) is up to date...Done
16:46:54: Installing Python packages from requirements.txt...
16:46:58: Installing Packages into Virtual Environment...Success
16:46:58: Downloading ALPR models...Checking 'C:\Program Files\CodeProject\AI\downloads\ALPR\paddleocr-models.zip'
16:47:00: Expanding...Done.
16:47:00: Applying patch for PaddlePaddle
16:47:00: The system cannot find the path specified.
16:47:00: 0 file(s) copied.
16:47:00: Module setup complete
16:47:00: Module Automatic Licence Plate Recognition (ALPR) installed successfully.
16:47:00: Starting C:\Program Files...ws\python37\venv\Scripts\python "C:\Program Files...\modules\ALPR\ALPR_adapter.py"
16:47:00:
16:47:00: Module 'License Plate Reader' (ID: ALPR)
16:47:00: Active: True
16:47:00: GPU: Support enabled
16:47:00: Parallelism: 0
16:47:00: Platforms: windows,linux,macos,macos-arm64
16:47:00: FilePath: ALPR_adapter.py
16:47:00: ModulePath: ALPR
16:47:00: Install: PostInstalled
16:47:00: Runtime:
16:47:00: Queue: ALPR_queue
16:47:00: Start pause: 1 sec
16:47:00: Valid: True
16:47:00: Environment Variables
16:47:00: PLATE_CONFIDENCE = 0.4
16:47:00:
16:47:00: Started License Plate Reader module
16:47:00: ALPR_adapter.py: Traceback (most recent call last):
16:47:00: ALPR_adapter.py: File "C:\Program Files\CodeProject\AI\modules\ALPR\ALPR_adapter.py", line 19, in
16:47:00: ALPR_adapter.py: from ALPR import detect_platenumber
16:47:00: ALPR_adapter.py: File "C:\Program Files\CodeProject\AI\modules\ALPR\ALPR.py", line 8, in
16:47:00: ALPR_adapter.py: import utils.tools as tool
16:47:00: ALPR_adapter.py: File "C:\Program Files\CodeProject\AI\modules\ALPR\utils\tools.py", line 2, in
16:47:00: ALPR_adapter.py: import cv2
16:47:00: ALPR_adapter.py: ModuleNotFoundError: No module named 'cv2'
16:47:00: ALPR_adapter.py: has exited
16:47:01: Module ALPR started successfully.
16:48:29: Queued: 'alpr' request, id b548c6b8-ebe2-4309-ab7c-326ea6531c44
16:48:42: Queued: 'alpr' request, id fa0b9eff-f102-4cdc-bc96-3baa21af64a7
|
|
|
|
|
connection broken by 'ConnectTimeoutError
PaddlePaddle can be hard to download some days due to server errors their end
cheers
Chris Maunder
|
|
|
|
|
I've installed License Plate recognition in v2.0.6 Beta on Windows 11
Using the explorer I'm sending in this image:
https://platerecognizer.com/wp-content/uploads/2022/04/ANPR-United-Kingdom-London-Number-Plate-Reader-System-scaled.png[^]
result is:
according to this, it at least was/ is working elsewhere
Feature request: License Plate Reader · Issue #244 · ispysoftware/iSpy · GitHub[^]
I installed OCR to see if missing that was part of the problem and it might be as running that on a load of images containing text is also not returning anything.
under trace in logs i've got
11:28:47: 2023-01-24 11:44:14: Queued: 'alpr' request, id d3e931d7-6be9-4952-891b-ac4d532068fd
2023-01-24 11:44:14: Dequeued 'alpr' request, id d3e931d7-6be9-4952-891b-ac4d532068fd
2023-01-24 11:44:14: License Plate Reader: Retrieved ALPR_queue command in License Plate Reader
2023-01-24 11:44:14: Dequeued 'custom' request, id a5dd7cf6-1d1b-4d61-9ac9-dd9b67ad3e7d
2023-01-24 11:44:14: Queued: 'custom' request, id a5dd7cf6-1d1b-4d61-9ac9-dd9b67ad3e7d
2023-01-24 11:44:14: Object Detection (YOLOv5 6.2): Retrieved objectdetection_queue command in Object Detection (YOLOv5 6.2)
2023-01-24 11:44:14: Object Detection (YOLOv5 6.2): Detecting using license-plate in Object Detection (YOLOv5 6.2)
2023-01-24 11:44:14: Object Detection (YOLOv5 6.2): Queue and Processing Object Detection (YOLOv5 6.2) command 'custom' took 40ms (command timing) in Object Detection (YOLOv5 6.2)
2023-01-24 11:44:14: Response received (id a5dd7cf6-1d1b-4d61-9ac9-dd9b67ad3e7d)
2023-01-24 11:44:14: License Plate Reader: Queue and Processing License Plate Reader command 'alpr' took 54ms (command timing) in License Plate Reader
2023-01-24 11:44:14: Response received (id d3e931d7-6be9-4952-891b-ac4d532068fd)
System info
Operating System: Windows (Microsoft Windows 11 version 10.0.22000)
Architecture: x64
Target: Windows
BuildConfig: Release
Execution Env: Native
Runtime Env: Production
System GPU info:
GPU 3D Usage 10%
GPU RAM Usage 10 GiB
Video adapter info:
NVIDIA GeForce RTX 3080:
Device ID VideoController1
Adapter RAM 4 GiB
Adapter DAC Type Integrated RAMDAC
Driver Version 31.0.15.2756
Video Processor NVIDIA GeForce RTX 3080
Video Architecture VGA
Video Memory Type Unknown
Global Environment variables:
CPAI_APPROOTPATH = %ROOT_PATH%
CPAI_PORT = 32168
Installed on Docker and seems to work ok there
|
|
|
|
|
Try test the image using the license-plate custom model to check if that part is working. It might be a Windows 11 issue. Below I am using Windows 10 Pro.
|
|
|
|
|
yep seems to work fine with the vision license plate model.
Just everything i install under "Image" doesn't want to play on my PC.
Works on Docker. I stress tested the Docker version with LPR, sending it one image a second for a few minutes and the docker crashed - couldn't even stop it, had to restart the host.
|
|
|
|
|
Sean
I was seeing the same issue with reading plates. Have you tried switching to CPU for that module?
That resolved it for me.
|
|
|
|
|
This is working on both my CPU and GPU systems.
But then I am running a pre-release version that we hope to release today.
There where some fixes for the module installations that may be causing your issue.
You might try uninstalling the ALPR module and re-installing it.
Also, the first detection may fail and timeout due to the time it takes to load the model onto the GPU and other initializations.
"Time flies like an arrow. Fruit flies like a banana."
|
|
|
|
|
yeah i've done all that, uninstalled and reinstalled the whole thing 3 times. I'll try the next update and keep you posted.
|
|
|
|
|
Hello,
It would be very usefull (at least for me) to add a MQTT integration in CPAI to see if the app is running fine.
For exemple, i already use MQTT with Blue Iris to watch if the app is running fine : it publishes in a dedicated topic every minute and Home Assistant watch it and send me notification if there is no publishes in the last 5 minutes and automatically reload the app.
It's not a priority but it can be interesting for safety.
Thanks.
PS : why all my post need to be approved ?
|
|
|
|
|
An excellent suggestion. Thank you.
Approval: this will be partly because you're new to the forums so the spam filter is a little untrusting. That will ease up soon!
cheers
Chris Maunder
|
|
|
|
|
How's the testing progressing?
Thanks
|
|
|
|
|
Good question, I would like to know this as well.
|
|
|
|
|
Honestly, non-existent at the moment. We've wrecked ourselves getting the big 2.0 release out, and are now mopping up, putting out fires, sanding down the rough bits, and about to release the final piece of ad-hoc module installs (which is done and just in testing).
Our focus this week (after we sweep up the dust) is getting Raspberry Pi working, which involves a new module using Coral. The Raspberry Pi work is mostly done: we can run the full dev environment on an RPi meaning we can code and debug directly on a Pi. We have a docker image that runs. We just don't have modules fast enough or lean enough for the Pi, which is where external accelerators like the Coral fit in.
cheers
Chris Maunder
|
|
|
|
|
Dear Chris,
So reading between the lines .. Future direction / Roadmap is to eliminate the Nvidia GPU card and acquire a Pi with an external accelerator like Coral that BlurIris will query?
|
|
|
|
|
No, not at all.
The whole point of our module system is to allow developers to create modules to suit different hardware and OS combos. I'm planning on running most things on my mac mini. Matthew has an awesome NVidia rig, as do many others. However, I also have some plans to deploy a Raspberry Pi - both in my home and also in my car (I have a cool project I hope I can write up soon).
It's never about eliminating options. It's about providing options.
cheers
Chris Maunder
|
|
|
|
|
Sounds awesome, I've been pondering a Pi based car computer and image recognition stuff. Would be interested in your car project when you get a write up done.
|
|
|
|
|
Working!
Inference times are about 2s on a fairly large image, so the work now is to streamline that and play with the settings.
cheers
Chris Maunder
|
|
|
|
|
Holy moly, this is great news! 👏🏻
|
|
|
|
|
That's super exciting, have a Coral in my BlueIris computer, can't wait to put it to work with this.
|
|
|
|
|
Hi ,
I have AI integrated with blue iris and it is working quite well detecting person,car , dog etc but I cant seem to get it to trigger an alert with MQTT . MQTT works but the alert with say a person will not . Anyone got any suggestions ?
|
|
|
|
|