|
I have eight TPUs in my machine, just none of them USB. So I know it should work.
|
|
|
|
|
8??? omg. how does the multi-mode work then?
|
|
|
|
|
|
Just a thought I wonder if the mesh would work like this. tpu on 1 instance of cpai and another instance of cpai with the 2nd tpu.
|
|
|
|
|
The pipelining between model segments will be more efficient if they are in the same machine.
|
|
|
|
|
ah nice - did not know unraid had the option in settings of running a 2nd instance of a container!
|
|
|
|
|
Wasn't able to get a 2nd instance running with a different port 32169 for example. It span up but somehow was linked to 32168 each time - even after making sure all the host ports were 32169 udp/tcp and web gui. unique name etc. But had no success
|
|
|
|
|
Set up a 2nd instance on the windows pc with the coral usb.
And 2 servers added on AITool so they share the 2 servers. Seems to work well and share the load.
|
|
|
|
|
I still think you should have better performance with one instance of CPAI running two TPUs, but if that doesn’t work, then I’m glad you got this working!
|
|
|
|
|
Some interesting results testing the tiny, small, medium and large MobileNet SSD with the same picture.
The small model found far more objects that all the other models even though some were wrong!
So going with the small right now and see how it goes with the filters on the AITool. May pick up the smaller objects that the medium and large miss or filter them out
|
|
|
|
|
My question :
Is it possible to have this configuration and the system work correctly ?
Because my GPU is every time at 0% usage and I have test lot of driver, cuda and codeproject ai version and event my GPU is at 0% usage...
I don't know if it's possible to have more information in the docs or idkb because the project have good evolution but even update never work correcly with my instance....
I'm on docker linux system.
Thank you a lot for next answer
What I have tried:
Test a lot of driver, cuda and codeproject ai (since 1 year)
|
|
|
|
|
Have you been able to run any version of CodeProject.AI Server? Also, could you please share your System Info tab from your CodeProject.AI Server dashboard, if you're able to load it, and share any install logs you have for modules where you were trying to use GPU?
Historically, a lot of users have had trouble getting the GPU to work for the GTX 1650. Half-precision should definitely be disabled. I did see one user report that 2.5.6 worked for them on Windows.
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
|
Thanks very much for the further info. If GPU is displayed on the CodeProject.AI Server dashboard next to the YOLOv8 module, it means the torch libraries are reporting GPU is present and will be used.
What tool/program are you using to monitor the GPU usage?
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
|
When I access the server via the IP address at port 32168, the server shows "Online"; however, when accessed through Cloudflare tunnel, the server displays "Searching" and then "Offline".
The CodeProject.AI server is running in my Docker on my NAS.
Any idea what could be the problem?
-- modified 20-Apr-24 3:18am.
|
|
|
|
|
Apologies, this is Cloudflare Tunnel setup question, and I am unfamiliar with it.
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
Inside of blueiris, I can view video and 'test with AI' where it puts a box around people, cars, etc and labels them. For some reason I am unable to get this feedback in BI when using Object Detection (YOLOv8) 1.4.2.
I've tested a bunch of object detection versions and I find YOLOv8 the best but I have no way to tell if it's actually running correctly.
When I run Object Detection (YOLOv5 .NET) 1.10.1 I am able to review footage 'testing with AI' and the box comes up around whatever is detected.
Is there a way to fix YOLOv8?
This is from the logs:
13:25:54:Response rec'd from Object Detection (YOLOv8) command 'detect' (...e47814)
13:25:54:Object Detection (YOLOv8): Unable to create YOLO detector for model yolov8m
13:26:12:Object Detection (YOLOv8): C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\assets\yolov8m.pt does not exist
13:26:12:Response rec'd from Object Detection (YOLOv8) command 'detect' (...e16bc8)
13:26:12:Object Detection (YOLOv8): Unable to create YOLO detector for model yolov8m
13:26:12:Object Detection (YOLOv8): C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv8\assets\yolov8m.pt does not exist
modified 23-Apr-24 13:29pm.
|
|
|
|
|
You should be able to see YOLOv8 detections happening in the CodeProject.AI server logs, if it's working. And you should get your usual Alerts or logs within Blue Iris as normal. Make sure you don't have multiple Object Detection modules active, just YOLOv8.
I'm also wondering if your YOLOv8 simply didn't install correctly. Could you please share the installation log? It's here:
After you share that, you might simply try un-installing and re-installing it.
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
Thanks, the log is below:
Module 'Object Detection (YOLOv8)' 1.4.3 (ID: ObjectDetectionYOLOv8)
Valid: True
Module Path: <root>\modules\ObjectDetectionYOLOv8
AutoStart: True
Queue: objectdetection_queue
Runtime: python3.9
Runtime Loc: Local
FilePath: detect_adapter.py
Start pause: 1 sec
Parallelism: 0
LogVerbosity:
Platforms: all
GPU Libraries: installed if available
GPU Enabled: enabled
Accelerator:
Half Precis.: enable
Environment Variables
APPDIR = <root>\modules\ObjectDetectionYOLOv8
CUSTOM_MODELS_DIR = <root>\modules\ObjectDetectionYOLOv8\custom-models
MODELS_DIR = <root>\modules\ObjectDetectionYOLOv8\assets
MODEL_SIZE = Medium
USE_CUDA = True
YOLO_VERBOSE = false
Status Data: {
"inferenceDevice": "GPU",
"inferenceLibrary": "CUDA",
"canUseGPU": "true",
"successfulInferences": 0,
"failedInferences": 89,
"numInferences": 89,
"averageInferenceMs": 0
}
Started: 17 Apr 2024 8:40:06 PM Eastern Standard Time
LastSeen: 17 Apr 2024 8:42:52 PM Eastern Standard Time
Status: Stopped
Requests: 96 (includes status calls)
|
|
|
|
|
I've uninstalled/reinstalled at least once before. I'm always sure to stop other YOLO instances before enabling v8.
In a comparison, yolov8 had the best benchmark scoring but for some reason it seems not to be showing up in BI.
|
|
|
|
|
Thank you kindly. One final thing, could you please share your System Info tab from your CodeProject.AI Server dashboard?
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
Server version: 2.6.2
System: Windows
Operating System: Windows (Microsoft Windows 10.0.19045)
CPUs: Intel(R) Core(TM) i7-6700T CPU @ 2.80GHz (Intel)
1 CPU x 4 cores. 8 logical processors (x64)
GPU (Primary): NVIDIA GeForce GTX 960 (4 GiB) (NVIDIA)
Driver: 552.12, CUDA: 12.4 (up to: 12.4), Compute: 5.2, cuDNN:
System RAM: 16 GiB
Platform: Windows
BuildConfig: Release
Execution Env: Native
Runtime Env: Production
Runtimes installed:
.NET runtime: 7.0.5
.NET SDK: Not found
Default Python: Not found
Go: Not found
NodeJS: Not found
Rust: Not found
Video adapter info:
NVIDIA GeForce GTX 960:
Driver Version 31.0.15.5212
Video Processor NVIDIA GeForce GTX 960
Microsoft Remote Display Adapter:
Driver Version 10.0.19041.3636
Video Processor
System GPU info:
GPU 3D Usage 0%
GPU RAM Usage 2.8 GiB
Global Environment variables:
CPAI_APPROOTPATH = <root>
CPAI_PORT = 32168
|
|
|
|
|
Sorry, one more thing. In C:/Program Files/CodeProject/AI/modules/ObjectDetectionYOLOv8 you will find a install.log file. Can you please share that with us?
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
2024-04-17 19:38:50: Installing CodeProject.AI Analysis Module
2024-04-17 19:38:50: ======================================================================
2024-04-17 19:38:50: CodeProject.AI Installer
2024-04-17 19:38:50: ======================================================================
2024-04-17 19:38:50: 91.9Gb of 953Gb available on
2024-04-17 19:38:50: General CodeProject.AI setup
2024-04-17 19:38:50: Creating Directories...Done
2024-04-17 19:38:50: GPU support
2024-04-17 19:38:50: CUDA Present...Yes (CUDA 11.3, No cuDNN found)
2024-04-17 19:38:51: ROCm Present...No
2024-04-17 19:38:53: Reading ObjectDetectionYOLOv8 settings.......Done
2024-04-17 19:38:53: Installing module Object Detection (YOLOv8) 1.4.3
2024-04-17 19:38:53: Installing Python 3.9
2024-04-17 19:38:53: Python 3.9 is already installed
2024-04-17 19:39:03: Creating Virtual Environment (Local)...Done
2024-04-17 19:39:04: Confirming we have Python 3.9 in our virtual environment...present
2024-04-17 19:39:04: Installing Python packages for Object Detection (YOLOv8)
2024-04-17 19:39:04: [0;Installing GPU-enabled libraries: If available
2024-04-17 19:39:07: Ensuring Python package manager (pip) is installed...Done
2024-04-17 19:39:19: Ensuring Python package manager (pip) is up to date...Done
2024-04-17 19:39:19: Python packages specified by requirements.windows.cuda.txt
2024-04-17 19:40:34: - Installing PyTorch, an open source machine learning framework...(checked) Done
2024-04-17 19:42:03: - Installing TorchVision, for working with computer vision models...(checked) Done
2024-04-17 19:44:16: - Installing Ultralytics package for object detection in images...(checked) Done
2024-04-17 19:44:16: Installing Python packages for the CodeProject.AI Server SDK
2024-04-17 19:44:18: Ensuring Python package manager (pip) is installed...Done
2024-04-17 19:44:21: Ensuring Python package manager (pip) is up to date...Done
2024-04-17 19:44:21: Python packages specified by requirements.txt
2024-04-17 19:44:23: - Installing Pillow, a Python Image Library...Already installed
2024-04-17 19:44:24: - Installing Charset normalizer...Already installed
2024-04-17 19:44:30: - Installing aiohttp, the Async IO HTTP library...(checked) Done
2024-04-17 19:44:34: - Installing aiofiles, the Async IO Files library...(checked) Done
2024-04-17 19:44:35: - Installing py-cpuinfo to allow us to query CPU info...Already installed
2024-04-17 19:44:36: - Installing Requests, the HTTP library...Already installed
2024-04-17 19:44:46: Self test: Self-test passed
2024-04-17 19:44:46: Module setup time 00:05:55.23
2024-04-17 19:44:46: Setup complete
2024-04-17 19:44:46: Total setup time 00:05:56.17
Installer exited with code 0
|
|
|
|