CodeProject.AI Version 2.0

[MikeLud1]

I see you like to run YOLOv5 .NET instead of the YOLOv5 6.2. Is there a particular benefit of that?

I am see faster speed with YOLOv5 .NET

 

[swilliams76360]

CodeProject.AI Update: Version 2.1.1 Windows Install was just released

V2.1.1

• Improved Raspberry Pi support. A new, fast object detection module with support for the Coral.AI TPU, all within an Arm64 Docker image
• All modules can now be installed / uninstalled (rather than having some modules fixed and uninstallble).
• Installer is streamlined: Only the server is installed at installation time, and on first run we install Object Detection (Python and .NET) and Face Processing (which can be uninstalled).
• Reworking of the Python module SDK. Modules are new child classes, not aggregators of our module runner.
• Reworking of the modulesettings file to make it simpler and have less replication
• Improved logging: quantity, quality, filtering and better information
• Addition of 2 modules: ObjectDetectionTFLite for Object Detection on a on Raspberry Pi using Coral, and Cartoonise for some fun
• Improvements to half-precision support checks on CUDA cards
• Modules are now versioned and our module registry will now only show modules that fit your current server version.
• Various bug fixes
• Shared Python runtimes now in runtimes.
• All modules moved from the AnalysisLayer folder to the modules folder
• Tested on CUDA 12

CodeProject.AI Server: AI the easy way.

Version 2.6.2. Our fast, free, self-hosted Artificial Intelligence Server for any platform, any language

www.codeproject.com

im not seeing the 2.1.1 release on the page to download...has it been delayed?

 

[CAL7]

Tested on CUDA 12

Is upgrading from 11.7 to 12 required?

 

[CrazyAsYou]

im not seeing the 2.1.1 release on the page to download...has it been delayed?

Same for me, still showing 2.0.8 for Windows installer

 

[CrazyAsYou]

Anyone tried this on a Rpi4 yet? I'm just wondering what the response times are like?

 

[djmadfx]

im not seeing the 2.1.1 release on the page to download...has it been delayed?

Same for me, still showing 2.0.8 for Windows installer

The link was previously in the linked article. It now shows 2.0.8. Here is the link for 2.1.1:

https://www.codeproject.com/KB/Articles/5322557/CodeProject.AI.Server-2.1.1.zip

I got some error 500s this morning. Nothing seems to be gained on my end from upgrading 2.0.8 >> 2.1.1

This explains why 2.1.1 was pulled for now: CodeProject.AI Server: AI the easy way.

 

[swilliams76360]

The link was previously in the linked article. It now shows 2.0.8. Here is the link for 2.1.1:

https://www.codeproject.com/KB/Articles/5322557/CodeProject.AI.Server-2.1.1.zip

I got some error 500s this morning. Nothing seems to be gained on my end from upgrading 2.0.8 >> 2.1.1

This explains why 2.1.1 was pulled for now: CodeProject.AI Server: AI the easy way.

thanks for clarifying...will wait for new update

 

[MikeLud1]

Is upgrading from 11.7 to 12 required?

I am using 11.7 so no upgrade neeeded

 

[CCTVCam]

Mike have you made any changes to CPAI server side?

In the last 24-48 hours, it's suddenly started surging to as high as 85% cpu and 7.33GB memory. Looking at the console, it coincides with the object analysis.

I alos don't have Licence Plate Analysis enabled. Prior to the change, mines been running fine - 5% steady and a few hundred mb of memory including BI.

I'm running a comparatively powerful pc for BI: i5 11400, 16gb DDR4 ....

 

[CAL7]

Thanks @kaltertod and @MikeLud1 But, still no joy. All the uninstalls and re-installs seems to go perfectly and the Program Files/CodeProject directory is created again. But it never runs. I see no sign of CPAI in Device Manager or in the Services list. In the Blue Iris AI screen the "Start Now" button (above the CP orange banner) is greyed-out and does not respond.

A quick update. None of the unistall/re-install processes worked with v2.0.8, but 2.1.1 installed beautifully. I have to figure out my model configuration and detection parameters because I get "Nothing Found" but I know CP.AI is being sent the images to analyze. Close!

 

[actran]

New YouTube video on CodeProject.AI

 

[Village Guy]

I am see faster speed with YOLOv5 .NET

Mike can you expand of your knowledge regarding the differences? I have been running with 2.08 and YOLOv5 6.2 since its release. After reading your comment I have switched to YOLOv5 .NET
Since switching my Error 500 timeouts have stopped and I can see from my BI log that it is handling more images per second. Could you explain the Pro's and Con's when you have the time?

 

[David L]

Mike can you expand of your knowledge regarding the differences? I have been running with 2.08 and YOLOv5 6.2 since its release. After reading your comment I have switched to YOLOv5 .NET
Since switching my Error 500 timeouts have stopped and I can see from my BI log that it is handling more images per second. Could you explain the Pro's and Con's when you have the time?

So you are no longer running CA.AI on your GPU?

 

[cybernetics1d]

It looks like version 2.1.3 is out. For those who's having issue with the last 2.1.x version, have you tried this latest? Are you seeing better result?

Regarding YOLOv5 .NET, is anyone using this with intel GPU? I have i7-6700 with intel GPU HD 530, which doesn't seem to be supported with this module as I can't seem to enable GPU mode when I tried using this before. Does anyone what GPU or minimum intel gen GPU that is supported with this or where we can find a list of supported GPU if we're using this YOLOv5 .NET module?

 

[Village Guy]

So you are no longer running CA.AI on your GPU?

Error Free

2023-04-20 13:14:35: Starting "C:\Program Files...ionNet\ObjectDetectionNet.exe"
2023-04-20 13:14:35:
2023-04-20 13:14:35: ** Module 'Object Detection (YOLOv5 .NET)' (ID: ObjectDetectionNet)
2023-04-20 13:14:35: ** Active: True
2023-04-20 13:14:35: ** GPU: Support enabled
2023-04-20 13:14:35: ** Parallelism: 0
2023-04-20 13:14:35: ** Platforms: windows,linux,linux-arm64,macos,macos-arm64
2023-04-20 13:14:35: ** FilePath: ObjectDetectionNet.exe
2023-04-20 13:14:35: ** ModulePath: ObjectDetectionNet
2023-04-20 13:14:35: ** Install: PreInstalled
2023-04-20 13:14:35: ** Runtime: execute
2023-04-20 13:14:35: ** Queue: objectdetection_queue
2023-04-20 13:14:35: ** Start pause: 1 sec
2023-04-20 13:14:35: ** Valid: True
2023-04-20 13:14:35: ** Environment Variables
2023-04-20 13:14:35: ** CPAI_MODULE_SUPPORT_GPU = True
2023-04-20 13:14:35: ** CUSTOM_MODELS_DIR = %CURRENT_MODULE_PATH%\custom-models
2023-04-20 13:14:35: ** MODELS_DIR = %CURRENT_MODULE_PATH%\assets
2023-04-20 13:14:35: ** MODEL_SIZE = MEDIUM
2023-04-20 13:14:35: ** USE_CUDA = True

2023-04-20 14:02:04: ** Operating System: Windows (Microsoft Windows 11 version 10.0.22621)
2023-04-20 14:02:04: ** CPUs: 1 CPU x 8 cores. 16 logical processors (x64)
2023-04-20 14:02:04: ** GPU: NVIDIA GeForce GTX 1060 6GB (6 GiB) (NVidia)
2023-04-20 14:02:04: ** Driver: 516.94 CUDA: 11.7 Compute: 6.1
2023-04-20 14:02:04: ** System RAM: 32 GiB
2023-04-20 14:02:04: ** Target: Windows
2023-04-20 14:02:04: ** BuildConfig: Release
2023-04-20 14:02:04: ** Execution Env: Native
2023-04-20 14:02:04: ** Runtime Env: Production
2023-04-20 14:02:04: ** .NET framework: .NET 7.0.3
2023-04-20 14:02:04: ** App DataDir: C:\ProgramData\CodeProject\AI
2023-04-20 14:02:04: System GPU info:
2023-04-20 14:02:04: GPU 3D Usage 0%
2023-04-20 14:02:04: GPU RAM Usage 279 MiB
2023-04-20 14:02:04: Video adapter info:
2023-04-20 14:02:04: NVIDIA GeForce GTX 1060 6GB:
2023-04-20 14:02:04: Adapter RAM 4 GiB
2023-04-20 14:02:04: Driver Version 31.0.15.1694
2023-04-20 14:02:04: Video Processor NVIDIA GeForce GTX 1060 6GB

 

[MikeLud1]

It looks like version 2.1.3 is out. For those who's having issue with the last 2.1.x version, have you tried this latest? Are you seeing better result?

Regarding YOLOv5 .NET, is anyone using this with intel GPU? I have i7-6700 with intel GPU HD 530, which doesn't seem to be supported with this module as I can't seem to enable GPU mode when I tried using this before. Does anyone what GPU or minimum intel gen GPU that is supported with this or where we can find a list of supported GPU if we're using this YOLOv5 .NET module?

See below for the GPU support

Hardware requirements
DirectML requires a DirectX 12 capable device. Almost all commercially-available graphics cards released in the last several years support DirectX 12. Examples of compatible hardware include:

• AMD GCN 1st Gen (Radeon HD 7000 series) and above
• Intel Haswell (4th-gen core) HD Integrated Graphics and above
• NVIDIA Kepler (GTX 600 series) and above
• Qualcomm Adreno 600 and above

 

[cybernetics1d]

Thanks for the additional info Mike. Based on that, it looks like my 6th gen Intel 530 should be able to work with DirectML. Last time, I tried, it doesn't seem to work. Is this just matter of enabling YOLOv5 .NET and enable GPU or will it auto detect the GPU? Do you know if it requires specific drivers or install DirectX 12 manually?

 

[MikeLud1]

Thanks for the additional info Mike. Based on that, it looks like my 6th gen Intel 530 should be able to work with DirectML. Last time, I tried, it doesn't seem to work. Is this just matter of enabling YOLOv5 .NET and enable GPU or will it auto detect the GPU? Do you know if it requires specific drivers or install DirectX 12 manually?

All you need to do is the below

• Disable Object Detection (YOLOv5 6.2)
• Enable Object Detection (YOLOv5 .NET). One note when you first enable .NET is will show only CPU, after the first detection it should show GPU (DirectML)

 

[rdxny]

All you need to do is the below

• Disable Object Detection (YOLOv5 6.2)
• Enable Object Detection (YOLOv5 .NET). One note when you first enable .NET is will show only CPU, after the first detection it should show GPU (DirectML)

Thanks Mike, that explains why, when I updated CPAI, I had only CPU showing on YOLOv5.NET, and then, later, GPU showed up (for intel internal GPU). I was wondering what I did.. now I know

 

[Jakc]

Is there a guide on how to setup the ipcam models?