|
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
If there's no easy answer, then post a message describing your setup (paste what's in the System Info tab, please), what you are doing and what you see. 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.
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.
Here are the latest tips for those having issues installing our latest version. Be sure you're using the latest 2.2.4.
1. You see Python errors complaining about a version compatibility mismatch in urllib.
This is a known issue due to the massive, and conflicting, dependencies in some of the modules, most notably the yolo python modules. It's safe to ignore this error.
2. Object Detection fails: Unable to create YOLO detector for model
Please go to C:\Program Files\CodeProject\AI\modules\ObjectDetectionYolo\assets. You should see a set of .pt files. If not, your installer failed.
Solution Reinstall the module (see below)
3. You see any error regarding a module not starting, a package not found, something failing or shutting down.
Please go to C:\Program Files\CodeProject\AI\modules[Module in question] and look at install.log. This may point to the installation failing or something failing to be downloaded
Solution Reinstall the module (see below)
4. I'm on Windows 10 and CodeProject.AI randomly stopped working after a Windows update
The KB5025221 update has been reported as causing troubles. If you have this update installed, try rolling it back. Microsoft has a tool to show/hide problematic updates.
5. I get "ModuleNotFoundError: No module named 'PIL'"
This means the module that threw the error wasn't installed fully, most likely due to a timeout.
Solution Reinstall the module (see below)
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 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.
In Docker you will need to open a terminal into the docker container. Docker Desktop, Visual Studio Code, or using docker attach. cd to /app/modules/module-id where module-id is the id of the module you need to resinstall. Run sudo bash ../../setup.sh to force a manual reinstall of that module.
NONE OF THESE HELP?
Post a message, ensuring you include the info we mentioned at the top of this message, and we'll dive in and see what we can do
IF ALL ELSE FAILS
Here are previous version downloads that will allow you to roll back
Version 2.1.10
Prev. generation: Version 2.0.8
cheers
Chris Maunder
modified 20-Sep-23 15:25pm.
|
|
|
|
|
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
|
|
|
|
|
If you've come across an issue in building, installing, running or configuring CodeProject.AI Server we're here to help. We just ask that you provide enough info for us to dig in quickly.
Please include:
Environment:
- What version of CodeProject.AI Server are you using?
- What Operating system (include Windows version, or if docker just 'Docker')
- Are you using a GPU? If so:
- What brand / model of GPU
- What driver version
- If the card is Nvidia, what version of CUDA is installed?
Some tips:
- In the root directory of CodeProject.AI Server is a logs/ directory. Take a look in there to see if you spot any logs that might be worth including in your post (remove personal info though!)
- Have you changed any settings? If so, let us know.
- We can usually only help with questions around CodeProject.AI Server. Questions about third party apps are usually outside our scope, so please keep the focus on CodeProject.AI Server.
cheers
Chris Maunder
modified 19-Dec-22 18:14pm.
|
|
|
|
|
I installed 2.3.4 on my BI system and all alerts stopped. It took me a couple of days to realise that the alerts stopping coincided with the install of 2.3.4 , which I did on 3rd December.
Symptoms were no new video clips on UI , and no alert emails coming from BI system at all.
I alerted BI , and today (Dec 6) uninstalled 2.3.4 and re-installed 2.3.2.
Immediately, BI returned to normal working.
Therefore must be a problem with 2.3.4
I have passed this information on to Antonio at BI support
|
|
|
|
|
I have the same problem (in my case a windows 11 install, T600, CUDA 11.7 etc) and see several other related posts about 2.3.4. I'm not an expert but tried Chris Maunders utils.bat file fix that worked for Rick Marshall 2023. Didn't work for me.
I uninstalled version 2.3.4 to downgrade to eg 2.3.2, 2.2.4 or thereabouts but now don't know how to find an earlier version. Would somebody please post a link or whatever I need to do this?
I can then upgrade when the wrinkles have been ironed out for non-IT bods like me.
Thank you
|
|
|
|
|
David - I had the previous versions in zipped files in my downloads folder. Might be worth a look - look for something like "CodeProject.AI-Server-win-x64-232". If you dont have them , I have .232 and .224 versions, both of which are about 27MB files. If they are any good for you, I could upload to a shared folder for you to download . Let me know if you want me to do that. Alternatively somebody else may know a better way to get hold of them.
Chris
|
|
|
|
|
Chris, thanks for the quick reply. I had deleted every CP thing I could find but still have v2.1.8 - perhaps a bit too old. Then I was starting to find out how to use a shared folder when I decided to try editing the up-to-date download string, changing 2.3.4 to 2.2.4. Looks like it’s going to work. Will try that first.
Thanks again Chris.
|
|
|
|
|
Same here. I came from v2.2.4 and now I can't get anything to work at all. I have even done a full Windows reinstall, fresh install of Blue Iris and Code Project. Nothing works. I have been at this for many, many hours.
I have posted the contents of the log, but I am not getting a response yet. I don't know what to do and now I am stuck with a system that doesn't' work at all.
|
|
|
|
|
|
Thanks very much for the report. Could you please share your System Info tab from the CodeProject.AI Server dashboard, as well as an logs of when you are expecting alerts to occur?
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
Hi Sean
I'm sorry but as the system was completely unusable without alerts, my main objective was to get it working rather than find out why it was not working.
It is, after all, a security system, and a security system with no alerts is simply not a security system.
I worked out that there was a possible link to the latest version, as the alerts stopped on the day the new version was installed. So I uninstalled it, and reinstalled a previous version.
This resolved the issue, and I have no way now of recreating the faulty version without rendering my system useless.
I suggest you may be able to get the information you seek from Blue Iris. They must have the ability to model and test . I had email communication with Antonio in their support team. They are contactable via support@blueirissoftware.com.
Good luck in your investigation - I have had many months good experience with your excellent product up to this week, I look forward to being able to upgrade again soon.
FYI I have attached system info so you replicate my system (NB I have had a message from a W11 user with same issue - his details on this discussion)
Regards Chris
|
|
|
|
|
I'll be happy to reinstall v2.3.4, do anything within my limited capability and report back.
PS. My Internet connection is a bit slow.
9:36:54:Operating System: Windows (Microsoft Windows 11 version 10.0.22621)
19:36:54:CPUs: Intel(R) Core(TM) i5-10500 CPU @ 3.10GHz (Intel)
19:36:54: 1 CPU x 6 cores. 12 logical processors (x64)
19:36:54:GPU: NVIDIA T600 (4 GiB) (NVIDIA)
19:36:54: Driver: 516.94 CUDA: 11.7.99 (max supported: 11.7) Compute: 7.5
19:36:54:System RAM: 16 GiB
19:36:54:Target: Windows
19:36:54:BuildConfig: Release
19:36:54:Execution Env: Native
19:36:54:Runtime Env: Production
19:36:54:.NET framework: .NET 7.0.5
19:36:54:App DataDir: C:\ProgramData\CodeProject\AI
19:36:54:Video adapter info:
19:36:54: Microsoft Remote Display Adapter:
19:36:54: Driver Version 10.0.22621.2506
19:36:54: Video Processor
19:36:54: NVIDIA T600:
19:36:54: Driver Version 31.0.15.1694
19:36:54: Video Processor NVIDIA T600
19:36:54:STARTING CODEPROJECT.AI SERVER
19:36:54:RUNTIMES_PATH = C:\Program Files\CodeProject\AI\runtimes
19:36:54:PREINSTALLED_MODULES_PATH = C:\Program Files\CodeProject\AI\preinstalled-modules
19:36:54:MODULES_PATH = C:\Program Files\CodeProject\AI\modules
19:36:54:PYTHON_PATH = \bin\windows\%PYTHON_RUNTIME%\venv\scripts\Python
19:36:54:Data Dir = C:\ProgramData\CodeProject\AI
19:36:55:Server version: 2.2.4-Beta
19:36:59:
19:36:59:Module 'Object Detection (YOLOv5 6.2)' 1.6.1 (ID: ObjectDetectionYolo)
19:36:59:Module Path: C:\Program Files\CodeProject\AI\modules\ObjectDetectionYolo
19:36:59:AutoStart: True
19:36:59:Queue: objectdetection_queue
19:36:59:Platforms: all
19:36:59:GPU: Support enabled
19:36:59:Parallelism: 0
19:36:59:Accelerator:
19:36:59:Half Precis.: enable
19:36:59:Runtime: python37
19:36:59:Runtime Loc: Shared
19:36:59:FilePath: detect_adapter.py
19:36:59:Pre installed: False
19:36:59:Start pause: 1 sec
19:36:59:LogVerbosity:
19:36:59:Valid: True
19:36:59:Environment Variables
19:36:59:APPDIR = %CURRENT_MODULE_PATH%
19:36:59:CPAI_MODULE_SUPPORT_GPU = True
19:36:59:CUSTOM_MODELS_DIR = %CURRENT_MODULE_PATH%/custom-models
19:36:59:MODELS_DIR = %CURRENT_MODULE_PATH%/assets
19:36:59:MODEL_SIZE = Medium
19:36:59:USE_CUDA = True
19:36:59:YOLOv5_AUTOINSTALL = false
19:36:59:YOLOv5_VERBOSE = false
19:36:59:
19:36:59:Started Object Detection (YOLOv5 6.2) module
19:37:01:detect_adapter.py: Traceback (most recent call last):
19:37:01:detect_adapter.py: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYolo\detect_adapter.py", line 12, in
19:37:01:detect_adapter.py: from request_data import RequestData
19:37:01:detect_adapter.py: File "../../SDK/Python\request_data.py", line 7, in
19:37:01:detect_adapter.py: from PIL import Image
19:37:01:detect_adapter.py: ModuleNotFoundError: No module named 'PIL'
19:37:01:Module ObjectDetectionYolo has shutdown
19:37:01:detect_adapter.py: has exited
19:37:01:A new version 2.3.4-Beta is available
19:37:22:
19:37:22:Module 'Object Detection (YOLOv5 6.2)' 1.6.1 (ID: ObjectDetectionYolo)
19:37:22:Module Path: C:\Program Files\CodeProject\AI\modules\ObjectDetectionYolo
19:37:22:AutoStart: True
19:37:22:Queue: objectdetection_queue
19:37:22:Platforms: all
19:37:22:GPU: Support enabled
19:37:22:Parallelism: 0
19:37:22:Accelerator:
19:37:22:Half Precis.: enable
19:37:22:Runtime: python37
19:37:22:Runtime Loc: Shared
19:37:22:FilePath: detect_adapter.py
19:37:22:Pre installed: False
19:37:22:Start pause: 1 sec
19:37:22:LogVerbosity:
19:37:22:Valid: True
19:37:22:Environment Variables
19:37:22:APPDIR = %CURRENT_MODULE_PATH%
19:37:22:CPAI_MODULE_SUPPORT_GPU = True
19:37:22:CUSTOM_MODELS_DIR = %CURRENT_MODULE_PATH%/custom-models
19:37:22:MODELS_DIR = %CURRENT_MODULE_PATH%/assets
19:37:22:MODEL_SIZE = Medium
19:37:22:USE_CUDA = True
19:37:22:YOLOv5_AUTOINSTALL = false
19:37:22:YOLOv5_VERBOSE = false
19:37:22:
19:37:22:Started Object Detection (YOLOv5 6.2) module
19:37:22:detect_adapter.py: Traceback (most recent call last):
19:37:22:detect_adapter.py: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYolo\detect_adapter.py", line 12, in
19:37:22:detect_adapter.py: from request_data import RequestData
19:37:22:detect_adapter.py: File "../../SDK/Python\request_data.py", line 7, in
19:37:22:detect_adapter.py: from PIL import Image
19:37:22:detect_adapter.py: ModuleNotFoundError: No module named 'PIL'
19:37:22:Module ObjectDetectionYolo has shutdown
19:37:22:detect_adapter.py: has exited
|
|
|
|
|
I would try uninstalling and reinstalling the module from the CodeProject.AI Server dashboard. If your internet is the culprit, you could try modifying the ModuleInstallTimeout value in appsettings.json. You could also try manually installing the module. I'd also recommend stopping Blue Iris so it doesn't inadvertently stop/start the AI system halfway through an install.
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
Excellent information thank you Sean. I've found the .json file that has loads of parameters for me to dabble with using Notepad++. For example, 20 minutes is not long enough for a module install. Struggling to decide if I should revert to v2.3.4 first...
|
|
|
|
|
Running 2.3.4.
Windows 11
NVidia GeForce card with latest graphic drivers.
CUDA 11.8 is installed, although I also tried 11.7 and 12.2.
I have run the install_CUDnn.bat batch file, although it is unclear if it makes a difference in which folder I run it.
YOLOv5.6.2 (also tried YOLOv5.3.1). Note that the YOLO info tab does say that CanUseGPU is set to false, and I don't know why.
I have tried uninstalling everything (CUDA, CodeProject.AI) and reinstalling them. No matter what I do I can't get object detection working in GPU mode. CodeProject appears to recognize that the GPU and CUDA are available.
I have run object detection with GPU in the past successfully. I'm out of ideas. I assume that there is some install error going on here. Maybe something to do with the install order, or the location from which I ran install_CUDnn.bat?
Also, on a potentially (but very unlikely) issue is that System Info still shows I'm using CUDA 12.3 even though I completely uninstalled it and did a downgrade to 11.8 as suggested. I don't know where it is picking this up. Nvcc shows the correct version, I don't see the version any environment settings. I assume it is a registry entry someplace that doesn't get cleaned up when you uninstall Codeproject.ai or the CUDA toolkit. Hopefully the app isn't actually using that version anyplace.
Any suggestions would be appreciated.
----------------------------
Server version: 2.3.4-Beta
System: Windows
Operating System: Windows (Microsoft Windows 11 version 10.0.22621)
CPUs: AMD Ryzen 9 5950X 16-Core Processor (AMD)
1 CPU x 16 cores. 32 logical processors (x64)
GPU: NVIDIA GeForce GTX 1660 Ti (6 GiB) (NVIDIA)
Driver: 546.29 CUDA: 12.3 (max supported: 12.3) Compute: 7.5
System RAM: 32 GiB
Target: Windows
BuildConfig: Release
Execution Env: Native
Runtime Env: Production
.NET framework: .NET 7.0.14
Video adapter info:
NVIDIA GeForce GTX 1660 Ti:
Driver Version 31.0.15.4629
Video Processor NVIDIA GeForce GTX 1660 Ti
System GPU info:
GPU 3D Usage 4%
GPU RAM Usage 946 MiB
Global Environment variables:
CPAI_APPROOTPATH = <root>
CPAI_PORT = 32168
----------------------------
Module 'Object Detection (YOLOv5 3.1)' 1.6.1 (ID: Yolov5-3.1)
Module Path: <root>\modules\Yolov5-3.1
AutoStart: False
Queue: objectdetection_queue
Platforms: windows,linux,linux-arm64,macos
GPU Libraries: installed if available
GPU Enabled: enabled
Parallelism: 0
Accelerator:
Half Precis.: enable
Runtime: python3.7
Runtime Loc: Local
FilePath: yolo_adapter.py
Pre installed: False
Start pause: 1 sec
LogVerbosity:
Valid: True
Environment Variables
APPDIR = <root>\modules\Yolov5-3.1
DATA_DIR = C:\ProgramData\CodeProject\AI
MODE = MEDIUM
MODELS_DIR = <root>\modules\Yolov5-3.1\assets
PROFILE = desktop_gpu
TEMP_PATH = <root>\modules\Yolov5-3.1\tempstore
USE_CUDA = True
YOLOv5_VERBOSE = false
Started: 06 Dec 2023 12:13:46 AM Pacific Standard Time
LastSeen: 06 Dec 2023 2:39:36 PM Pacific Standard Time
Status: Started
Processed: 52743
Provider:
CanUseGPU: False
HardwareType: CPU
modified 9hrs 10mins ago.
|
|
|
|
|
I've been using codeproject for some time now. and it always seems to be a headache in getting it to work. so im hoping someone can shed some light on how to resolve it.
usually the .net works better as far as resources are concerned i can explain if needed. but recently i had to reinstall windows and now neither the new version or the old version will use .net object detection. so i figured to try and get 6.2 to actually use the gpu. one part of the logs says its true and other says cant use.
<pre>Server version: 2.3.4-Beta
System: Windows
Operating System: Windows (Microsoft Windows 10.0.19045)
CPUs: AMD Ryzen 7 2700X Eight-Core Processor (AMD)
1 CPU x 8 cores. 16 logical processors (x64)
GPU: NVIDIA GeForce RTX 3060 (12 GiB) (NVIDIA)
Driver: 546.29 CUDA: 12.3 (max supported: 12.3) Compute: 8.6
System RAM: 16 GiB
Target: Windows
BuildConfig: Release
Execution Env: Native
Runtime Env: Production
.NET framework: .NET 7.0.5
Video adapter info:
NVIDIA GeForce RTX 3060:
Driver Version 31.0.15.4629
Video Processor NVIDIA GeForce RTX 3060
System GPU info:
GPU 3D Usage 19%
GPU RAM Usage 2.2 GiB
Global Environment variables:
CPAI_APPROOTPATH = <root>
CPAI_PORT = 32168
00:03:48:System: Windows
00:03:48:Operating System: Windows (Microsoft Windows 10.0.19045)
00:03:48:CPUs: AMD Ryzen 7 2700X Eight-Core Processor (AMD)
00:03:48: 1 CPU x 8 cores. 16 logical processors (x64)
00:03:48:GPU: NVIDIA GeForce RTX 3060 (12 GiB) (NVIDIA)
00:03:48: Driver: 546.29 CUDA: 12.3 (max supported: 12.3) Compute: 8.6
00:03:48:System RAM: 16 GiB
00:03:48:Target: Windows
00:03:48:BuildConfig: Release
00:03:48:Execution Env: Native
00:03:48:Runtime Env: Production
00:03:48:.NET framework: .NET 7.0.5
00:03:48:App DataDir: C:\ProgramData\CodeProject\AI
00:03:48:Video adapter info:
00:03:48: NVIDIA GeForce RTX 3060:
00:03:48: Driver Version 31.0.15.4629
00:03:48: Video Processor NVIDIA GeForce RTX 3060
00:03:48:STARTING CODEPROJECT.AI SERVER
00:03:48:RUNTIMES_PATH = C:\Program Files\CodeProject\AI\runtimes
00:03:48:PREINSTALLED_MODULES_PATH = C:\Program Files\CodeProject\AI\preinstalled-modules
00:03:48:MODULES_PATH = C:\Program Files\CodeProject\AI\modules
00:03:48:PYTHON_PATH = \bin\windows\%PYTHON_DIRECTORY%\venv\Scripts\python
00:03:48:Data Dir = C:\ProgramData\CodeProject\AI
00:03:48:Server version: 2.3.4-Beta
00:03:51:
00:03:51:Module 'Object Detection (YOLOv5 6.2)' 1.7.1 (ID: ObjectDetectionYolo)
00:03:51:Module Path: C:\Program Files\CodeProject\AI\modules\ObjectDetectionYolo
00:03:51:AutoStart: True
00:03:51:Queue: objectdetection_queue
00:03:51:Platforms: all
00:03:51:GPU Libraries: installed if available
00:03:51:GPU Enabled: enabled
00:03:51:Parallelism: 0
00:03:51:Accelerator:
00:03:51:Half Precis.: enable
00:03:51:Runtime: python3.7
00:03:51:Runtime Loc: Shared
00:03:51:FilePath: detect_adapter.py
00:03:51:Pre installed: False
00:03:51:Start pause: 1 sec
00:03:51:LogVerbosity:
00:03:51:Valid: True
00:03:51:Environment Variables
00:03:51:APPDIR = %CURRENT_MODULE_PATH%
00:03:51:CPAI_MODULE_ENABLE_GPU = True
00:03:51:CUSTOM_MODELS_DIR = %CURRENT_MODULE_PATH%/custom-models
00:03:51:MODELS_DIR = %CURRENT_MODULE_PATH%/assets
00:03:51:MODEL_SIZE = Medium
00:03:51:USE_CUDA = True
00:03:51:YOLOv5_AUTOINSTALL = false
00:03:51:YOLOv5_VERBOSE = false
00:03:51:
00:03:51:Started Object Detection (YOLOv5 6.2) module
00:03:53:Server: This is the latest version
00:03:56:Object Detection (YOLOv5 6.2): Rec'd request for Object Detection (YOLOv5 6.2) command 'list-custom' (...39abee) took 2ms
00:03:56:Sending shutdown request to python/ObjectDetectionYolo
00:04:06:detect_adapter.py: Inference processing will occur on device 'CPU'
00:04:07:Module ObjectDetectionYolo has shutdown
00:04:07:detect_adapter.py: has exited
00:04:16:Unable to find module YOLOv5-3.1
00:04:29:ObjectDetectionYolo went quietly
00:04:29:
00:04:29:Module 'Object Detection (YOLOv5 6.2)' 1.7.1 (ID: ObjectDetectionYolo)
00:04:29:Module Path: C:\Program Files\CodeProject\AI\modules\ObjectDetectionYolo
00:04:29:AutoStart: True
00:04:29:Queue: objectdetection_queue
00:04:29:Platforms: all
00:04:29:GPU Libraries: installed if available
00:04:29:GPU Enabled: enabled
00:04:29:Parallelism: 0
00:04:29:Accelerator:
00:04:29:Half Precis.: enable
00:04:29:Runtime: python3.7
00:04:29:Runtime Loc: Shared
00:04:29:FilePath: detect_adapter.py
00:04:29:Pre installed: False
00:04:29:Start pause: 1 sec
00:04:29:LogVerbosity:
00:04:29:Valid: True
00:04:29:Environment Variables
00:04:29:APPDIR = %CURRENT_MODULE_PATH%
00:04:29:CPAI_MODULE_ENABLE_GPU = True
00:04:29:CUSTOM_MODELS_DIR = %CURRENT_MODULE_PATH%/custom-models
00:04:29:MODELS_DIR = %CURRENT_MODULE_PATH%/assets
00:04:29:MODEL_SIZE = Medium
00:04:29:USE_CUDA = True
00:04:29:YOLOv5_AUTOINSTALL = false
00:04:29:YOLOv5_VERBOSE = false
00:04:29:
00:04:29:Started Object Detection (YOLOv5 6.2) module
00:04:37:Object Detection (YOLOv5 6.2): Rec'd request for Object Detection (YOLOv5 6.2) command 'detect' (...8831ed) took 2760ms
00:04:37:Object Detection (YOLOv5 6.2): Rec'd request for Object Detection (YOLOv5 6.2) command 'detect' (...6e599a) took 2776ms
00:04:37:Object Detection (YOLOv5 6.2): Rec'd request for Object Detection (YOLOv5 6.2) command 'detect' (...98383f) took 3033ms
00:04:38:Object Detection (YOLOv5 6.2): Rec'd request for Object Detection (YOLOv5 6.2) command 'detect' (...fd42e6) took 3129ms
00:04:38:Object Detection (YOLOv5 6.2): Rec'd request for Object Detection (YOLOv5 6.2) command 'detect' (...c797ab) took 3186ms
00:04:38:Object Detection (YOLOv5 6.2): Rec'd request for Object Detection (YOLOv5 6.2) command 'detect' (...35b568) took 3204ms
00:04:38:Object Detection (YOLOv5 6.2): Rec'd request for Object Detection (YOLOv5 6.2) command 'detect' (...7ddd23) took 3208ms
00:04:49:Object Detection (YOLOv5 6.2): Rec'd request for Object Detection (YOLOv5 6.2) command 'detect' (...60e08e) took 788ms
00:04:49:Object Detection (YOLOv5 6.2): Rec'd request for Object Detection (YOLOv5 6.2) command 'detect' (...d57faa) took 832ms
00:04:49:Object Detection (YOLOv5 6.2): Rec'd request for Object Detection (YOLOv5 6.2) command 'detect' (...8f5dd1) took 724ms
00:04:49:Object Detection (YOLOv5 6.2): Rec'd request for Object Detection (YOLOv5 6.2) command 'detect' (...539eef) took 546ms
00:07:28:Object Detection (YOLOv5 6.2): Rec'd request for Object Detection (YOLOv5 6.2) command 'detect' (...84f6d2) took 715ms
Module 'Object Detection (YOLOv5 6.2)' 1.7.1 (ID: ObjectDetectionYolo)
Module Path: <root>\modules\ObjectDetectionYolo
AutoStart: True
Queue: objectdetection_queue
Platforms: all
GPU Libraries: installed if available
GPU Enabled: enabled
Parallelism: 0
Accelerator:
Half Precis.: enable
Runtime: python3.7
Runtime Loc: Shared
FilePath: detect_adapter.py
Pre installed: False
Start pause: 1 sec
LogVerbosity:
Valid: True
Environment Variables
APPDIR = <root>\modules\ObjectDetectionYolo
CPAI_MODULE_ENABLE_GPU = True
CUSTOM_MODELS_DIR = <root>\modules\ObjectDetectionYolo\custom-models
MODELS_DIR = <root>\modules\ObjectDetectionYolo\assets
MODEL_SIZE = Medium
USE_CUDA = True
YOLOv5_AUTOINSTALL = false
YOLOv5_VERBOSE = false
Started: 06 Dec 2023 12:06:26 AM Eastern Standard Time
LastSeen: 06 Dec 2023 12:29:30 AM Eastern Standard Time
Status: Started
Processed: 130
Provider:
CanUseGPU: False
HardwareType: CPU
Installation Log
2023-12-05 23:32:06: Installing CodeProject.AI Analysis Module
2023-12-05 23:32:06: ========================================================================
2023-12-05 23:32:06: CodeProject.AI Installer
2023-12-05 23:32:06: ========================================================================
2023-12-05 23:32:06: General CodeProject.AI setup
2023-12-05 23:32:07: Creating Directories...Done
2023-12-05 23:32:07: GPU support
2023-12-05 23:32:07: CUDA Present...No
2023-12-05 23:32:07: ROCm Present...False
2023-12-05 23:32:07: Installing module ObjectDetectionYolo 1.7.1
2023-12-05 23:32:07: Installing Python 3.7
2023-12-05 23:32:07: Python 3.7 is already installed
2023-12-05 23:32:07: Creating Virtual Environment (Shared)...Virtual Environment already present
2023-12-05 23:32:07: Confirming we have Python 3.7 in our virtual environment...present
2023-12-05 23:32:13: Downloading Standard YOLO models...Expanding...Done.
2023-12-05 23:32:13: Copying contents of models-yolo5-pt.zip to assets...done
2023-12-05 23:32:13: Cleaning up...done
2023-12-05 23:32:21: Downloading Custom YOLO models...Expanding...Done.
2023-12-05 23:32:21: Copying contents of custom-models-yolo5-pt.zip to custom-models...done
2023-12-05 23:32:21: Cleaning up...done
2023-12-05 23:32:21: Installing Python packages for ObjectDetectionYolo
2023-12-05 23:32:21: [0;Installing GPU-enabled libraries: If available
2023-12-05 23:32:22: Ensuring Python package manager (pip) is installed...Done
2023-12-05 23:32:25: Ensuring Python package manager (pip) is up to date...Done
2023-12-05 23:32:25: Python packages specified by requirements.txt
2023-12-05 23:32:26: - Installing urllib3, the HTTP client for Python...Already installed
2023-12-05 23:32:27: - Installing Pandas, a data analysis / data manipulation tool...Already installed
2023-12-05 23:32:28: - Installing CoreMLTools, for working with .mlmodel format models...Already installed
2023-12-05 23:32:29: - Installing OpenCV, the Open source Computer Vision library...Already installed
2023-12-05 23:32:30: - Installing Pillow, a Python Image Library...Already installed
2023-12-05 23:32:31: - Installing SciPy, a library for mathematics, science, and engineering...Already installed
2023-12-05 23:32:32: - Installing PyYAML, a library for reading configuration files...Already installed
2023-12-05 23:32:33: - Installing PyTorch, for Tensor computation and Deep neural networks...Already installed
2023-12-05 23:32:34: - Installing TorchVision, for Computer Vision based AI...Already installed
2023-12-05 23:34:28: - Installing Ultralytics YoloV5 package for object detection in images...(âœ"ï¸ checked) Done
2023-12-05 23:34:29: - Installing Seaborn, a data visualization library based on matplotlib...Already installed
2023-12-05 23:34:29: Installing Python packages for the CodeProject.AI Server SDK
2023-12-05 23:34:30: Ensuring Python package manager (pip) is installed...Done
2023-12-05 23:34:33: Ensuring Python package manager (pip) is up to date...Done
2023-12-05 23:34:33: Python packages specified by requirements.txt
2023-12-05 23:34:35: - Installing Pillow, a Python Image Library...Already installed
2023-12-05 23:34:36: - Installing Charset normalizer...Already installed
2023-12-05 23:34:37: - Installing aiohttp, the Async IO HTTP library...Already installed
2023-12-05 23:34:38: - Installing aiofiles, the Async IO Files library...Already installed
2023-12-05 23:34:39: - Installing py-cpuinfo to allow us to query CPU info...Already installed
2023-12-05 23:34:41: - Installing Requests, the HTTP library...Already installed
2023-12-05 23:34:41: Setup complete
Installer exited with code 0
|
|
|
|
|
I don't suppose there is a watch folder for each module to monitor and thus process?
...when API access isn't possible with codeproject.ai Server *or* with the 3rd party application.
Example:
Image is created by a 3rd party app.
Image is written to a network volume with a CodeProject.ai watched folder.
Super Resolution (or another module) up-reses the image in the monitored folder and exports it to a network volume and folder.
Repeat.
Thanks!
|
|
|
|
|
When trying to update from v2.2.4 to 2.3.4, I get this message.
After several attempts to uninstall and reinstall CodeProject, no fix.
I had to do a Windows system restore to when I had v2.2.4 and the problem went away.
Tried to update again to v2.3.4 and the issue came back. It seems there's an issue with the installation of this version that my computer doesn't like.
For now, I guess I won't be able to install the newest version. Any help is greatly appreciated.
Thank you.
|
|
|
|
|
I use CPAI for object detection with Blue Iris. A few weeks ago I replaced a poorly performing GeForce 1030 card with a Coral TPU and the results were quite good. On any day after a fresh system restart I get very quick alert notifications pushed to my phone as I walk through the field of view of the camera on my back porch, which is a test I perform every morning. But then, over time, usually a period of 2-3 days, object detection degrades until eventually, CPAI reports no objects found when I've clearly just walked in front of a camera 10 feet away. I've checked the CPAI logs and they report no objects found. However, with a full system restart, object detection is back to peak performance. What should I look for? Thanks in advance for your help.
|
|
|
|
|
Thanks very much for the report. Could you please share your System Info tab from the CodeProject.AI Server dashboard? Also, in the logs, is there simply just no data at all, or is there some kind of message? If yes, please share those as well.
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
I am using a GeForce 760 and would like to know which YOLO version to use.
Also, how do I know if it's working on doing what it's supposed to compared to when not using CUDA?
What is the benefit of using CUDA GPU vs not?
Thanks.
|
|
|
|
|
Use the 3.1 version - it offers better support for your card.
fotingo wrote: how do I know if it's working on doing what it's supposed to compared to when not using CUDA?
You'll see the "GPU" label in the status on the dashboard for that module.
fotingo wrote: What is the benefit of using CUDA GPU vs not?
Speed, and taking the load off your CPU.
cheers
Chris Maunder
|
|
|
|
|
|
That's a first!
cheers
Chris Maunder
|
|
|
|
|
EDIT.. Never mind.. I see the status...
But...
Also, after installing YOLO v5.31 I am not getting any alerts at all.
I am getting this...
12:33:39:Object Detection (YOLOv5 3.1): Unable to load model at C:\Program Files\CodeProject\AI\modules\YOLOv5-3.1\assets\yolov5m.pt (CUDA error: no kernel image is available for execution on the device)
12:33:39:Object Detection (YOLOv5 3.1): Unable to create YOLO detector for model yolov5m
12:33:39:Object Detection (YOLOv5 3.1): Rec'd request for Object Detection (YOLOv5 3.1) command 'detect' (...6d996b) took 104ms
12:34:43:Object Detection (YOLOv5 3.1): Unable to load model at C:\Program Files\CodeProject\AI\modules\YOLOv5-3.1\assets\yolov5m.pt (CUDA error: no kernel image is available for execution on the device)
12:34:43:Object Detection (YOLOv5 3.1): Unable to create YOLO detector for model yolov5m
12:34:43:Object Detection (YOLOv5 3.1): Rec'd request for Object Detection (YOLOv5 3.1) command 'detect' (...16ce28) took 85ms
12:35:14:Object Detection (YOLOv5 3.1): Unable to load model at C:\Program Files\CodeProject\AI\modules\YOLOv5-3.1\assets\yolov5m.pt (CUDA error: no kernel image is available for execution on the device)
12:35:14:Object Detection (YOLOv5 3.1): Unable to create YOLO detector for model yolov5m
12:35:14:Object Detection (YOLOv5 3.1): Rec'd request for Object Detection (YOLOv5 3.1) command 'detect' (...2846d8) took 122ms
12:35:14:Object Detection (YOLOv5 3.1): Unable to load model at C:\Program Files\CodeProject\AI\modules\YOLOv5-3.1\assets\yolov5m.pt (CUDA error: no kernel image is available for execution on the device)
12:35:14:Object Detection (YOLOv5 3.1): Unable to create YOLO detector for model yolov5m
12:35:14:Object Detection (YOLOv5 3.1): Rec'd request for Object Detection (YOLOv5 3.1) command 'detect' (...fa7fc1) took 155ms
12:35:15:Object Detection (YOLOv5 3.1): Unable to load model at C:\Program Files\CodeProject\AI\modules\YOLOv5-3.1\assets\yolov5m.pt (CUDA error: no kernel image is available for execution on the device)
12:35:15:Object Detection (YOLOv5 3.1): Unable to create YOLO detector for model yolov5m
12:35:15:Object Detection (YOLOv5 3.1): Rec'd request for Object Detection (YOLOv5 3.1) command 'detect' (...e26ee5) took 103ms
12:35:16:Object Detection (YOLOv5 3.1): Unable to load model at C:\Program Files\CodeProject\AI\modules\YOLOv5-3.1\assets\yolov5m.pt (CUDA error: no kernel image is available for execution on the device)
12:35:16:Object Detection (YOLOv5 3.1): Rec'd request for Object Detection (YOLOv5 3.1) command 'detect' (...3abbfc) took 102ms
12:35:16:Object Detection (YOLOv5 3.1): Unable to create YOLO detector for model yolov5m
12:35:20:Object Detection (YOLOv5 3.1): Unable to load model at C:\Program Files\CodeProject\AI\modules\YOLOv5-3.1\assets\yolov5m.pt (CUDA error: no kernel image is available for execution on the device)
12:35:20:Object Detection (YOLOv5 3.1): Unable to create YOLO detector for model yolov5m
12:35:20:Object Detection (YOLOv5 3.1): Rec'd request for Object Detection (YOLOv5 3.1) command 'detect' (...9655e7) took 105ms
12:36:42:Object Detection (YOLOv5 3.1): Unable to load model at C:\Program Files\CodeProject\AI\modules\YOLOv5-3.1\assets\yolov5m.pt (CUDA error: no kernel image is available for execution on the device)
12:36:42:Object Detection (YOLOv5 3.1): Unable to create YOLO detector for model yolov5m
|
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
