|
|
I am choosing the EfficientDet-Lite model and Medium size and although logs say it is using that it, I can tell from testing in the Explorer with a test image that it is not really using that model. It is using the MobileNetSSD. This did work in 2.5.1 testing the same way. I then upgraded to 2.6.2 which broke it. 2.6.5 still broken. Unfortunately when I tried to go back to 2.5.1 I get an error 404 on the installer. More steps/details below after the System Info and logs.
Here is my System Info
Server version: 2.6.5
System: Windows
Operating System: Windows (Microsoft Windows 10.0.19045)
CPUs: Intel(R) Core(TM) i5-8500 CPU @ 3.00GHz (Intel)
1 CPU x 6 cores. 6 logical processors (x64)
GPU (Primary): Intel(R) UHD Graphics 630 (1,024 MiB) (Intel Corporation)
Driver: 30.0.100.9864
System RAM: 16 GiB
Platform: Windows
BuildConfig: Release
Execution Env: Native
Runtime Env: Production
Runtimes installed:
.NET runtime: 7.0.10
.NET SDK: Not found
Default Python: Not found
Go: Not found
NodeJS: Not found
Rust: Not found
Video adapter info:
Intel(R) UHD Graphics 630:
Driver Version 30.0.100.9864
Video Processor Intel(R) UHD Graphics Family
System GPU info:
GPU 3D Usage 4%
GPU RAM Usage 0
Global Environment variables:
CPAI_APPROOTPATH = <root>
CPAI_PORT = 32168
I can give a copy of the install log as well but it's long.
Here is a screenshot of the log while testing:
Notice the times for "Detect Objects" which is using the configured EfficientDet-Lite model and size Medium is not matching the "Custom Detect" when configured to use the same model. When I switch the custom model to MobileNetSSD the times match again. Also, the confidence percentages match for the 1st and 3rd run (MobileNetSSD) as well as the same tags as well as labeled my truck a car. The 2nd run correctly labeled my truck a truck and had different confidence percentages for the other items.
The screenshot missed the configuration so here is the log:
2024-08-03 15:51:04: Attempting to start ObjectDetectionCoral with C:\Program Files\CodeProject\AI\modules\ObjectDetectionCoral\bin\windows\python39\venv\Scripts\python "C:\Program Files\CodeProject\AI\modules\ObjectDetectionCoral\objectdetection_coral_adapter.py"
2024-08-03 15:51:04: Starting C:\Program Files...ws\python39\venv\Scripts\python "C:\Program Files...ectdetection_coral_adapter.py"
2024-08-03 15:51:04:
2024-08-03 15:51:04: ** Module 'Object Detection (Coral)' 2.3.4 (ID: ObjectDetectionCoral)
2024-08-03 15:51:04: ** Valid: True
2024-08-03 15:51:04: ** Module Path: <root>\modules\ObjectDetectionCoral
2024-08-03 15:51:04: ** Module Location: Internal
2024-08-03 15:51:04: ** AutoStart: True
2024-08-03 15:51:04: ** Queue: objectdetection_queue
2024-08-03 15:51:04: ** Runtime: python3.9
2024-08-03 15:51:04: ** Runtime Location: Local
2024-08-03 15:51:04: ** FilePath: objectdetection_coral_adapter.py
2024-08-03 15:51:04: ** Start pause: 1 sec
2024-08-03 15:51:04: ** Parallelism: 16
2024-08-03 15:51:04: ** LogVerbosity:
2024-08-03 15:51:04: ** Platforms: all
2024-08-03 15:51:04: ** GPU Libraries: installed if available
2024-08-03 15:51:04: ** GPU: use if supported
2024-08-03 15:51:04: ** Accelerator:
2024-08-03 15:51:04: ** Half Precision: enable
2024-08-03 15:51:04: ** Environment Variables
2024-08-03 15:51:04: ** CPAI_CORAL_MODEL_NAME = EfficientDet-Lite
2024-08-03 15:51:04: ** CPAI_CORAL_MULTI_TPU = False
2024-08-03 15:51:04: ** MODELS_DIR = <root>\modules\ObjectDetectionCoral\assets
2024-08-03 15:51:04: ** MODEL_SIZE = medium
2024-08-03 15:51:04:
2024-08-03 15:51:04: Started Object Detection (Coral) module
2024-08-03 15:51:06: objectdetection_coral_adapter.py: Unable to load OpenCV or numpy modules. Only using PIL.
2024-08-03 15:51:06: objectdetection_coral_adapter.py: MODULE_PATH: C:\Program Files\CodeProject\AI\modules\ObjectDetectionCoral
2024-08-03 15:51:06: objectdetection_coral_adapter.py: MODELS_DIR: C:\Program Files\CodeProject\AI\modules\ObjectDetectionCoral\assets
2024-08-03 15:51:06: objectdetection_coral_adapter.py: CPAI_CORAL_MODEL_NAME: efficientdet-lite
2024-08-03 15:51:06: objectdetection_coral_adapter.py: MODEL_SIZE: medium
2024-08-03 15:51:06: objectdetection_coral_adapter.py: CPU_MODEL_NAME: efficientdet_lite3_512_ptq.tflite
2024-08-03 15:51:06: objectdetection_coral_adapter.py: TPU_MODEL_NAME: efficientdet_lite3_512_ptq_edgetpu.tflite
2024-08-03 15:51:06: objectdetection_coral_adapter.py: Running init for Object Detection (Coral)
2024-08-03 15:51:06: objectdetection_coral_adapter.py: TPU detected
2024-08-03 15:51:06: objectdetection_coral_adapter.py: Input details: {'name': 'serving_default_images:0', 'index': 0, 'shape': array([ 1, 512, 512, 3]), 'shape_signature': array([ 1, 512, 512, 3]), 'dtype': <class 'numpy.uint8'>, 'quantization': (0.0078125, 127), 'quantization_parameters': {'scales': array([0.0078125], dtype=float32), 'zero_points': array([127]), 'quantized_dimension': 0}, 'sparsity_parameters': {}}
2024-08-03 15:51:06: objectdetection_coral_adapter.py: Output details: {'name': 'StatefulPartitionedCall:31', 'index': 23, 'shape': array([ 1, 25, 4]), 'shape_signature': array([ 1, 25, 4]), 'dtype': <class 'numpy.float32'>, 'quantization': (0.0, 0), 'quantization_parameters': {'scales': array([], dtype=float32), 'zero_points': array([], dtype=int32), 'quantized_dimension': 0}, 'sparsity_parameters': {}}
2024-08-03 15:51:06: objectdetection_coral_adapter.py: Using Edge TPU
2024-08-03 15:51:33: Request 'detect' dequeued from 'objectdetection_queue' (#reqid f296f35c-ebab-46ed-9430-eec8bb363c65)
2024-08-03 15:51:33: Client request 'detect' in queue 'objectdetection_queue' (#reqid f296f35c-ebab-46ed-9430-eec8bb363c65)
2024-08-03 15:51:33: Object Detection (Coral): Retrieved objectdetection_queue command 'detect' in Object Detection (Coral)
2024-08-03 15:51:33: Response rec'd from Object Detection (Coral) command 'detect' (#reqid f296f35c-ebab-46ed-9430-eec8bb363c65) ['Found dog, person, car...'] took 123ms
2024-08-03 15:51:45: Client request 'detect' in queue 'objectdetection_queue' (#reqid ebeb1e63-622f-4348-9f3a-c6c44bbf1af9)
2024-08-03 15:51:45: Request 'detect' dequeued from 'objectdetection_queue' (#reqid ebeb1e63-622f-4348-9f3a-c6c44bbf1af9)
2024-08-03 15:51:45: Object Detection (Coral): Retrieved objectdetection_queue command 'detect' in Object Detection (Coral)
2024-08-03 15:51:45: Response rec'd from Object Detection (Coral) command 'detect' (#reqid ebeb1e63-622f-4348-9f3a-c6c44bbf1af9) ['Found dog, person, car...'] took 19ms
2024-08-03 15:51:59: Request 'detect' dequeued from 'objectdetection_queue' (#reqid 0ad44b34-4810-4128-bb2a-8c540d181550)
2024-08-03 15:51:59: Client request 'detect' in queue 'objectdetection_queue' (#reqid 0ad44b34-4810-4128-bb2a-8c540d181550)
2024-08-03 15:51:59: Object Detection (Coral): Retrieved objectdetection_queue command 'detect' in Object Detection (Coral)
2024-08-03 15:51:59: Response rec'd from Object Detection (Coral) command 'detect' (#reqid 0ad44b34-4810-4128-bb2a-8c540d181550) ['Found dog, person, car...'] took 19ms
2024-08-03 15:52:32: Request 'custom' dequeued from 'objectdetection_queue' (#reqid e27c4551-5abf-42a9-8878-dadb70d232b0)
2024-08-03 15:52:32: Client request 'custom' in queue 'objectdetection_queue' (#reqid e27c4551-5abf-42a9-8878-dadb70d232b0)
2024-08-03 15:52:32: Object Detection (Coral): Retrieved objectdetection_queue command 'custom' in Object Detection (Coral)
2024-08-03 15:52:32: Response rec'd from Object Detection (Coral) command 'custom' (#reqid e27c4551-5abf-42a9-8878-dadb70d232b0) ['Found car, dog, person...'] took 196ms
2024-08-03 15:52:43: Client request 'custom' in queue 'objectdetection_queue' (#reqid 315ac321-a068-473e-a5b5-03f287acb91b)
2024-08-03 15:52:43: Request 'custom' dequeued from 'objectdetection_queue' (#reqid 315ac321-a068-473e-a5b5-03f287acb91b)
2024-08-03 15:52:44: Object Detection (Coral): Retrieved objectdetection_queue command 'custom' in Object Detection (Coral)
2024-08-03 15:52:44: Response rec'd from Object Detection (Coral) command 'custom' (#reqid 315ac321-a068-473e-a5b5-03f287acb91b) ['Found car, dog, person...'] took 101ms
2024-08-03 15:52:51: Request 'custom' dequeued from 'objectdetection_queue' (#reqid 0f71a391-1117-4d44-9c4f-0a86c713891b)
2024-08-03 15:52:51: Client request 'custom' in queue 'objectdetection_queue' (#reqid 0f71a391-1117-4d44-9c4f-0a86c713891b)
2024-08-03 15:52:51: Object Detection (Coral): Retrieved objectdetection_queue command 'custom' in Object Detection (Coral)
2024-08-03 15:52:52: Response rec'd from Object Detection (Coral) command 'custom' (#reqid 0f71a391-1117-4d44-9c4f-0a86c713891b) ['Found car, dog, person...'] took 100ms
2024-08-03 15:54:35: Request 'custom' dequeued from 'objectdetection_queue' (#reqid 1f45e11a-2806-437f-ac20-684ee534d4a9)
2024-08-03 15:54:35: Client request 'custom' in queue 'objectdetection_queue' (#reqid 1f45e11a-2806-437f-ac20-684ee534d4a9)
2024-08-03 15:54:35: Object Detection (Coral): Retrieved objectdetection_queue command 'custom' in Object Detection (Coral)
2024-08-03 15:54:35: Response rec'd from Object Detection (Coral) command 'custom' (#reqid 1f45e11a-2806-437f-ac20-684ee534d4a9) ['Found dog, person, car...'] took 104ms
2024-08-03 15:54:41: Request 'custom' dequeued from 'objectdetection_queue' (#reqid dec15ef6-aa05-4d82-8e48-818ad5115334)
2024-08-03 15:54:41: Client request 'custom' in queue 'objectdetection_queue' (#reqid dec15ef6-aa05-4d82-8e48-818ad5115334)
2024-08-03 15:54:41: Object Detection (Coral): Retrieved objectdetection_queue command 'custom' in Object Detection (Coral)
2024-08-03 15:54:41: Response rec'd from Object Detection (Coral) command 'custom' (#reqid dec15ef6-aa05-4d82-8e48-818ad5115334) ['Found dog, person, car...'] took 18ms
2024-08-03 15:54:42: Request 'custom' dequeued from 'objectdetection_queue' (#reqid 0f6bf566-6218-48ad-9d94-0ed8ebc8c2bd)
2024-08-03 15:54:42: Client request 'custom' in queue 'objectdetection_queue' (#reqid 0f6bf566-6218-48ad-9d94-0ed8ebc8c2bd)
2024-08-03 15:54:42: Object Detection (Coral): Retrieved objectdetection_queue command 'custom' in Object Detection (Coral)
2024-08-03 15:54:42: Response rec'd from Object Detection (Coral) command 'custom' (#reqid 0f6bf566-6218-48ad-9d94-0ed8ebc8c2bd) ['Found dog, person, car...'] took 17ms
The reason I want to use EfficientDet-Lite (medium) is it is a lot more accurate than MobileNetSSD. I spent hours testing them earlier in the year get the best accuracy for my situation.
For example, with the MobileNetSSD every time a car drives by it tags it as a person. So if I'm searching for people I'm getting every car that drives by (which is a 100 times more than people walking by). A few more examples is it tags all vehicles as cars so if I'm searching for Bus or Truck I'm not finding them. It also misses my dog which is close to the camera and perfectly positioned (sideways) for identifying. 2.5.1 was the last version that correctly used the selected model (Efficient-Lite) versus the default "MobileNetSSD".
I looked as some of the dat files from Blue Iris to see what it was thinking was a person and ror some reason the glares on the windows are what is boxed as the person. Like I said, I spent a LOT of time testing/researching it.
I tried reverting to 2.5.1 but I get 404 errors on the installer now.
I also retried uninstall and reinstalling many times. Didn't matter.
One other issue I have now is it keeps reverting to CPU.
Also, if the sytem reboots the Coral Module is not auto starting. It is the only module I am using at the moment.
modified 5-Aug-24 10:58am.
|
|
|
|
|
Using Coral latest on CPAI latest. The Coral stops identifying images after about a day, every single time. It starts finding nothing ("['']" instead of e.g. "['car', 'person']"). Blue Iris reports "AI: No bitmap" for every alert.
Restarting the module only switches it to CPU mode instead of using the Coral (which should never happen). Restarting the Docker container is the only thing that works.
I've been reporting this problem for 6+ months now.
System info:
Server version: 2.6.5
System: Docker (3c9638416897)
Operating System: Linux (Ubuntu 22.04)
CPUs: Intel(R) Core(TM) i7-7700K CPU @ 4.20GHz (Intel)
1 CPU x 4 cores. 8 logical processors (x64)
System RAM: 15 GiB
Platform: Linux
BuildConfig: Release
Execution Env: Docker
Runtime Env: Production
Runtimes installed:
.NET runtime: 7.0.19
.NET SDK: Not found
Default Python: 3.10.12
Go: Not found
NodeJS: Not found
Rust: Not found
Video adapter info:
System GPU info:
GPU 3D Usage 0%
GPU RAM Usage 0
Global Environment variables:
CPAI_APPROOTPATH = <root>
CPAI_PORT = 32168
|
|
|
|
|
Where can I get and download CodeProject version 2.0.8 ?
I tried installing some of the newer versions but did not install properly on my windows 7 64 bit machine with Blue Iris 5. I have heard that version 2.0.8 works great with win 7
|
|
|
|
|
I am running 2.6.5 on Win 7. The issues are not with the Server software. Current video drivers and Python are the hurdles you must overcome. Unless you are proficient in diagnosing the unsupported points of failure and have patience with testing it will fail. Python 3.9 and above do not support Win 7, unless, you find all the missing api dll's and put them in the proper places. It can be done. I am running 7 modules in 2.6.5 on Win 7.
|
|
|
|
|
Ok, I understand, but if I could get a hold of an older version like 2.08, wouldn't this work better, at least a better intro to code project on a Win 7 setup? Is it possible to find this version somewhere?
|
|
|
|
|
Hello again;
Thanks for the tip. I was wondering if you could list the files that I have to install/change to get CodeProject 2.6.5 working in Win 7? If its not too much trouble.
|
|
|
|
|
لم أستطيع كتابة هذا السؤال برمجياً
I could not write this question programmatically.
|
|
|
|
|
While we are more than willing to help those that are stuck, that doesn't mean that we are here to do it all for you! We can't do all the work, you are either getting paid for this, or it's part of your grades and it wouldn't be at all fair for us to do it all for you.
So we need you to do the work, and we will help you when you get stuck. That doesn't mean we will give you a step by step solution you can hand in!
Start by explaining where you are at the moment, and what the next step in the process is. Then tell us what you have tried to get that next step working, and what happened when you did.
If you are having problems getting started at all, then this may help: How to Write Code to Solve a Problem, A Beginner's Guide[^]
في حين أننا على استعداد تام لمساعدة أولئك الذين يواجهون صعوبات، فإن هذا لا يعني أننا هنا للقيام بكل شيء من أجلك! لا يمكننا القيام بكل العمل، إما أنك تحصل على أجر مقابل ذلك، أو أنه جزء من درجاتك ولن يكون من العدل على الإطلاق أن نقوم بكل ذلك من أجلك.
لذا، نحتاج منك القيام بالعمل، وسنساعدك عندما تواجه صعوبات. هذا لا يعني أننا سنقدم لك حلاً خطوة بخطوة يمكنك تسليمه!
ابدأ بشرح موقفك في الوقت الحالي، وما هي الخطوة التالية في العملية. ثم أخبرنا بما حاولت القيام به لإنجاح الخطوة التالية، وما حدث عندما فعلت ذلك.
إذا كنت تواجه مشكلات في البدء على الإطلاق، فقد يساعدك هذا: كيفية كتابة التعليمات البرمجية لحل مشكلة، دليل المبتدئين[^]
"I have no idea what I did, but I'm taking full credit for it." - ThisOldTony
"Common sense is so rare these days, it should be classified as a super power" - Random T-shirt
AntiTwitter: @DalekDave is now a follower!
|
|
|
|
|
Overall, this is an amazing system to say the least. These are some camera captures I thought you might be interested in. This is using 2.6.5 and Yolo5 6.2 (Yolo8 doesn't seem to do animals yet).
Microsoft OneDrive[^]
My System Info:
Quote: Server version: 2.6.5
System: Windows
Operating System: Windows (Microsoft Windows 11 version 10.0.22631)
CPUs: 12th Gen Intel(R) Core(TM) i7-12700H (Intel)
1 CPU x 14 cores. 20 logical processors (x64)
GPU (Primary): NVIDIA GeForce RTX 3060 Laptop GPU (6 GiB) (NVIDIA)
Driver: 552.12, CUDA: 12.4 (up to: 12.4), Compute: 8.6, cuDNN:
System RAM: 64 GiB
Platform: Windows
BuildConfig: Release
Execution Env: Native
Runtime Env: Production
Runtimes installed:
.NET runtime: 7.0.11
.NET SDK: 7.0.401
Default Python: Not found
Go: Not found
NodeJS: Not found
Rust: Not found
Video adapter info:
NVIDIA GeForce RTX 3060 Laptop GPU:
Driver Version 31.0.15.5212
Video Processor NVIDIA GeForce RTX 3060 Laptop GPU
Intel(R) Iris(R) Xe Graphics:
Driver Version 31.0.101.5186
Video Processor Intel(R) Iris(R) Xe Graphics Family
System GPU info:
GPU 3D Usage 20%
GPU RAM Usage 2.2 GiB
Global Environment variables:
CPAI_APPROOTPATH = <root>
CPAI_PORT = 32168
|
|
|
|
|
Hi there, I have tried several times to install 2.6.5 using the windows installer - win 11 pro 64 bit PC no GPU (each time using the uninstaller, deleting the program file and program data directories, and restarting the machine to get a clean install). Each attempt gets completed but various errors are thrown. Previous versions of CodeProject.AI installed fine so I'm not sure what's changed - the server has had a win10 to win 11 upgrade is about all. I'm using it with latest BlueIris SW. Have checked Winget seems to be available in powershell and checked no throttling entries in the registry and set UseSystemMaximum in the registry so BITS isn't supposed to restricted for downloads.
I get winget errors, BITS errors and the downloading of the models has issues so it seems to step over that and they don't get downloaded. I've manually installed .Net v8 but the installer code seems to do a check and only picks up ver 7 directory and seems to ignores the v8 directory and then tries to use winget to install it??.
I've tried various suggests in the forums for individual issues but with little progress. I have the various logs and have attached the System info Tab and server logs - hopefully these can yield some potential fixes.
------------------system Info----
Server version: 2.6.5
System: Windows
Operating System: Windows (Microsoft Windows 11 version 10.0.22631)
CPUs: 12th Gen Intel(R) Core(TM) i7-12700 (Intel)
1 CPU x 12 cores. 20 logical processors (x64)
GPU (Primary): Intel(R) UHD Graphics 770 (1,024 MiB) (Intel Corporation)
Driver: 31.0.101.4577
System RAM: 32 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) UHD Graphics 770:
Driver Version 31.0.101.4577
Video Processor Intel(R) UHD Graphics Family
System GPU info:
GPU 3D Usage 9%
GPU RAM Usage 0
Global Environment variables:
CPAI_APPROOTPATH = <root>
CPAI_PORT = 32168
-----------------------------
server logs
16:52:49:System: Windows
16:52:49:Operating System: Windows (Microsoft Windows 11 version 10.0.22631)
16:52:49:CPUs: 12th Gen Intel(R) Core(TM) i7-12700 (Intel)
16:52:49: 1 CPU x 12 cores. 20 logical processors (x64)
16:52:49:GPU (Primary): Intel(R) UHD Graphics 770 (1,024 MiB) (Intel Corporation)
16:52:49: Driver: 31.0.101.4577
16:52:49:System RAM: 32 GiB
16:52:49:Platform: Windows
16:52:49:BuildConfig: Release
16:52:49:Execution Env: Native
16:52:49:Runtime Env: Production
16:52:49:Runtimes installed:
16:52:49: .NET runtime: 7.0.20
16:52:49: .NET SDK: Not found
16:52:49: Default Python: Not found
16:52:49: Go: Not found
16:52:49: NodeJS: Not found
16:52:49: Rust: Not found
16:52:49:App DataDir: C:\ProgramData\CodeProject\AI
16:52:49:Video adapter info:
16:52:49: Intel(R) UHD Graphics 770:
16:52:49: Driver Version 31.0.101.4577
16:52:49: Video Processor Intel(R) UHD Graphics Family
16:52:49:STARTING CODEPROJECT.AI SERVER
16:52:49:RUNTIMES_PATH = C:\Program Files\CodeProject\AI\runtimes
16:52:49:PREINSTALLED_MODULES_PATH = C:\Program Files\CodeProject\AI\preinstalled-modules
16:52:49:DEMO_MODULES_PATH = C:\Program Files\CodeProject\AI\src\demos\modules
16:52:49:EXTERNAL_MODULES_PATH =
16:52:49:MODULES_PATH = C:\Program Files\CodeProject\AI\modules
16:52:49:PYTHON_PATH = \bin\windows\%PYTHON_NAME%\venv\Scripts\python
16:52:49:Data Dir = C:\ProgramData\CodeProject\AI
16:52:49:Server version: 2.6.5
16:52:52:Setting up initial modules. Please be patient...
16:52:52:Installing initial module ObjectDetectionYOLOv5Net.
16:52:52:Preparing to install module 'ObjectDetectionYOLOv5Net'
16:52:54:Downloading module 'ObjectDetectionYOLOv5Net'
16:52:55:Installing module 'ObjectDetectionYOLOv5Net'
16:52:55:Server: This is the latest version
16:52:55:ObjectDetectionYOLOv5Net: Installing CodeProject.AI Analysis Module
16:52:56:ObjectDetectionYOLOv5Net: ======================================================================
16:52:56:ObjectDetectionYOLOv5Net: CodeProject.AI Installer
16:52:56:ObjectDetectionYOLOv5Net: ======================================================================
16:52:56:ObjectDetectionYOLOv5Net: 870.6Gb of 953Gb available on
16:52:56:ObjectDetectionYOLOv5Net: General CodeProject.AI setup
16:52:56:ObjectDetectionYOLOv5Net: Creating Directories...done
16:52:56:ObjectDetectionYOLOv5Net: GPU support
16:52:56:ObjectDetectionYOLOv5Net: CUDA Present...No
16:52:56:ObjectDetectionYOLOv5Net: ROCm Present...No
16:52:56:ObjectDetectionYOLOv5Net: Checking for .NET 7.0...Checking SDKs...Upgrading: .NET is 0
16:52:56:ObjectDetectionYOLOv5Net: Current version is 0. Installing newer version.
16:52:56:ObjectDetectionYOLOv5Net: 'winget' is not recognized as an internal or external command,
16:52:56:ObjectDetectionYOLOv5Net: operable program or batch file.
16:52:58:ObjectDetectionYOLOv5Net: Reading ObjectDetectionYOLOv5Net settings.......done
16:52:58:ObjectDetectionYOLOv5Net: Installing module Object Detection (YOLOv5 .NET) 1.10.2
16:55:57:ObjectDetectionYOLOv5Net: Downloading ObjectDetectionYOLOv5Net-DirectML-1.10.2.zip...Expanding...done.
16:55:57:ObjectDetectionYOLOv5Net: Copying contents of ObjectDetectionYOLOv5Net-DirectML-1.10.2.zip to bin...done
17:05:40:ObjectDetectionYOLOv5Net: Downloading YOLO ONNX models...Expanding...done.
17:05:40:ObjectDetectionYOLOv5Net: Copying contents of yolonet-models.zip to assets...done
17:10:31:ObjectDetectionYOLOv5Net: Downloading Custom YOLO ONNX models...Expanding...done.
17:10:31:ObjectDetectionYOLOv5Net: Copying contents of yolonet-custom-models.zip to custom-models...done
17:10:31:ObjectDetectionYOLOv5Net: Scanning modulesettings for downloadable models...No models specified
17:10:33:ObjectDetectionYOLOv5Net: Self test: Self-test passed
17:10:33:ObjectDetectionYOLOv5Net: Module setup time 00:17:36.63
17:10:33:ObjectDetectionYOLOv5Net: Setup complete
17:10:33:ObjectDetectionYOLOv5Net: Total setup time 00:17:37.20
17:10:33:Module ObjectDetectionYOLOv5Net installed successfully.
17:10:33:Module ObjectDetectionYOLOv5Net not configured to AutoStart.
17:10:33:Installer exited with code 0
17:10:33:Installing initial module ObjectDetectionYOLOv5-6.2.
17:10:33:Preparing to install module 'ObjectDetectionYOLOv5-6.2'
17:10:33:Downloading module 'ObjectDetectionYOLOv5-6.2'
17:10:35:Installing module 'ObjectDetectionYOLOv5-6.2'
17:10:35:ObjectDetectionYOLOv5-6.2: Installing CodeProject.AI Analysis Module
17:10:35:ObjectDetectionYOLOv5-6.2: ======================================================================
17:10:35:ObjectDetectionYOLOv5-6.2: CodeProject.AI Installer
17:10:35:ObjectDetectionYOLOv5-6.2: ======================================================================
17:10:35:ObjectDetectionYOLOv5-6.2: 869.6Gb of 953Gb available on
17:10:35:ObjectDetectionYOLOv5-6.2: General CodeProject.AI setup
17:10:35:ObjectDetectionYOLOv5-6.2: Creating Directories...done
17:10:35:ObjectDetectionYOLOv5-6.2: GPU support
17:10:35:ObjectDetectionYOLOv5-6.2: CUDA Present...No
17:10:35:ObjectDetectionYOLOv5-6.2: ROCm Present...No
17:10:35:ObjectDetectionYOLOv5-6.2: Checking for .NET 7.0...Checking SDKs...Upgrading: .NET is 0
17:10:35:ObjectDetectionYOLOv5-6.2: Current version is 0. Installing newer version.
17:10:35:ObjectDetectionYOLOv5-6.2: 'winget' is not recognized as an internal or external command,
17:10:35:ObjectDetectionYOLOv5-6.2: operable program or batch file.
17:10:37:ObjectDetectionYOLOv5-6.2: Reading ObjectDetectionYOLOv5-6.2 settings.......done
17:10:37:ObjectDetectionYOLOv5-6.2: Installing module Object Detection (YOLOv5 6.2) 1.9.2
17:10:37:ObjectDetectionYOLOv5-6.2: Installing Python 3.7
17:11:12:ObjectDetectionYOLOv5-6.2: Downloading Python 3.7 interpreter...Expanding...done.
17:11:17:ObjectDetectionYOLOv5-6.2: Creating Virtual Environment (Shared)...done
17:11:17:ObjectDetectionYOLOv5-6.2: Confirming we have Python 3.7 in our virtual environment...present
17:17:38:ObjectDetectionYOLOv5-6.2: Downloading Standard YOLO models...Expanding...done.
17:17:38:ObjectDetectionYOLOv5-6.2: Copying contents of models-yolo5-pt.zip to assets...done
17:45:13:ObjectDetectionYOLOv5-6.2: Start-BitsTransfer : There are currently no active network connections. Background Intelligent Transfer Service (BITS)
17:45:13:ObjectDetectionYOLOv5-6.2: will try again when an adapter is connected.
17:45:13:ObjectDetectionYOLOv5-6.2: At line:1 char:1
17:45:13:ObjectDetectionYOLOv5-6.2: + Start-BitsTransfer -Source 'https://codeproject-ai.s3.ca-central-1.am ...
17:45:13:ObjectDetectionYOLOv5-6.2: + ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
17:45:13:ObjectDetectionYOLOv5-6.2: + CategoryInfo : InvalidOperation: (:) [Start-BitsTransfer], Exception
17:45:13:ObjectDetectionYOLOv5-6.2: + FullyQualifiedErrorId : StartBitsTransferCOMException,Microsoft.BackgroundIntelligentTransfer.Management.NewBits
17:45:13:ObjectDetectionYOLOv5-6.2: TransferCommand
17:45:14:ObjectDetectionYOLOv5-6.2: Start-BitsTransfer : There are currently no active network connections. Background Intelligent Transfer Service (BITS)
17:45:14:ObjectDetectionYOLOv5-6.2: will try again when an adapter is connected.
17:45:14:ObjectDetectionYOLOv5-6.2: At line:1 char:1
17:45:14:ObjectDetectionYOLOv5-6.2: + Start-BitsTransfer -Source 'https:
17:45:14:ObjectDetectionYOLOv5-6.2: + ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
17:45:14:ObjectDetectionYOLOv5-6.2: + CategoryInfo : InvalidOperation: (:) [Start-BitsTransfer], Exception
17:45:14:ObjectDetectionYOLOv5-6.2: + FullyQualifiedErrorId : StartBitsTransferCOMException,Microsoft.BackgroundIntelligentTransfer.Management.NewBits
17:45:14:ObjectDetectionYOLOv5-6.2: TransferCommand
17:45:14:ObjectDetectionYOLOv5-6.2: Downloading Custom YOLO models...BITS transfer failed. Trying Powershell....
17:54:23:ObjectDetectionYOLOv5-6.2: Expanding...done.
17:54:23:ObjectDetectionYOLOv5-6.2: Copying contents of custom-models-yolo5-pt.zip to custom-models...done
17:54:23:ObjectDetectionYOLOv5-6.2: Installing Python packages for Object Detection (YOLOv5 6.2)
17:54:23:ObjectDetectionYOLOv5-6.2: [0;Installing GPU-enabled libraries: If available
17:54:24:ObjectDetectionYOLOv5-6.2: Ensuring Python package manager (pip) is installed...done
17:54:28:ObjectDetectionYOLOv5-6.2: Ensuring Python package manager (pip) is up to date...done
17:54:28:ObjectDetectionYOLOv5-6.2: Python packages specified by requirements.txt
17:54:29:ObjectDetectionYOLOv5-6.2: - Installing urllib3, the HTTP client for Python...(✅ checked) done
17:54:31:Module ObjectDetectionYOLOv5-6.2 installed successfully.
17:54:31:ObjectDetectionYOLOv5-6.2: - Installing Pandas, a data analysis / data manipulation tool...
17:54:31:
17:54:31:Module 'Object Detection (YOLOv5 6.2)' 1.9.2 (ID: ObjectDetectionYOLOv5-6.2)
17:54:31:Valid: True
17:54:31:Module Path: <root>\modules\ObjectDetectionYOLOv5-6.2
17:54:31:Module Location: Internal
17:54:31:AutoStart: True
17:54:31:Queue: objectdetection_queue
17:54:31:Runtime: python3.7
17:54:31:Runtime Location: Shared
17:54:31:FilePath: detect_adapter.py
17:54:31:Start pause: 1 sec
17:54:31:Parallelism: 0
17:54:31:LogVerbosity:
17:54:31:Platforms: all,!raspberrypi,!jetson
17:54:31:GPU Libraries: installed if available
17:54:31:GPU: use if supported
17:54:31:Accelerator:
17:54:31:Half Precision: enable
17:54:31:Environment Variables
17:54:31:APPDIR = <root>\modules\ObjectDetectionYOLOv5-6.2
17:54:31:CUSTOM_MODELS_DIR = <root>\modules\ObjectDetectionYOLOv5-6.2\custom-models
17:54:31:MODELS_DIR = <root>\modules\ObjectDetectionYOLOv5-6.2\assets
17:54:31:MODEL_SIZE = Medium
17:54:31:USE_CUDA = True
17:54:31:YOLOv5_AUTOINSTALL = false
17:54:31:YOLOv5_VERBOSE = false
17:54:31:
17:54:31:Started Object Detection (YOLOv5 6.2) module
17:54:31:Unable to install ObjectDetectionYOLOv5-6.2: Timed out attempting to install Module 'ObjectDetectionYOLOv5-6.2' (A task was canceled.)
17:54:31:Installing initial module FaceProcessing.
17:54:31:Preparing to install module 'FaceProcessing'
17:54:31:Downloading module 'FaceProcessing'
17:54:31:detect_adapter.py: Traceback (most recent call last):
17:54:31:detect_adapter.py: File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-6.2\detect_adapter.py", line 19, in
17:54:31:detect_adapter.py: from codeproject_ai_sdk import JSON, ModuleRunner, LogMethod, LogVerbosity, RequestData
17:54:31:detect_adapter.py: ModuleNotFoundError: No module named 'codeproject_ai_sdk'
17:54:31:Module ObjectDetectionYOLOv5-6.2 has shutdown
17:54:31:detect_adapter.py: has exited
17:54:32:Module ObjectDetectionYOLOv5-6.2 started successfully.
17:54:32:Installing module 'FaceProcessing'
17:54:32:FaceProcessing: Installing CodeProject.AI Analysis Module
17:54:32:FaceProcessing: ======================================================================
17:54:32:FaceProcessing: CodeProject.AI Installer
17:54:32:FaceProcessing: ======================================================================
17:54:32:FaceProcessing: 868.3Gb of 953Gb available on
17:54:32:FaceProcessing: General CodeProject.AI setup
17:54:32:FaceProcessing: Creating Directories...done
17:54:32:FaceProcessing: GPU support
17:54:32:FaceProcessing: CUDA Present...No
17:54:32:FaceProcessing: ROCm Present...No
17:54:32:FaceProcessing: Checking for .NET 7.0...Checking SDKs...Upgrading: .NET is 0
17:54:32:FaceProcessing: Current version is 0. Installing newer version.
17:54:32:FaceProcessing: 'winget' is not recognized as an internal or external command,
17:54:32:FaceProcessing: operable program or batch file.
17:54:34:FaceProcessing: Reading FaceProcessing settings.......done
17:54:34:FaceProcessing: Installing module Face Processing 1.11.0
17:54:34:FaceProcessing: Installing Python 3.7
17:54:34:FaceProcessing: Python 3.7 is already installed
17:54:34:FaceProcessing: Creating Virtual Environment (Shared)...Virtual Environment already present
17:54:34:FaceProcessing: Confirming we have Python 3.7 in our virtual environment...present
21:51:26:FaceProcessing: Start-BitsTransfer : There are currently no active network connections. Background Intelligent Transfer Service (BITS)
21:51:26:FaceProcessing: will try again when an adapter is connected.
21:51:26:FaceProcessing: At line:1 char:1
21:51:26:FaceProcessing: + Start-BitsTransfer -Source 'https://codeproject-ai.s3.ca-central-1.am ...
21:51:26:FaceProcessing: + ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
21:51:26:FaceProcessing: + CategoryInfo : InvalidOperation: (:) [Start-BitsTransfer], Exception
21:51:26:FaceProcessing: + FullyQualifiedErrorId : StartBitsTransferCOMException,Microsoft.BackgroundIntelligentTransfer.Management.NewBits
21:51:26:FaceProcessing: TransferCommand
21:51:26:FaceProcessing: Start-BitsTransfer : There are currently no active network connections. Background Intelligent Transfer Service (BITS)
21:51:26:FaceProcessing: will try again when an adapter is connected.
21:51:26:FaceProcessing: At line:1 char:1
21:51:26:FaceProcessing: + Start-BitsTransfer -Source 'https:
21:51:26:FaceProcessing: + ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
21:51:26:FaceProcessing: + CategoryInfo : InvalidOperation: (:) [Start-BitsTransfer], Exception
21:51:26:FaceProcessing: + FullyQualifiedErrorId : StartBitsTransferCOMException,Microsoft.BackgroundIntelligentTransfer.Management.NewBits
21:51:26:FaceProcessing: TransferCommand
21:51:26:FaceProcessing: Downloading Face models...BITS transfer failed. Trying Powershell....
21:51:26:FaceProcessing: Invoke-WebRequest : The remote name could not be resolved: 'codeproject-ai.s3.ca-central-1.amazonaws.com'
21:51:26:FaceProcessing: At line:1 char:1
21:51:26:FaceProcessing: + Invoke-WebRequest 'https://codeproject-ai.s3.ca-central-1.amazonaws.c ...
21:51:26:FaceProcessing: + ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
21:51:26:FaceProcessing: + CategoryInfo : InvalidOperation: (System.Net.HttpWebRequest:HttpWebRequest) [Invoke-WebRequest], WebExc
21:51:26:FaceProcessing: eption
21:51:26:FaceProcessing: + FullyQualifiedErrorId : WebCmdletWebResponseException,Microsoft.PowerShell.Commands.InvokeWebRequestCommand
21:51:26:FaceProcessing: Download failed. Sorry.
21:51:26:FaceProcessing: Failed to download and extract models-face-pt.zip
21:51:27:FaceProcessing: Installing Python packages for Face Processing
21:51:27:FaceProcessing: [0;Installing GPU-enabled libraries: If available
21:51:27:FaceProcessing: Ensuring Python package manager (pip) is installed...done
21:51:36:FaceProcessing: Ensuring Python package manager (pip) is up to date...done
21:51:36:FaceProcessing: Python packages specified by requirements.txt
21:51:36:FaceProcessing: - Installing urllib3, the HTTP client for Python...Already installed
21:51:45:FaceProcessing: - Installing Pandas, a data analysis / data manipulation tool...(✅ checked) done
21:52:03:FaceProcessing: - Installing CoreMLTools, for working with .mlmodel format models...(✅ checked) done
21:52:07:FaceProcessing: - Installing OpenCV, the Open source Computer Vision library...(✅ checked) done
21:52:09:FaceProcessing: - Installing Pillow, a Python Image Library...(✅ checked) done
21:52:16:FaceProcessing: - Installing SciPy, a library for mathematics, science, and engineering...(✅ checked) done
21:52:17:FaceProcessing: - Installing PyYAML, a library for reading configuration files...Already installed
21:52:41:FaceProcessing: - Installing PyTorch, for Tensor computation and Deep neural networks...(✅ checked) done
21:53:14:FaceProcessing: - Installing TorchVision, for Computer Vision based AI...(✅ checked) done
21:53:31:FaceProcessing: - Installing Seaborn, a data visualization library based on matplotlib...(✅ checked) done
21:53:39:FaceProcessing: - Installing the CodeProject.AI SDK...(✅ checked) done
21:53:39:FaceProcessing: Installing Python packages for the CodeProject.AI Server SDK
21:53:40:FaceProcessing: Ensuring Python package manager (pip) is installed...done
21:53:41:FaceProcessing: Ensuring Python package manager (pip) is up to date...done
21:53:41:FaceProcessing: Python packages specified by requirements.txt
21:53:42:FaceProcessing: - Installing Pillow, a Python Image Library...Already installed
21:53:42:FaceProcessing: - Installing Charset normalizer...Already installed
21:53:43:FaceProcessing: - Installing aiohttp, the Async IO HTTP library...Already installed
21:53:43:FaceProcessing: - Installing aiofiles, the Async IO Files library...Already installed
21:53:44:FaceProcessing: - Installing py-cpuinfo to allow us to query CPU info...Already installed
21:53:45:FaceProcessing: - Installing Requests, the HTTP library...Already installed
21:53:45:FaceProcessing: Scanning modulesettings for downloadable models...No models specified
21:53:54:FaceProcessing: Self test: Self-test passed
21:53:54:FaceProcessing: Module setup time 03:59:21.90
21:53:54:FaceProcessing: Setup complete
21:53:55:FaceProcessing: Total setup time 03:59:22.43
21:53:55:Module FaceProcessing installed successfully.
21:53:55:
21:53:55:Module 'Face Processing' 1.11.0 (ID: FaceProcessing)
21:53:55:Valid: True
21:53:55:Module Path: <root>\modules\FaceProcessing
21:53:55:Module Location: Internal
21:53:55:AutoStart: True
21:53:55:Queue: faceprocessing_queue
21:53:55:Runtime: python3.7
21:53:55:Runtime Location: Shared
21:53:55:FilePath: intelligencelayer\face.py
21:53:55:Start pause: 3 sec
21:53:55:Parallelism: 0
21:53:55:LogVerbosity:
21:53:55:Platforms: all,!jetson
21:53:55:GPU Libraries: installed if available
21:53:55:GPU: use if supported
21:53:55:Accelerator:
21:53:55:Half Precision: enable
21:53:55:Environment Variables
21:53:55:APPDIR = <root>\modules\FaceProcessing\intelligencelayer
21:53:55:DATA_DIR = C:\ProgramData\CodeProject\AI
21:53:55:MODE = MEDIUM
21:53:55:MODELS_DIR = <root>\modules\FaceProcessing\assets
21:53:55:PROFILE = desktop_gpu
21:53:55:USE_CUDA = True
21:53:55:YOLOv5_AUTOINSTALL = false
21:53:55:YOLOv5_VERBOSE = false
21:53:55:
21:53:55:Started Face Processing module
21:53:55:Installer exited with code 0
21:53:58:Module FaceProcessing started successfully.
21:59:17:Update ObjectDetectionYOLOv5-6.2. Setting AutoStart=false
21:59:17:Stopping Object Detection (YOLOv5 6.2)
21:59:24:Update ObjectDetectionYOLOv5Net. Setting AutoStart=true
21:59:24:Restarting Object Detection (YOLOv5 .NET) to apply settings change
21:59:24:
21:59:24:Module 'Object Detection (YOLOv5 .NET)' 1.10.2 (ID: ObjectDetectionYOLOv5Net)
21:59:24:Valid: True
21:59:24:Module Path: <root>\modules\ObjectDetectionYOLOv5Net
21:59:24:Module Location: Internal
21:59:24:AutoStart: True
21:59:24:Queue: objectdetection_queue
21:59:24:Runtime: dotnet
21:59:24:Runtime Location: System
21:59:24:FilePath: bin\ObjectDetectionYOLOv5Net.exe
21:59:24:Start pause: 1 sec
21:59:24:Parallelism: 0
21:59:24:LogVerbosity:
21:59:24:Platforms: all,!windows-arm64
21:59:24:GPU Libraries: installed if available
21:59:24:GPU: use if supported
21:59:24:Accelerator:
21:59:24:Half Precision: enable
21:59:24:Environment Variables
21:59:24:CUSTOM_MODELS_DIR = <root>\modules\ObjectDetectionYOLOv5Net\custom-models
21:59:24:MODELS_DIR = <root>\modules\ObjectDetectionYOLOv5Net\assets
21:59:24:MODEL_SIZE = MEDIUM
21:59:24:
21:59:24:Started Object Detection (YOLOv5 .NET) module
22:00:29:Sending shutdown request to python/FaceProcessing
22:00:37:ObjectDetectionYOLOv5Net.exe: Application started. Press Ctrl+C to shut down.
22:00:37:ObjectDetectionYOLOv5Net.exe: Hosting environment: Production
22:00:37:ObjectDetectionYOLOv5Net.exe: Content root path: C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5Net
22:00:38:Object Detection (YOLOv5 .NET): Object Detection (YOLOv5 .NET) module started.
22:00:39:face.py: Face Processing started.
22:00:39:Module FaceProcessing has shutdown
22:00:39:face.py: has exited
22:01:02:FaceProcessing went quietly
----------------------------
thanks charlie
|
|
|
|
|
|
Thanks Sean, while I had looked at this earlier (as it was mentioned in another of your posts), I had missed the troubleshooting section and common issues at the bottom of the page which then links off to
https://github.com/microsoft/winget-cli/tree/master/doc/troubleshooting#common-issues[^]
The third fix.... App Installer did not automatically add the PATH environment variable ... seems have worked and the install was successful.
Thanks for your help.
|
|
|
|
|
System info (Docker on unraid):
Server version: 2.6.5
System: Docker (06b6a39b30a2)
Operating System: Linux (Ubuntu 22.04)
CPUs: 12th Gen Intel(R) Core(TM) i5-12600K (Intel)
1 CPU x 10 cores. 16 logical processors (x64)
System RAM: 63 GiB
Platform: Linux
BuildConfig: Release
Execution Env: Docker
Runtime Env: Production
Runtimes installed:
.NET runtime: 7.0.19
.NET SDK: Not found
Default Python: 3.10.12
Go: Not found
NodeJS: Not found
Rust: Not found
Video adapter info:
System GPU info:
GPU 3D Usage 0%
GPU RAM Usage 0
Global Environment variables:
CPAI_APPROOTPATH = <root>
CPAI_PORT = 32168
Starting with multi TPU and then after a few minutes it switches to single TPU. Did a completely reinstall of code project and it's modules, but didn't help. See the following log:
18:09:40:Module 'Object Detection (Coral)' 2.3.4 (ID: ObjectDetectionCoral)
18:09:40:Valid: True
18:09:40:Module Path: <root>/modules/ObjectDetectionCoral
18:09:40:Module Location: Internal
18:09:40:AutoStart: True
18:09:40:Queue: objectdetection_queue
18:09:40:Runtime: python3.9
18:09:40:Runtime Location: Local
18:09:40:FilePath: objectdetection_coral_adapter.py
18:09:40:Start pause: 1 sec
18:09:40:Parallelism: 16
18:09:40:LogVerbosity:
18:09:40:Platforms: all
18:09:40:GPU Libraries: installed if available
18:09:40:GPU: use if supported
18:09:40:Accelerator:
18:09:40:Half Precision: enable
18:09:40:Environment Variables
18:09:40:CPAI_CORAL_MODEL_NAME = YOLOv8
18:09:40:CPAI_CORAL_MULTI_TPU = true
18:09:40:MODELS_DIR = <root>/modules/ObjectDetectionCoral/assets
18:09:40:MODEL_SIZE = small
18:09:40:
18:09:40:Started Object Detection (Coral) module
18:09:42:objectdetection_coral_adapter.py: Unable to load OpenCV or numpy modules. Only using PIL.
18:09:42:objectdetection_coral_adapter.py: TPU detected
18:09:42:objectdetection_coral_adapter.py: Attempting multi-TPU initialisation
18:09:42:objectdetection_coral_adapter.py: Supporting multiple Edge TPUs
18:10:08:Response rec'd from Object Detection (Coral) command 'custom' (...90087c) [''] took 112ms
18:10:09:Response rec'd from Object Detection (Coral) command 'custom' (...6d7f74) [''] took 86ms
18:10:09:Response rec'd from Object Detection (Coral) command 'custom' (...26839f) [''] took 107ms
18:10:09:Response rec'd from Object Detection (Coral) command 'custom' (...a74e58) [''] took 110ms
18:10:09:Response rec'd from Object Detection (Coral) command 'custom' (...e6f93e) [''] took 83ms
18:10:10:Response rec'd from Object Detection (Coral) command 'custom' (...2ab28a) ['Found person'] took 101ms
18:10:10:Response rec'd from Object Detection (Coral) command 'custom' (...5d5479) [''] took 101ms
18:10:11:Response rec'd from Object Detection (Coral) command 'custom' (...1b57e1) [''] took 97ms
18:10:11:Response rec'd from Object Detection (Coral) command 'custom' (...26b36d) [''] took 83ms
18:10:12:Response rec'd from Object Detection (Coral) command 'custom' (...6d13de) ['Found person'] took 91ms
18:10:22:Response rec'd from Object Detection (Coral) command 'custom' (...17d97d) [''] took 90ms
18:10:27:Response rec'd from Object Detection (Coral) command 'custom' (...e1384b) [''] took 101ms
18:12:21:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU detection
18:12:21:Response rec'd from Object Detection (Coral) command 'custom' (...ebb79b) ['Found boat'] took 89ms
18:12:27:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU detection
18:12:27:Response rec'd from Object Detection (Coral) command 'custom' (...f824c4) ['No objects found'] took 86ms
18:12:40:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU detection
18:12:41:Response rec'd from Object Detection (Coral) command 'custom' (...79975a) ['Found boat'] took 86ms
18:13:00:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU detection
18:13:00:Response rec'd from Object Detection (Coral) command 'custom' (...6019a8) ['Found boat'] took 86ms
18:14:26:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU detection
18:14:26:Response rec'd from Object Detection (Coral) command 'custom' (...ce7a06) ['No objects found'] took 85ms
18:14:59:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU detection
18:14:59:Response rec'd from Object Detection (Coral) command 'custom' (...34430b) ['Found boat'] took 86ms
18:16:25:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU detection
18:16:25:Response rec'd from Object Detection (Coral) command 'custom' (...4ab153) ['No objects found'] took 87ms
18:16:58:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU detection
18:16:58:Response rec'd from Object Detection (Coral) command 'custom' (...9e49b0) ['Found boat'] took 86ms
18:18:24:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU detection
18:18:24:objectdetection_coral_adapter.py: Object Detection (Coral) started.
18:18:24:objectdetection_coral_adapter.py: Model change detected. Forcing model reload.
18:18:24:objectdetection_coral_adapter.py: Refreshing the Tensorflow Interpreter
18:18:24:objectdetection_coral_adapter.py: Model change detected. Forcing model reload.
18:18:24:objectdetection_coral_adapter.py: Refreshing the Tensorflow Interpreter
18:18:24:objectdetection_coral_adapter.py: Model change detected. Forcing model reload.
18:18:24:objectdetection_coral_adapter.py: Refreshing the Tensorflow Interpreter
18:18:24:objectdetection_coral_adapter.py: Model change detected. Forcing model reload.
18:18:24:objectdetection_coral_adapter.py: Refreshing the Tensorflow Interpreter
18:18:24:objectdetection_coral_adapter.py: Model change detected. Forcing model reload.
18:18:24:objectdetection_coral_adapter.py: Refreshing the Tensorflow Interpreter
18:18:24:objectdetection_coral_adapter.py: Model change detected. Forcing model reload.
18:18:24:objectdetection_coral_adapter.py: Refreshing the Tensorflow Interpreter
18:18:24:objectdetection_coral_adapter.py: Model change detected. Forcing model reload.
18:18:24:objectdetection_coral_adapter.py: Refreshing the Tensorflow Interpreter
18:18:24:objectdetection_coral_adapter.py: Model change detected. Forcing model reload.
18:18:24:objectdetection_coral_adapter.py: Refreshing the Tensorflow Interpreter
18:18:25:Response rec'd from Object Detection (Coral) command 'custom' (...e5348b) ['No objects found'] took 86ms
|
|
|
|
|
I've did some more testing. And it looks like when the coral is not been used for over a minute, it does something which causes the YOLOv8 model to "disappear". Don't know if the device goes into sleep mode or something?
11:50:59:Response rec'd from Object Detection (Coral) command 'custom' (...1cb9fb) ['Found car'] took 113ms
11:51:03:Response rec'd from Object Detection (Coral) command 'custom' (...25297c) ['Found car, truck'] took 55ms
11:51:14:Response rec'd from Object Detection (Coral) command 'custom' (...f0746e) ['Found car, person'] took 105ms
11:51:17:Response rec'd from Object Detection (Coral) command 'custom' (...6dcb9d) ['Found car, person'] took 56ms
11:51:20:Response rec'd from Object Detection (Coral) command 'custom' (...a2d7f2) ['Found car, person'] took 127ms
11:51:59:Response rec'd from Object Detection (Coral) command 'custom' (...3e42cc) ['Found car, person'] took 115ms
11:52:12:Response rec'd from Object Detection (Coral) command 'custom' (...bc375e) [''] took 82ms
11:52:34:Response rec'd from Object Detection (Coral) command 'custom' (...70382a) ['Found n/a'] took 83ms
11:53:58:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU listing
11:53:58:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU listing
11:54:11:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU detection
11:54:11:Response rec'd from Object Detection (Coral) command 'custom' (...13e823) ['No objects found'] took 86ms
11:54:33:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU detection
11:54:33:Response rec'd from Object Detection (Coral) command 'custom' (...160a03) ['Found boat'] took 85ms
11:54:49:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU listing
11:54:49:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU listing
11:54:52:Response rec'd from Object Detection (Coral) command 'custom' (...140453) ['Found n/a'] took 131ms
11:54:58:Response rec'd from Object Detection (Coral) command 'custom' (...e8aaed) ['Found car, person'] took 57ms
11:55:05:Response rec'd from Object Detection (Coral) command 'custom' (...dea51f) ['Found car, person'] took 29ms
11:55:07:Response rec'd from Object Detection (Coral) command 'custom' (...0900b2) ['Found car, person'] took 29ms
11:55:08:Response rec'd from Object Detection (Coral) command 'custom' (...a4c163) ['Found car, person'] took 29ms
11:55:10:Response rec'd from Object Detection (Coral) command 'custom' (...be7804) ['Found car, person'] took 28ms
11:55:12:Response rec'd from Object Detection (Coral) command 'custom' (...a9c121) ['Found n/a'] took 117ms
When this happens I can see in the explorer that only these 2 are available:
When I geve the explorer some tasks, it "wakes-up" the coral device, and the YOLOv8 is available again in the explorer. And I can see there are no errors in the log and Multi-TPU is supported.
Is there an option for the Coral to not go into "Sleep mode"?
|
|
|
|
|
@sean-ewington Just want to make sure you would see my second post as well. Did some extra testing, hopefully this information is useful.
|
|
|
|
|
I am also seeing a similar issue on my unraid server using the dual tpu with magic-blue-smoke adapter for pcie
however mine happens immediately. I have both apex_0 and apex_1 passed into the devices on the docker template
11:10:56:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU detection
11:10:56:Response rec'd from Object Detection (Coral) command 'detect' (...0befd9) ['Found chair, book'] took 9ms
11:10:56:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU detection
11:10:56:Response rec'd from Object Detection (Coral) command 'detect' (...63ce15) ['Found airplane'] took 9ms
11:10:56:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU detection
11:10:56:Response rec'd from Object Detection (Coral) command 'detect' (...339d19) ['Found airplane'] took 9ms
11:10:56:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU detection
11:10:56:Response rec'd from Object Detection (Coral) command 'detect' (...d59db8) ['Found chair'] took 9ms
11:10:56:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU detection
11:10:56:Response rec'd from Object Detection (Coral) command 'detect' (...057bcd) ['Found chair'] took 9ms
11:10:56:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU detection
11:10:56:Response rec'd from Object Detection (Coral) command 'detect' (...a9c465) ['No objects found'] took 9ms
11:10:57:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU detection
11:10:57:Response rec'd from Object Detection (Coral) command 'detect' (...5509a6) ['Found chair'] took 9ms
11:10:57:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU detection
11:10:57:Response rec'd from Object Detection (Coral) command 'detect' (...30e498) ['Found chair, car'] took 9ms
11:10:57:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-TPU/CPU detection
11:10:57:Response rec'd from Object Detection (Coral) command 'detect' (...96e754) ['Found chair'] took 9ms
11:10:57:objectdetection_coral_adapter.py: WARNING:root:No multi-TPU interpreters: Falling back to single-T
I am trying code project ai as when I tried frigate with the dual tpu my whole server crashes for some reason
|
|
|
|
|
I have the same issue. No dual TPU, but the logs still say the same things you posted: "Falling back to single-TPU/CPU detection". I assume it's still working on the TPU, but no way to really make sure, is there?
|
|
|
|
|
Hi,
No matter what I try, I can't get my CodeProject.AI Docker installation to recognize the Coral TPU. I'm using the original cable, have tried the native USB ports as well as a powered hub USB port on my mini PC running Ubuntu.
Any suggestions?
Below is the output:
20:25:04:Module 'Object Detection (Coral)' 2.3.4 (ID: ObjectDetectionCoral)
20:25:04:Valid: True
20:25:04:Module Path: <root>/modules/ObjectDetectionCoral
20:25:04:Module Location: Internal
20:25:04:AutoStart: True
20:25:04:Queue: objectdetection_queue
20:25:04:Runtime: python3.9
20:25:04:Runtime Location: Local
20:25:04:FilePath: objectdetection_coral_adapter.py
20:25:04:Start pause: 1 sec
20:25:04:Parallelism: 16
20:25:04:LogVerbosity:
20:25:04:Platforms: all
20:25:04:GPU Libraries: installed if available
20:25:04:GPU: use if supported
20:25:04:Accelerator:
20:25:04:Half Precision: enable
20:25:04:Environment Variables
20:25:04:CPAI_CORAL_MODEL_NAME = YOLOv8
20:25:04:CPAI_CORAL_MULTI_TPU = True
20:25:04:MODELS_DIR = <root>/modules/ObjectDetectionCoral/assets
20:25:04:MODEL_SIZE = medium
20:25:04:
20:25:04:Started Object Detection (Coral) module
20:25:05:objectdetection_coral_adapter.py: Unable to load OpenCV or numpy modules. Only using PIL.
20:25:05:objectdetection_coral_adapter.py: Unable to find or initialise the Coral TPU. Falling back to CPU-only.
20:25:05:objectdetection_coral_adapter.py: Using CPU
|
|
|
|
|
Thanks very much for your report. Could you please share your System Info tab from your CodeProject.AI Server dashboard? What are you running CodeProject.AI Server on?
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
Hi friend, I have some problems training a custom model for weapon detection. I'll explain a little bit and obviously I'm doing this as a test to leave a proven base for other training. I'm using Windows, CodeProject.AI on a computer that serves as a server and DVR agent installed on a local computer also with Windows. I did everything that some instructions and links indicated but very vaguely, I'm sorry for me since I don't know much about python and other tools that are recommended but nevertheless I got to the point of creating the .pt file which was long nights of testing, trial and error but when I put the file it gives me an error: (AI server error: check the logs and that the AI server is running) and obviously it doesn't recognize anything at least not what I want.
The configuration that I put in the endpoint is: /v1/vision/custom/arma_model
Object classes: gun (all images were tagged like this)
In the configuration to find objects I select gun, but it doesn't recognize anything.
Now I'll explain the process a little bit. First I downloaded about 150 images and placed them in a folder, then with labelImg I placed labels on all of them, finally with a train.py file between this custom model which gave me arma_model.pth as a result, obviously I changed the extension to .pt and copied it to the folder ....\CodeProject\AI\modules\ObjectDetectionYOLOv5-6.2, after this I went to AgentDvr and within the Object Recognition configuration I made the changes I mentioned above but it doesn't work for me. Please if someone has a more explicit and intuitive instruction on how to train or create an object recognition model or any tips that I can use for that I would really appreciate it. I've been doing this for more than 3 days now but without results.
CodeProject.AI Version V.2.6.5
AgentDvr Version V.5.6.1.0
Windows11 64Bit
|
|
|
|
|
This is v 2.6.5 connected to Agent DVR 5.6.0.0 on a Windows 11 system. Agent DVR tests the AI server as OK.
It looks like the logging stops intermittently because Agent DVR is sending motion detections every minute or so but I'm only seeing a log entry every 15 minutes or so, both when something is detected and nothing found, but many queries are not in the logs.
It was running for awhile, then stopped logging. This is a section from the log. Notice the log gap at the end. The time when I took this snapshot was 14:49 so nothing was received for 15 minutes while there were several motion events.
Quote: 14:15:02:Object Detection (YOLOv5 6.2): Detecting using ipcam-combined
14:15:02:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...f35649) ['No objects found'] took 72ms
14:15:03:Object Detection (YOLOv5 6.2): Detecting using ipcam-combined
14:15:03:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...ee5f36) ['No objects found'] took 60ms
14:15:04:Object Detection (YOLOv5 6.2): Detecting using ipcam-combined
14:15:04:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...846101) ['No objects found'] took 57ms
14:15:05:Object Detection (YOLOv5 6.2): Detecting using ipcam-combined
14:15:05:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...04462b) ['No objects found'] took 44ms
14:15:06:Object Detection (YOLOv5 6.2): Detecting using ipcam-combined
14:15:06:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...4a6f63) ['No objects found'] took 65ms
14:15:07:Object Detection (YOLOv5 6.2): Detecting using ipcam-combined
14:15:07:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...18300c) ['No objects found'] took 72ms
14:15:09:Object Detection (YOLOv5 6.2): Detecting using ipcam-combined
14:15:09:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...1e1ef3) ['Found person'] took 71ms
14:15:10:Object Detection (YOLOv5 6.2): Detecting using ipcam-combined
14:15:10:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...63286a) ['No objects found'] took 68ms
14:15:15:Object Detection (YOLOv5 6.2): Detecting using ipcam-combined
14:15:15:Response rec'd from Object Detection (YOLOv5 6.2) command 'custom' (...4961b8) ['No objects found'] took 50ms
14:34:52:Response rec'd from Object Detection (YOLOv5 6.2) command 'detect' (...7b70a1) ['Found person'] took 69ms
|
|
|
|
|
Thanks very much for your report. Could you please share your System Info tab from your CodeProject.AI Server dashboard?
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
It's not stopping now, I think that was some kind of intermittent problem because I've not seen it since then.
However, is there any way to make the log file longer? I'm getting a lot of motion events from having the camera in patrol mode so the log file is wrapping around to quickly.
Here's the System Info:
Quote: Server version: 2.6.5
System: Windows
Operating System: Windows (Microsoft Windows 11 version 10.0.22631)
CPUs: 12th Gen Intel(R) Core(TM) i7-12700H (Intel)
1 CPU x 14 cores. 20 logical processors (x64)
GPU (Primary): NVIDIA GeForce RTX 3060 Laptop GPU (6 GiB) (NVIDIA)
Driver: 552.12, CUDA: 12.4 (up to: 12.4), Compute: 8.6, cuDNN:
System RAM: 64 GiB
Platform: Windows
BuildConfig: Release
Execution Env: Native
Runtime Env: Production
Runtimes installed:
.NET runtime: 7.0.11
.NET SDK: 7.0.401
Default Python: Not found
Go: Not found
NodeJS: Not found
Rust: Not found
Video adapter info:
NVIDIA GeForce RTX 3060 Laptop GPU:
Driver Version 31.0.15.5212
Video Processor NVIDIA GeForce RTX 3060 Laptop GPU
Intel(R) Iris(R) Xe Graphics:
Driver Version 31.0.101.5186
Video Processor Intel(R) Iris(R) Xe Graphics Family
System GPU info:
GPU 3D Usage 15%
GPU RAM Usage 2.1 GiB
Global Environment variables:
CPAI_APPROOTPATH = <root>
CPAI_PORT = 32168
|
|
|
|
|
You can always look at the log file itself. If you go to C:\Program Files\CodeProject\AI\modules then look at the corresponding module folder, you should be able to find install.log in there which is complete.
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|