|
IF YOU ARE HAVING A PROBLEM
- Take a look at the logs in
C:\Program Files\CodeProject\AI\logs and see if there's anything in there that screams 'something broke'.
- Check the FAQs in the CodeProject.AI Server documentation
- Make sure you've tested the server using the Explorer (blue link, top middle of the dashboard) to ensure it's a server issue rather than something else such as Blue Iris or another app using CodeProject.AI server.
- If there's no obvious answer, then copy and paste into a message the contents of the System Info tab, describe what you are doing, and what you see, and what you would expect.
Always include a copy and paste from the System Info tab of the dashboard. It gives us a ton of info on your setup. If an individual module is failing, click the 'Info' button to the right of the module's name in the status list and copy and paste that info too.
How to reinstall a module
Option 1. Go to the install modules tab on the dashboard and try re-installing the package. Make sure you have enough disk space and a reliable internet connection.
Option 2: (Option 1 with a vengeance): If that fails, head to the module's folder ([app root]\modules\module-id), open a terminal in admin mode, and run ..\..\setup . This will force a manual reinstall using the install script.
Docker: In Docker you will need to open a terminal into the docker container. You can do this using Docker Desktop, or Visual Studio Code with the Docker remote extension, or on the command using using docker attach . Then do a cd /app/modules/module-id where module-id is the id of the module you need to resinstall. Next, run sudo bash ../../setup.sh --verbosity info to force a manual reinstall of that module. (Set verbosity as quiet, info or loud to get less or more info)
cheers
Chris Maunder
modified 18-Feb-24 15:48pm.
|
|
|
|
|
If you are a Blue Iris user and you are using custom models, then you would notice that the option, in Blue Iris, to set the custom model location is greyed out. This is because Blue Iris does not currently make changes to CodeProject.AI Server's settings. It can be done by manually starting CodeProject.AI with command line parameters (not a great solution), or editing the module settings files (a little messy), or setting system-wide environment variables (way easier). For version 1.6 we added an API to allow any app to change our settings programmatically, and we take care of stopping/restarting things and persisting the changes.
So: Blue Iris doesn't currently change CodeProject.AI Server's settings, so it doesn't provide you a way to change the custom model folder location from within Blue Iris.
Blue Iris will still use the contents of this folder to determine the calls it makes. If you don't specify a model to use in the Custom Models textbox, then Blue Iris will use all models in the custom models folder that it knows about.
Here we've specified a specific model to use. The Blue Iris help file explains more about how this works, including inclusive and exclusive filters on the models it finds.
CodeProject.AI Server doesn't know about Blue Iris' folder, so it can't tell what models it may be expected to use, nor can it tell Blue Iris about what models CodeProject.AI server has available. Our API allows Blue Iris to get a list of the AI models installed with CodeProject.AI Server, and also to set the folder where these models reside. But Blue Iris doesn't, yet, use that API.
So we do a hack.
At install time we sniff the registry to find where Blue Iris thinks the custom models should be. We then make empty copies of the models that we have, and copy them into that folder. If the folder doesn't exist (eg you were using C:\Program Files\CodeProject\AI\AnalysisLayer\CustomObjectDetection\assets , which no longer exists) then we create that folder, and then copy over the empty files.
When Blue Iris looks in that folder to decide what custom calls it can make, it sees the models, notes their names, and uses those names in the calls. CodeProject.AI Server has those models, so when the calls come through we can process them.
Blue Iris doesn't use the models. It uses the list of model names.
If you have your own models in the Blue Iris folder
You will need to copy them to the CodeProject.AI server's custom model folder (by default this is C:\Program Files\CodeProject\AI\AnalysisLayer\ObjectDetectionYolo\custom-models )
If you've modified the registry and have your own custom models
If you were using a folder in C:\Program Files\CodeProject\AI\AnalysisLayer\CustomObjectDetection\ (which no longer existed after the upgrade, but was recreated by our hack) you'll need to re-copy your custom model into that folder.
The simplest solutions are:
- Modify the registry (Computer\HKEY_LOCAL_MACHINE\SOFTWARE\Perspective Software\Blue Iris\Options\AI, key 'deepstack_custompath') so Blue Iris looks in
C:\Program Files\CodeProject\AI\AnalysisLayer\ObjectDetectionYolo\custom-models for custom models, and copy your models into there.
or
- Modify
C:\Program Files\CodeProject\AI\AnalysisLayer\ObjectDetectionYolo\modulesettings.json file and set CUSTOM_MODELS_DIR to be whatever Blue Iris thinks the custom model folder is.
cheers
Chris Maunder
|
|
|
|
|
I'd like to start by mentioning that CP.AI works beautifully... when it works.
Usually, that happens after I spend several hours fixing its installation after each update. This is a process that is, and has been in DIRE need of improvement for the last couple years since I started using CP.AI.
Updating from 2.6.2 to 2.6.5 is no different.
2.6.2 worked perfectly for months (that is, since about a day after I upgraded, because the first day was spent fixing the update process). Using YOLOv8 and License Plate Reader on a dedicated machine hosting Blue Iris, with an RTX 4060 as GPU.
I installed 2.6.5 - the default modules checked were YOLOv5 .NET and YOLOv5 6.2; since I use none, I unchecked them and checked YOLOv8 and License Plate Reader. Much to my surprise, once everything was installed, I found out that my options were ignored. It happens, I guess.
I uninstalled those modules and clicked "Install" (with "Do not use cache enabled") next to YOLOv8 module.
Nothing.
After several attempts, I restarted the CP.AI service - still nothing, no reaction to pressing the button for YOLOv8 module.
Running out of options, I restarted the whole PC and reinstalled CP.AI 2.6.5, once again checking YOLOv8 and License Plate Reader only.
Surprisingly, this time, the modules started installing... there is hope.
But both YOLOv8 and ALPR modules failed to install and start properly.
Log is below:
<pre>18:07:31:Installing module 'ObjectDetectionYOLOv8'
18:07:31:ObjectDetectionYOLOv8: Installing CodeProject.AI Analysis Module
18:07:31:ObjectDetectionYOLOv8: ======================================================================
18:07:31:ObjectDetectionYOLOv8: CodeProject.AI Installer
18:07:31:ObjectDetectionYOLOv8: ======================================================================
18:07:31:ObjectDetectionYOLOv8: 868.3Gb of 976Gb available on BIBoot
18:07:31:ObjectDetectionYOLOv8: General CodeProject.AI setup
18:07:31:ObjectDetectionYOLOv8: Creating Directories...done
18:07:31:ObjectDetectionYOLOv8: GPU support
18:07:31:ObjectDetectionYOLOv8: CUDA Present...Yes (CUDA 12.4, cuDNN 9.1)
18:07:31:ObjectDetectionYOLOv8: ROCm Present...No
18:07:31:ObjectDetectionYOLOv8: Checking for .NET 7.0...Checking SDKs...Upgrading: .NET is 0
18:07:31:ObjectDetectionYOLOv8: Current version is 0. Installing newer version.
18:07:31:ObjectDetectionYOLOv8: 'winget' is not recognized as an internal or external command,
18:07:31:ObjectDetectionYOLOv8: operable program or batch file.
18:07:33:ObjectDetectionYOLOv8: Reading ObjectDetectionYOLOv8 settings.......done
18:07:33:ObjectDetectionYOLOv8: Installing module Object Detection (YOLOv8) 1.4.3
18:07:33:Module ALPR started successfully.
18:07:33:ObjectDetectionYOLOv8: Installing Python 3.9
18:07:33:ObjectDetectionYOLOv8: Python 3.9 is already installed
18:07:38:ObjectDetectionYOLOv8: Creating Virtual Environment (Local)...done
18:07:38:ObjectDetectionYOLOv8: Confirming we have Python 3.9 in our virtual environment...present
18:07:38:ObjectDetectionYOLOv8: Installing Python packages for Object Detection (YOLOv8)
18:07:38:ObjectDetectionYOLOv8: [0;Installing GPU-enabled libraries: If available
18:07:40:ObjectDetectionYOLOv8: Ensuring Python package manager (pip) is installed...done
18:07:48:ObjectDetectionYOLOv8: Ensuring Python package manager (pip) is up to date...done
18:07:48:ObjectDetectionYOLOv8: Python packages specified by requirements.windows.cuda.txt
18:08:43:ObjectDetectionYOLOv8: - Installing PyTorch, an open source machine learning framework...(✅ checked) done
18:09:57:ObjectDetectionYOLOv8: - Installing TorchVision, for working with computer vision models...(✅ checked) done
18:11:46:ObjectDetectionYOLOv8: - Installing Ultralytics package for object detection in images...(✅ checked) done
18:11:47:ObjectDetectionYOLOv8: Installing Python packages for the CodeProject.AI Server SDK
18:11:48:ObjectDetectionYOLOv8: Ensuring Python package manager (pip) is installed...done
18:11:50:ObjectDetectionYOLOv8: Ensuring Python package manager (pip) is up to date...done
18:11:50:ObjectDetectionYOLOv8: Python packages specified by requirements.txt
18:11:51:ObjectDetectionYOLOv8: - Installing Pillow, a Python Image Library...Already installed
18:11:52:ObjectDetectionYOLOv8: - Installing Charset normalizer...Already installed
18:11:56:ObjectDetectionYOLOv8: - Installing aiohttp, the Async IO HTTP library...(✅ checked) done
18:11:58:ObjectDetectionYOLOv8: - Installing aiofiles, the Async IO Files library...(✅ checked) done
18:11:59:ObjectDetectionYOLOv8: - Installing py-cpuinfo to allow us to query CPU info...Already installed
18:12:00:ObjectDetectionYOLOv8: - Installing Requests, the HTTP library...Already installed
18:12:01:ObjectDetectionYOLOv8: Scanning modulesettings for downloadable models...Processing model list
18:14:52:ObjectDetectionYOLOv8: Downloading YOLOv8 Object Detection all sizes...Expanding...done.
18:14:52:ObjectDetectionYOLOv8: Copying contents of objectdetection-coco-yolov8-pt-nsmlx.zip to assets...done
18:18:04:ObjectDetectionYOLOv8: Downloading YOLOv8 Object Segmentation all sizes...Expanding...done.
18:18:04:ObjectDetectionYOLOv8: Copying contents of objectsegmentation-coco-yolov8-pt-nsmlx.zip to assets...done
18:18:34:ObjectDetectionYOLOv8: Downloading YOLOv8 Object Custom models...Expanding...done.
18:18:34:ObjectDetectionYOLOv8: Copying contents of objectdetection-custom-yolov8-pt-m.zip to custom-models...done
18:18:38:ObjectDetectionYOLOv8: A module that was compiled using NumPy 1.x cannot be run in
18:18:38:ObjectDetectionYOLOv8: NumPy 2.0.0 as it may crash. To support both 1.x and 2.x
18:18:38:ObjectDetectionYOLOv8: versions of NumPy, modules must be compiled with NumPy 2.0.
18:18:38:ObjectDetectionYOLOv8: Some module may need to rebuild instead e.g. with 'pybind11>=2.12'.
18:18:38:ObjectDetectionYOLOv8: If you are a user of the module, the easiest solution will be to
18:18:38:ObjectDetectionYOLOv8: downgrade to 'numpy<2' or try to upgrade the affected module.
18:18:38:ObjectDetectionYOLOv8: We expect that some modules will need time to support NumPy 2.
18:18:38:ObjectDetectionYOLOv8: Traceback (most recent call last): File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\detect_adapter.py", line 20, in
18:18:38:ObjectDetectionYOLOv8: from detect import do_detection
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\detect.py", line 11, in
18:18:38:ObjectDetectionYOLOv8: from ultralytics import YOLO
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\lib\site-packages\ultralytics\__init__.py", line 5, in
18:18:38:ObjectDetectionYOLOv8: from ultralytics.data.explorer.explorer import Explorer
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\lib\site-packages\ultralytics\data\__init__.py", line 3, in
18:18:38:ObjectDetectionYOLOv8: from .base import BaseDataset
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\lib\site-packages\ultralytics\data\base.py", line 12, in
18:18:38:ObjectDetectionYOLOv8: import cv2
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\lib\site-packages\cv2\__init__.py", line 181, in
18:18:38:ObjectDetectionYOLOv8: bootstrap()
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\lib\site-packages\cv2\__init__.py", line 153, in bootstrap
18:18:38:ObjectDetectionYOLOv8: native_module = importlib.import_module("cv2")
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python39\lib\importlib\__init__.py", line 127, in import_module
18:18:38:ObjectDetectionYOLOv8: return _bootstrap._gcd_import(name[level:], package, level)
18:18:38:ObjectDetectionYOLOv8: AttributeError: _ARRAY_API not found
18:18:38:ObjectDetectionYOLOv8: Traceback (most recent call last):
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\detect_adapter.py", line 20, in
18:18:38:ObjectDetectionYOLOv8: from detect import do_detection
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\detect.py", line 11, in
18:18:38:ObjectDetectionYOLOv8: from ultralytics import YOLO
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\lib\site-packages\ultralytics\__init__.py", line 5, in
18:18:38:ObjectDetectionYOLOv8: from ultralytics.data.explorer.explorer import Explorer
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\lib\site-packages\ultralytics\data\__init__.py", line 3, in
18:18:38:ObjectDetectionYOLOv8: from .base import BaseDataset
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\lib\site-packages\ultralytics\data\base.py", line 12, in
18:18:38:ObjectDetectionYOLOv8: import cv2
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\lib\site-packages\cv2\__init__.py", line 181, in
18:18:38:ObjectDetectionYOLOv8: bootstrap()
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\lib\site-packages\cv2\__init__.py", line 153, in bootstrap
18:18:38:ObjectDetectionYOLOv8: native_module = importlib.import_module("cv2")
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python39\lib\importlib\__init__.py", line 127, in import_module
18:18:38:ObjectDetectionYOLOv8: return _bootstrap._gcd_import(name[level:], package, level)
18:18:38:ObjectDetectionYOLOv8: ImportError: numpy.core.multiarray failed to import
18:18:38:ObjectDetectionYOLOv8: Self test: Self-test passed
18:18:38:ObjectDetectionYOLOv8: Module setup time 00:11:06.29
18:18:38:ObjectDetectionYOLOv8: Setup complete
18:18:38:ObjectDetectionYOLOv8: Total setup time 00:11:06.94
18:18:38:Module ObjectDetectionYOLOv8 installed successfully.
18:18:38:Module ObjectDetectionYOLOv8 not configured to AutoStart.
18:18:38:Installer exited with code 0
Now, I am not a Python developer, therefore I don't know how to resolve this. I do see there are two separate problems:
1.
18:07:31:ObjectDetectionYOLOv8: Checking for .NET 7.0...Checking SDKs...Upgrading: .NET is 0
18:07:31:ObjectDetectionYOLOv8: Current version is 0. Installing newer version.
18:07:31:ObjectDetectionYOLOv8: 'winget' is not recognized as an internal or external command,
18:07:31:ObjectDetectionYOLOv8: operable program or batch file.
2.
<pre>18:18:38:ObjectDetectionYOLOv8: A module that was compiled using NumPy 1.x cannot be run in
18:18:38:ObjectDetectionYOLOv8: NumPy 2.0.0 as it may crash. To support both 1.x and 2.x
18:18:38:ObjectDetectionYOLOv8: versions of NumPy, modules must be compiled with NumPy 2.0.
18:18:38:ObjectDetectionYOLOv8: Some module may need to rebuild instead e.g. with 'pybind11>=2.12'.
18:18:38:ObjectDetectionYOLOv8: If you are a user of the module, the easiest solution will be to
18:18:38:ObjectDetectionYOLOv8: downgrade to 'numpy<2' or try to upgrade the affected module.
18:18:38:ObjectDetectionYOLOv8: We expect that some modules will need time to support NumPy 2.
18:18:38:ObjectDetectionYOLOv8: Traceback (most recent call last): File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\detect_adapter.py", line 20, in
18:18:38:ObjectDetectionYOLOv8: from detect import do_detection
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\detect.py", line 11, in
18:18:38:ObjectDetectionYOLOv8: from ultralytics import YOLO
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\lib\site-packages\ultralytics\__init__.py", line 5, in
18:18:38:ObjectDetectionYOLOv8: from ultralytics.data.explorer.explorer import Explorer
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\lib\site-packages\ultralytics\data\__init__.py", line 3, in
18:18:38:ObjectDetectionYOLOv8: from .base import BaseDataset
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\lib\site-packages\ultralytics\data\base.py", line 12, in
18:18:38:ObjectDetectionYOLOv8: import cv2
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\lib\site-packages\cv2\__init__.py", line 181, in
18:18:38:ObjectDetectionYOLOv8: bootstrap()
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\lib\site-packages\cv2\__init__.py", line 153, in bootstrap
18:18:38:ObjectDetectionYOLOv8: native_module = importlib.import_module("cv2")
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python39\lib\importlib\__init__.py", line 127, in import_module
18:18:38:ObjectDetectionYOLOv8: return _bootstrap._gcd_import(name[level:], package, level)
18:18:38:ObjectDetectionYOLOv8: AttributeError: _ARRAY_API not found
18:18:38:ObjectDetectionYOLOv8: Traceback (most recent call last):
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\detect_adapter.py", line 20, in
18:18:38:ObjectDetectionYOLOv8: from detect import do_detection
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\detect.py", line 11, in
18:18:38:ObjectDetectionYOLOv8: from ultralytics import YOLO
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\lib\site-packages\ultralytics\__init__.py", line 5, in
18:18:38:ObjectDetectionYOLOv8: from ultralytics.data.explorer.explorer import Explorer
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\lib\site-packages\ultralytics\data\__init__.py", line 3, in
18:18:38:ObjectDetectionYOLOv8: from .base import BaseDataset
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\lib\site-packages\ultralytics\data\base.py", line 12, in
18:18:38:ObjectDetectionYOLOv8: import cv2
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\lib\site-packages\cv2\__init__.py", line 181, in
18:18:38:ObjectDetectionYOLOv8: bootstrap()
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\lib\site-packages\cv2\__init__.py", line 153, in bootstrap
18:18:38:ObjectDetectionYOLOv8: native_module = importlib.import_module("cv2")
18:18:38:ObjectDetectionYOLOv8: File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python39\lib\importlib\__init__.py", line 127, in import_module
18:18:38:ObjectDetectionYOLOv8: return _bootstrap._gcd_import(name[level:], package, level)
18:18:38:ObjectDetectionYOLOv8: ImportError: numpy.core.multiarray failed to import
I attempted to fix the first issue by manually installing .NET 7.0 - which resolved exactly nothing. Same error messages appeared.
So, once again, I am at someone else's pity to help me successfully finalize the update.
Thank you!
|
|
|
|
|
I have resolved NumPy 2.0.0 error by downgrading to NumPy 1.23.0
For those which experience a similar issue, here are the steps:
1. Open a Command Prompt in Admin mode;
2. Navigate to the YOLOv8 installation folder, Scripts subfolder. In my case, the full path was
C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\bin\windows\python39\venv\Scripts>
3. Activate the virtual environment by typing:
activate
4. Run the following command:
pip install numpy==1.23.0
This will uninstall NumPy 2.0.0 and replace it with NumPy 1.23.0
Afterwards, the YOLOv8 module will start and run successfully.
At this point, I am too tired and fed up to even attempt installing other modules. At least Blue Iris sends info to CP.AI and detections are successfully processed.
|
|
|
|
|
YOLO5.Net stops running after an hour or two even though it's supposed to stop / start with Blue Iris. The Blue Iris Server is running. The CodeProjectAI server indicates it is still on-line.
How can I prevent YOLOv5.net from stopping?
19:25:51:System: Windows
19:25:51:Operating System: Windows (Microsoft Windows 11 version 10.0.22631)
19:25:51:CPUs: 13th Gen Intel(R) Core(TM) i7-1360P (Intel)
19:25:51: 1 CPU x 12 cores. 16 logical processors (x64)
19:25:51:GPU (Primary): Intel(R) Iris(R) Xe Graphics (128 MiB) (Intel Corporation)
19:25:51: Driver: 31.0.101.5522
19:25:51:System RAM: 32 GiB
19:25:51:Platform: Windows
19:25:51:BuildConfig: Release
19:25:51:Execution Env: Native
19:25:51:Runtime Env: Production
19:25:51:Runtimes installed:
19:25:51: .NET runtime: 8.0.3
19:25:51: .NET SDK: 8.0.202
19:25:51: Default Python: Not found
19:25:51: Go: Not found
19:25:51: NodeJS: Not found
19:25:51: Rust: Not found
19:25:51:App DataDir: C:\ProgramData\CodeProject\AI
19:25:51:Video adapter info:
19:25:51: Intel(R) Iris(R) Xe Graphics:
19:25:51: Driver Version 31.0.101.5522
19:25:51: Video Processor Intel(R) Iris(R) Xe Graphics Family
19:25:51:STARTING CODEPROJECT.AI SERVER
19:25:51:RUNTIMES_PATH = C:\Program Files\CodeProject\AI\runtimes
19:25:51:PREINSTALLED_MODULES_PATH = C:\Program Files\CodeProject\AI\preinstalled-modules
19:25:51:DEMO_MODULES_PATH = C:\Program Files\CodeProject\AI\src\demos\modules
19:25:51:EXTERNAL_MODULES_PATH =
19:25:51:MODULES_PATH = C:\Program Files\CodeProject\AI\modules
19:25:51:PYTHON_PATH = \bin\windows\%PYTHON_NAME%\venv\Scripts\python
19:25:51:Data Dir = C:\ProgramData\CodeProject\AI
19:25:51:Server version: 2.6.5
19:25:55:
19:25:55:Module 'Face Processing' 1.10.2 (ID: FaceProcessing)
19:25:55:Valid: True
19:25:55:Module Path: <root>\modules\FaceProcessing
19:25:55:Module Location: Internal
19:25:55:AutoStart: True
19:25:55:Queue: faceprocessing_queue
19:25:55:Runtime: python3.7
19:25:55:Runtime Location: Shared
19:25:55:FilePath: intelligencelayer\face.py
19:25:55:Start pause: 3 sec
19:25:55:Parallelism: 0
19:25:55:LogVerbosity:
19:25:55:Platforms: all,!jetson
19:25:55:GPU Libraries: installed if available
19:25:55:GPU: use if supported
19:25:55:Accelerator:
19:25:55:Half Precision: enable
19:25:55:Environment Variables
19:25:55:APPDIR = <root>\modules\FaceProcessing\intelligencelayer
19:25:55:DATA_DIR = C:\ProgramData\CodeProject\AI
19:25:55:MODE = MEDIUM
19:25:55:MODELS_DIR = <root>\modules\FaceProcessing\assets
19:25:55:PROFILE = desktop_gpu
19:25:55:USE_CUDA = True
19:25:55:YOLOv5_AUTOINSTALL = false
19:25:55:YOLOv5_VERBOSE = false
19:25:55:
19:25:55:Started Face Processing module
19:25:57:Server: This is the latest version
19:28:35:Sending shutdown request to python/FaceProcessing
19:28:49:face.py: Face Processing started.
19:28:50:Module FaceProcessing has shutdown
19:28:50:face.py: has exited
19:29:08:FaceProcessing went quietly
Logging level
|
|
|
|
|
If I already have cropped plates is it possible to bypass detecting what is a plate and just submit a cropped plate to the OCR part and return the plate?
|
|
|
|
|
Can you post some sample images at full resolution. I will try add the option to only run the OCR in the next release of the ALPR module.
|
|
|
|
|
System info:
Server version: 2.6.5
System: Windows
Operating System: Windows (Microsoft Windows 10.0.19045)
CPUs: Intel(R) Core(TM) i5-7500 CPU @ 3.40GHz (Intel)
1 CPU x 4 cores. 4 logical processors (x64)
GPU (Primary): Intel(R) HD Graphics 630 (1,024 MiB) (Intel Corporation)
Driver: 31.0.101.2111
System RAM: 16 GiB
Platform: Windows
BuildConfig: Release
Execution Env: Native
Runtime Env: Production
Runtimes installed:
.NET runtime: 7.0.5
.NET SDK: Not found
Default Python: Not found
Go: Not found
NodeJS: Not found
Rust: Not found
Video adapter info:
Intel(R) HD Graphics 630:
Driver Version 31.0.101.2111
Video Processor Intel(R) HD Graphics Family
System GPU info:
GPU 3D Usage 4%
GPU RAM Usage 0
Global Environment variables:
CPAI_APPROOTPATH = <root>
CPAI_PORT = 32168
I am assuming that I need to use the Default Objects setting in Blue Iris since there are no real models that reduce the number of objects that are found using the Coral module.
Blue Iris AI Settings:
Blue Iris Camera Settings:
Are there any recommended settings for the Coral Module that I can use to improve the accuracy of the results from the Coral Module?
Using what I assume are the default settings for the Coral module, I get this in Blue Iris.
The Coral module seems to return lots and lots of "persons". (Plus an Airplane?) Is there any Coral Model that is more accurate? I have changed the model size from small to medium, but this doesn't seem to have any affect.
I keep going back to the YOLOv5 .Net module, which is slower, but seems to be more accurate using the ipcam-* models.
Coral Module Info:
Module 'Object Detection (Coral)' 2.2.2 (ID: ObjectDetectionCoral)
Valid: True
Module Path: <root>\modules\ObjectDetectionCoral
Module Location: Internal
AutoStart: True
Queue: objectdetection_queue
Runtime: python3.9
Runtime Location: Local
FilePath: objectdetection_coral_adapter.py
Start pause: 1 sec
Parallelism: 16
LogVerbosity:
Platforms: all
GPU Libraries: installed if available
GPU: use if supported
Accelerator:
Half Precision: enable
Environment Variables
CPAI_CORAL_MODEL_NAME = MobileNet SSD
CPAI_CORAL_MULTI_TPU = True
MODELS_DIR = <root>\modules\ObjectDetectionCoral\assets
MODEL_SIZE = medium
Status Data: {
"inferenceDevice": "Multi-TPU",
"inferenceLibrary": "TF-Lite",
"canUseGPU": "false",
"successfulInferences": 297,
"failedInferences": 7,
"numInferences": 304,
"averageInferenceMs": 13.447811447811448
}
Started: 12 Jun 2024 9:08:09 AM Central Standard Time
LastSeen: 12 Jun 2024 9:19:16 AM Central Standard Time
Status: Stopped
Requests: 304 (includes status calls)
Installation Log
2024-06-06 08:00:39: Installing CodeProject.AI Analysis Module
2024-06-06 08:00:39: ======================================================================
2024-06-06 08:00:39: CodeProject.AI Installer
2024-06-06 08:00:39: ======================================================================
2024-06-06 08:00:39: 285.7Gb of 487Gb available on
2024-06-06 08:00:39: General CodeProject.AI setup
2024-06-06 08:00:39: Creating Directories...Done
2024-06-06 08:00:39: GPU support
2024-06-06 08:00:40: CUDA Present...No
2024-06-06 08:00:40: ROCm Present...No
2024-06-06 08:00:42: Reading ObjectDetectionCoral settings.......Done
2024-06-06 08:00:42: Installing module Object Detection (Coral) 2.1.6
2024-06-06 08:00:42: Installing Python 3.9
2024-06-06 08:00:49: Downloading Python 3.9 interpreter...Expanding...Done.
2024-06-06 08:00:57: Creating Virtual Environment (Local)...Done
2024-06-06 08:00:58: Confirming we have Python 3.9 in our virtual environment...present
2024-06-06 08:01:01: Downloading edge TPU runtime...Expanding...Done.
2024-06-06 08:01:01: Copying contents of edgetpu_runtime-20221024.zip to edgetpu_runtime...done
2024-06-06 08:01:01: Installing the edge TPU libraries...
2024-06-06 08:01:01: Installing UsbDk
2024-06-06 08:01:02: Installing Windows drivers
2024-06-06 08:01:02: Microsoft PnP Utility
2024-06-06 08:01:02: Adding driver package: coral.inf
2024-06-06 08:01:02: Driver package added successfully. (Already exists in the system)
2024-06-06 08:01:02: Published Name: oem40.inf
2024-06-06 08:01:02: Driver package is up-to-date on device: PCI\VEN_1AC1&DEV_089A&SUBSYS_089A1AC1&REV_00\4&6ba732e&0&00D8
2024-06-06 08:01:02: Adding driver package: Coral_USB_Accelerator.inf
2024-06-06 08:01:02: Driver package added successfully. (Already exists in the system)
2024-06-06 08:01:02: Published Name: oem43.inf
2024-06-06 08:01:02: Driver package installed on device: USB\VID_18D1&PID_9302\5&220fb38b&0&10
2024-06-06 08:01:02: Adding driver package: Coral_USB_Accelerator_(DFU).inf
2024-06-06 08:01:02: Driver package added successfully. (Already exists in the system)
2024-06-06 08:01:02: Published Name: oem55.inf
2024-06-06 08:01:02: Total driver packages: 3
2024-06-06 08:01:02: Added driver packages: 2
2024-06-06 08:01:02: Installing performance counters
2024-06-06 08:01:02: Info: Provider {aaa5bf9e-c44b-4177-af65-d3a06ba45fe7} defined in C:\Program Files\CodeProject\AI\modules\ObjectDetectionCoral\edgetpu_runtime\third_party\coral_accelerator_windows\coral.man is already installed in system repository.
2024-06-06 08:01:02: Info: Successfully installed performance counters in C:\Program Files\CodeProject\AI\modules\ObjectDetectionCoral\edgetpu_runtime\third_party\coral_accelerator_windows\coral.manCopying edgetpu and libusb to System32
2024-06-06 08:01:02: 1 file(s) copied.
2024-06-06 08:01:02: 1 file(s) copied.
2024-06-06 08:01:02: Install complete
2024-06-06 08:01:10: Downloading EfficientDet (large) models...Expanding...Done.
2024-06-06 08:01:10: Copying contents of objectdetection-efficientdet-large-edgetpu.zip to assets...done
2024-06-06 08:01:14: Downloading EfficientDet (medium) models...Expanding...Done.
2024-06-06 08:01:14: Copying contents of objectdetection-efficientdet-medium-edgetpu.zip to assets...done
2024-06-06 08:01:18: Downloading EfficientDet (small) models...Expanding...Done.
2024-06-06 08:01:19: Copying contents of objectdetection-efficientdet-small-edgetpu.zip to assets...done
2024-06-06 08:01:21: Downloading EfficientDet (tiny) models...Expanding...Done.
2024-06-06 08:01:21: Copying contents of objectdetection-efficientdet-tiny-edgetpu.zip to assets...done
2024-06-06 08:01:34: Downloading MobileNet (large) models...Expanding...Done.
2024-06-06 08:01:34: Copying contents of objectdetection-mobilenet-large-edgetpu.zip to assets...done
2024-06-06 08:01:37: Downloading MobileNet (medium) models...Expanding...Done.
2024-06-06 08:01:37: Copying contents of objectdetection-mobilenet-medium-edgetpu.zip to assets...done
2024-06-06 08:01:40: Downloading MobileNet (small) models...Expanding...Done.
2024-06-06 08:01:40: Copying contents of objectdetection-mobilenet-small-edgetpu.zip to assets...done
2024-06-06 08:01:43: Downloading MobileNet (tiny) models...Expanding...Done.
2024-06-06 08:01:43: Copying contents of objectdetection-mobilenet-tiny-edgetpu.zip to assets...done
2024-06-06 08:01:58: Downloading YOLOv8 (large) models...Expanding...Done.
2024-06-06 08:01:58: Copying contents of objectdetection-yolov8-large-edgetpu.zip to assets...done
2024-06-06 08:02:10: Downloading YOLOv8 (medium) models...Expanding...Done.
2024-06-06 08:02:13: Copying contents of objectdetection-yolov8-medium-edgetpu.zip to assets...done
2024-06-06 08:02:21: Downloading YOLOv8 (small) models...Expanding...Done.
2024-06-06 08:02:21: Copying contents of objectdetection-yolov8-small-edgetpu.zip to assets...done
2024-06-06 08:02:28: Downloading YOLOv8 (tiny) models...Expanding...Done.
2024-06-06 08:02:29: Copying contents of objectdetection-yolov8-tiny-edgetpu.zip to assets...done
2024-06-06 08:02:29: Installing Python packages for Object Detection (Coral)
2024-06-06 08:02:29: [0;Installing GPU-enabled libraries: If available
2024-06-06 08:02:34: Ensuring Python package manager (pip) is installed...Done
2024-06-06 08:02:44: Ensuring Python package manager (pip) is up to date...Done
2024-06-06 08:02:44: Python packages specified by requirements.windows.txt
2024-06-06 08:02:48: - Installing Pillow, a Python Image Library...(checked) Done
2024-06-06 08:02:54: - Installing Tensorflow Lite...(checked) Done
2024-06-06 08:03:02: - Installing PyCoral...(checked) Done
2024-06-06 08:03:21: - Installing NumPy, a package for scientific computing...Already installed
2024-06-06 08:03:21: Installing Python packages for the CodeProject.AI Server SDK
2024-06-06 08:03:23: Ensuring Python package manager (pip) is installed...Done
2024-06-06 08:03:25: Ensuring Python package manager (pip) is up to date...Done
2024-06-06 08:03:25: Python packages specified by requirements.txt
2024-06-06 08:03:26: - Installing Pillow, a Python Image Library...Already installed
2024-06-06 08:03:29: - Installing Charset normalizer...(checked) Done
2024-06-06 08:03:33: - Installing aiohttp, the Async IO HTTP library...(checked) Done
2024-06-06 08:03:35: - Installing aiofiles, the Async IO Files library...(checked) Done
2024-06-06 08:03:38: - Installing py-cpuinfo to allow us to query CPU info...(checked) Done
2024-06-06 08:03:41: - Installing Requests, the HTTP library...(checked) Done
2024-06-06 08:03:48: Self test: Self-test passed
2024-06-06 08:03:48: Module setup time 00:03:07.86
2024-06-06 08:03:48: Setup complete
2024-06-06 08:03:48: Total setup time 00:03:09.13
Installer exited with code 0
2024-06-10 17:22:48: Installing CodeProject.AI Analysis Module
2024-06-10 17:22:49: ======================================================================
2024-06-10 17:22:49: CodeProject.AI Installer
2024-06-10 17:22:49: ======================================================================
2024-06-10 17:22:50: 289.9Gb of 487Gb available on
2024-06-10 17:22:50: General CodeProject.AI setup
2024-06-10 17:22:50: Creating Directories...done
2024-06-10 17:22:50: GPU support
2024-06-10 17:22:51: CUDA Present...No
2024-06-10 17:22:51: ROCm Present...No
2024-06-10 17:22:51: Checking for .NET 7.0...Checking SDKs...Upgrading: .NET is 0
2024-06-10 17:22:51: Current version is 0. Installing newer version.
2024-06-10 17:22:51: 'winget' is not recognized as an internal or external command,
2024-06-10 17:22:51: operable program or batch file.
2024-06-10 17:22:54: Reading ObjectDetectionCoral settings.......done
2024-06-10 17:22:54: Installing module Object Detection (Coral) 2.2.2
2024-06-10 17:22:55: Installing Python 3.9
2024-06-10 17:22:55: Python 3.9 is already installed
2024-06-10 17:22:56: Creating Virtual Environment (Local)...Virtual Environment already present
2024-06-10 17:22:56: Confirming we have Python 3.9 in our virtual environment...present
2024-06-10 17:22:56: Installing the edge TPU libraries...
2024-06-10 17:22:56: Installing UsbDk
2024-06-10 17:22:57: Installing Windows drivers
2024-06-10 17:22:57: Microsoft PnP Utility
2024-06-10 17:22:57: Adding driver package: coral.inf
2024-06-10 17:22:57: Driver package added successfully. (Already exists in the system)
2024-06-10 17:22:57: Published Name: oem40.inf
2024-06-10 17:22:57: Driver package is up-to-date on device: PCI\VEN_1AC1&DEV_089A&SUBSYS_089A1AC1&REV_00\4&6ba732e&0&00D8
2024-06-10 17:22:57: Adding driver package: Coral_USB_Accelerator.inf
2024-06-10 17:22:57: Driver package added successfully. (Already exists in the system)
2024-06-10 17:22:57: Published Name: oem43.inf
2024-06-10 17:22:57: Driver package installed on device: USB\VID_18D1&PID_9302\5&220fb38b&0&10
2024-06-10 17:22:57: Adding driver package: Coral_USB_Accelerator_(DFU).inf
2024-06-10 17:22:57: Driver package added successfully. (Already exists in the system)
2024-06-10 17:22:57: Published Name: oem55.inf
2024-06-10 17:22:57: Total driver packages: 3
2024-06-10 17:22:57: Added driver packages: 2
2024-06-10 17:22:57: Installing performance counters
2024-06-10 17:22:57: Info: Provider {aaa5bf9e-c44b-4177-af65-d3a06ba45fe7} defined in C:\Program Files\CodeProject\AI\modules\ObjectDetectionCoral\edgetpu_runtime\third_party\coral_accelerator_windows\coral.man is already installed in system repository.
2024-06-10 17:22:57: Info: Successfully installed performance counters in C:\Program Files\CodeProject\AI\modules\ObjectDetectionCoral\edgetpu_runtime\third_party\coral_accelerator_windows\coral.manCopying edgetpu and libusb to System32
2024-06-10 17:22:57: 1 file(s) copied.
2024-06-10 17:22:57: 1 file(s) copied.
2024-06-10 17:22:57: Install complete
2024-06-10 17:23:07: Downloading EfficientDet (large) models...Expanding...done.
2024-06-10 17:23:07: Copying contents of objectdetection-efficientdet-large-edgetpu.zip to assets...done
2024-06-10 17:23:14: Downloading EfficientDet (medium) models...Expanding...done.
2024-06-10 17:23:14: Copying contents of objectdetection-efficientdet-medium-edgetpu.zip to assets...done
2024-06-10 17:23:21: Downloading EfficientDet (small) models...Expanding...done.
2024-06-10 17:23:21: Copying contents of objectdetection-efficientdet-small-edgetpu.zip to assets...done
2024-06-10 17:23:26: Downloading EfficientDet (tiny) models...Expanding...done.
2024-06-10 17:23:26: Copying contents of objectdetection-efficientdet-tiny-edgetpu.zip to assets...done
2024-06-10 17:23:44: Downloading MobileNet (large) models...Expanding...done.
2024-06-10 17:23:44: Copying contents of objectdetection-mobilenet-large-edgetpu.zip to assets...done
2024-06-10 17:23:47: Downloading MobileNet (medium) models...Expanding...done.
2024-06-10 17:23:47: Copying contents of objectdetection-mobilenet-medium-edgetpu.zip to assets...done
2024-06-10 17:23:51: Downloading MobileNet (small) models...Expanding...done.
2024-06-10 17:23:51: Copying contents of objectdetection-mobilenet-small-edgetpu.zip to assets...done
2024-06-10 17:23:55: Downloading MobileNet (tiny) models...Expanding...done.
2024-06-10 17:23:55: Copying contents of objectdetection-mobilenet-tiny-edgetpu.zip to assets...done
2024-06-10 17:24:15: Downloading YOLOv8 (large) models...Expanding...done.
2024-06-10 17:24:15: Copying contents of objectdetection-yolov8-large-edgetpu.zip to assets...done
2024-06-10 17:24:30: Downloading YOLOv8 (medium) models...Expanding...done.
2024-06-10 17:24:30: Copying contents of objectdetection-yolov8-medium-edgetpu.zip to assets...done
2024-06-10 17:24:34: Downloading YOLOv8 (small) models...Expanding...done.
2024-06-10 17:24:34: Copying contents of objectdetection-yolov8-small-edgetpu.zip to assets...done
2024-06-10 17:24:35: Downloading YOLOv8 (tiny) models...Expanding...done.
2024-06-10 17:24:35: Copying contents of objectdetection-yolov8-tiny-edgetpu.zip to assets...done
2024-06-10 17:24:35: Installing Python packages for Object Detection (Coral)
2024-06-10 17:24:35: [0;Installing GPU-enabled libraries: If available
2024-06-10 17:24:37: Ensuring Python package manager (pip) is installed...done
2024-06-10 17:24:40: Ensuring Python package manager (pip) is up to date...done
2024-06-10 17:24:40: Python packages specified by requirements.windows.txt
2024-06-10 17:24:41: - Installing Pillow, a Python Image Library...Already installed
2024-06-10 17:24:42: - Installing Tensorflow Lite...Already installed
2024-06-10 17:24:43: - Installing PyCoral...Already installed
2024-06-10 17:25:05: - Installing NumPy, a package for scientific computing...Already installed
2024-06-10 17:25:05: Installing Python packages for the CodeProject.AI Server SDK
2024-06-10 17:25:06: Ensuring Python package manager (pip) is installed...done
2024-06-10 17:25:09: Ensuring Python package manager (pip) is up to date...done
2024-06-10 17:25:09: Python packages specified by requirements.txt
2024-06-10 17:25:10: - Installing Pillow, a Python Image Library...Already installed
2024-06-10 17:25:11: - Installing Charset normalizer...Already installed
2024-06-10 17:25:12: - Installing aiohttp, the Async IO HTTP library...Already installed
2024-06-10 17:25:13: - Installing aiofiles, the Async IO Files library...Already installed
2024-06-10 17:25:14: - Installing py-cpuinfo to allow us to query CPU info...Already installed
2024-06-10 17:25:15: - Installing Requests, the HTTP library...Already installed
2024-06-10 17:25:16: Scanning modulesettings for downloadable models...Processing model list
2024-06-10 17:25:17: Downloading MobileNet Large...already exists...Expanding...done.
2024-06-10 17:25:17: Copying contents of objectdetection-mobilenet-large-edgetpu.zip to assets...done
2024-06-10 17:25:19: Downloading MobileNet Medium...already exists...Expanding...done.
2024-06-10 17:25:19: Copying contents of objectdetection-mobilenet-medium-edgetpu.zip to assets...done
2024-06-10 17:25:20: Downloading MobileNet Small...already exists...Expanding...done.
2024-06-10 17:25:20: Copying contents of objectdetection-mobilenet-small-edgetpu.zip to assets...done
2024-06-10 17:25:22: Downloading MobileNet Tiny...already exists...Expanding...done.
2024-06-10 17:25:22: Copying contents of objectdetection-mobilenet-tiny-edgetpu.zip to assets...done
2024-06-10 17:25:36: Self test: Self-test passed
2024-06-10 17:25:36: Module setup time 00:02:44.52
2024-06-10 17:25:36: Setup complete
2024-06-10 17:25:36: Total setup time 00:02:46.62
Installer exited with code 0
|
|
|
|
|
Someone else will need to get you the correct settings, but I suspect that yours are wrong because ‘IPcam-combined’ isn’t currently supported for Coral. Try using the default model first instead of a custom one. Also, your confidence threshold is low.
Edit: also, are you able to switch to YOLOv8 from MobileNet SSD?
|
|
|
|
|
Maybe I didn't explain completely.
I go back to YOLOv5 .NET because I get more accurate results with the YOLOv5.NET WITH the ipcam-* models.
I know those models are not available with the Coral modules.
That's why I use the Default Objects settings.
|
|
|
|
|
AFAIK the Use custom models and the use default objects options on the Settings AI page control how the request to CPAI is constructed.
The ipcam-combined model field in the camera page is ignored if the default objects checkbox is checked.
|
|
|
|
|
Also, confidence was set low because at one time I was missing things like persons, cars, busses etc. I eventually got tired of spending hours trying to find tune those settings. BTW, the YOLO modules work fine with those settings. Just Coral module produces those multiple "person" identifications.
I will try the YOLO8 model in the Coral module. (Again)
|
|
|
|
|
Changed to YOLO V8 Using Default Object Detection in Blue Iris.
Module 'Object Detection (Coral)' 2.2.2 (ID: ObjectDetectionCoral)
Valid: True
Module Path: <root>\modules\ObjectDetectionCoral
AutoStart: True
Queue: objectdetection_queue
Runtime: python3.9
Runtime Loc: Local
FilePath: objectdetection_coral_adapter.py
Start pause: 1 sec
Parallelism: 16
LogVerbosity:
Platforms: all
GPU Libraries: installed if available
GPU Enabled: enabled
Accelerator:
Half Precis.: enable
Environment Variables
CPAI_CORAL_MODEL_NAME = YOLOv8
CPAI_CORAL_MULTI_TPU = true
MODELS_DIR = <root>\modules\ObjectDetectionCoral\assets
MODEL_SIZE = medium
Status Data: {
"inferenceDevice": "Multi-TPU",
"inferenceLibrary": "TF-Lite",
"canUseGPU": "false",
"successfulInferences": 384,
"failedInferences": 0,
"numInferences": 384,
"averageInferenceMs": 14.434895833333334
}
Started: 12 Jun 2024 4:36:46 PM Central Standard Time
LastSeen: 12 Jun 2024 4:42:47 PM Central Standard Time
Status: Started
Requests: 445 (includes status calls)
Results:
I'm going to remove the "Banana" from the cancel textbox.
|
|
|
|
|
I'm done trying this for now.
I've also been trying to get a handle on a memory leak that started on 6/6 when I installed 2.6.5. Blue Iris goes from ~600 mBytes to ~9 gBytes over about 15 hours. Eventually Blue Iris shows only "nothing found".
Back to Old Faithful.
|
|
|
|
|
Hi,
Following upgrade to CPAI 2.6.5 on Ubuntu I have seen the Coral module crash several times, with the UI showing "Lost Contact" with the module and the following log messages:
09:02:11:Response rec'd from Object Detection (Coral) command 'detect' (...ee25ac) [''] took 21ms
09:03:17:objectdetection_coral_adapter.py: WARNING:root:Queue stalled; refreshing interpreters.
09:03:18:objectdetection_coral_adapter.py: WARNING:root:Queue stalled; refreshing interpreters.
09:04:13:objectdetection_coral_adapter.py: WARNING:root:Queue stalled; refreshing interpreters.
09:04:15:objectdetection_coral_adapter.py: WARNING:root:Queue stalled; refreshing interpreters.
09:04:17:objectdetection_coral_adapter.py: WARNING:root:Queue stalled; refreshing interpreters.
09:04:17:objectdetection_coral_adapter.py: WARNING:root:Pipe thread didn't join!
and again a few hours later:
11:48:52:Response rec'd from Object Detection (Coral) command 'detect' (...f1837e) [''] took 19ms
11:50:22:objectdetection_coral_adapter.py: WARNING:root:Queue stalled; refreshing interpreters.
11:51:22:objectdetection_coral_adapter.py: WARNING:root:Pipe thread didn't join!
I have a second instance that is still on 2.6.2 which has not exhibited this behaviour, so assume this to be an issue with the new code.
modified 5 days ago.
|
|
|
|
|
Thanks very much for your report. Could you please share your System Info tab from your CodeProject.AI Server dashboard?
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
sure..
Server version: 2.6.5
System: Linux
Operating System: Linux (Ubuntu 22.04)
CPUs: Intel(R) Xeon(R) CPU E3-1268L v3 @ 2.30GHz (Intel)
4 CPUs x 1 core. 1 logical processors (x64)
System RAM: 2 GiB
Platform: Linux
BuildConfig: Release
Execution Env: Native
Runtime Env: Production
Runtimes installed:
.NET runtime: 7.0.19
.NET SDK: 7.0.119
Default Python: 3.10.12
Go: Not found
NodeJS: Not found
Rust: Not found
Video adapter info:
VMware SVGA II Adapter:
Driver Version
Video Processor
System GPU info:
GPU 3D Usage 0%
GPU RAM Usage 0
Global Environment variables:
CPAI_APPROOTPATH = <root>
CPAI_PORT = 32168
and from the other system thats not exhibiting the same behaviour:
Server version: 2.6.2
System: Linux
Operating System: Linux (Ubuntu 22.04)
CPUs: Intel(R) Xeon(R) CPU E3-1268L v3 @ 2.30GHz (Intel)
4 CPUs x 1 core. 1 logical processors (x64)
System RAM: 2 GiB
Platform: Linux
BuildConfig: Release
Execution Env: Native
Runtime Env: Production
Runtimes installed:
.NET runtime: 7.0.19
.NET SDK: 7.0.119
Default Python: 3.10.12
Go: Not found
NodeJS: Not found
Rust: Not found
Video adapter info:
VMware SVGA II Adapter:
Driver Version
Video Processor
System GPU info:
GPU 3D Usage 0%
GPU RAM Usage 0
Global Environment variables:
CPAI_APPROOTPATH = <root>
CPAI_PORT = 32168
|
|
|
|
|
Thanks very much for that. We have an update to the module we are going to deploy. Stay tuned.
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
Cool project. Thank you.
I've deployed it in an LXC under Proxmox, and another LXC with the full development project. FWIW I also have it running on an RPI 5 with NVME drive and a Coral TPU deployed to docker with the dockge interface.
I've successfully run the "Optical Character Recognition" against images of road signs and of a technical manual in .pdf form. Works very well.
For grins I ran the OCR against an image of my terrible cursive handwriting. Of three paragraphs it got two thirds of the Date correct as I had written it as "month d, yyyy" The remainder of the sample was gibberish.
In my investegations I've come across, among others;
* Transkribus[^]
* Pen2text.com
Pen2text blew me away in the ease to making a simple test on that same sample of my, horribly illegible, handwriting. It missed two words that frankly looked like a leaky pen.
At any rate for either of these projects I feel I'd have to hire legal representation to understand the ownership and use of the OCR'ed sources and results.
I'd sure appreciate any tips on open source, self hosted, trainable OCR software suitable for a collection of perhaps fifty cursive multipage letters written in the same hand six or more decades ago. Once processed the text would be fed to a model to allow for chat of that subject matter.
Bonus points for pointers to open source archival platforms to organize the letters, that has an api so that I could correlate the OCRed text to the collection of images. Why reinvent that, archiving, wheel so to speak.
Thanks for listening by way or your reading.
Jeff
KF7CRU @jhalbrecht
|
|
|
|
|
Since upgrading to 2.6.5 I get AI not responding and no detections. I have to enable the service to start with Blue Iris after every reboot. Also changing from enable GPU or disabling GPU doesn't seem to change anything. I am using an Intel CPU with integrated GPU and used to be able to select enable GPU. Also the Codeproject AI status does not indicate Direct ML even after several detections. I am using Yolo.Net. Please advise? Everything I mentioned seemed to work fine with 2.6.2.
|
|
|
|
|
Thanks very much for your report. Could you please share your System Info tab from your CodeProject.AI Server dashboard?
One thing, I recommend going to Blue Iris main AI settings and unchecking auto stop/start.
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
Here it is
Server version: 2.6.5
System: Windows
Operating System: Windows (Microsoft Windows 10.0.19045)
CPUs: Intel(R) Core(TM) i7-6700T CPU @ 2.80GHz (Intel)
1 CPU x 4 cores. 8 logical processors (x64)
GPU (Primary): Intel(R) HD Graphics 530 (1,024 MiB) (Intel Corporation)
Driver: 31.0.101.2111
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:
Intel(R) HD Graphics 530:
Driver Version 31.0.101.2111
Video Processor Intel(R) HD Graphics Family
System GPU info:
GPU 3D Usage 0%
GPU RAM Usage 0
Global Environment variables:
CPAI_APPROOTPATH = <root>
CPAI_PORT = 32168
|
|
|
|
|
I unchecked Start/Stop in Blue Iris. Restarted Blue Iris PC. I have to manually start Codeproject in Codeproject Dashboard but at least I now see Direct ML after I do this. Only problem is that Custom Models are not displaying in AI Main settings. If I hit the three dots, I get the Refresh AI to display models. Looks like the custom models are not loading for some reason. How would I refresh AI? Please advise?
|
|
|
|
|
Restart the Blue Iris service and the custom model list should update
|
|
|
|
|
Looks like all these steps seem to make things work normally again. I'm assuming this is a temporary measure at the moment until further bugs are ironed out?
|
|
|
|
|