New CodeProject.AI Object Detection (YOLO11 .NET) Module

[MikeLud1]

Since CodeProject.AI has not been receiving any updated modules I figured a way for me to provide updates and new modules. The second module I added is a total new Object Detection (YOLO11 .NET) module. To get my updated or new modules all that is needed is to replace one file see attached (appsettings.json). I recommend backing up the original appsettings.json file before replacing the file. After replacing the file restart the CodeProject.AI server then when on the Dashboard page do a CTRL + F5 to refresh the Dashboard page.

This will now use my available modules in the Install Modules tab. Existing modules will show as Private. If you uninstall a Private module and want to reinstall the module you will need to replace the appsettings.json file with the backed up appsettings.json file. After replacing the file restart the CodeProject.AI server then when on the Dashboard page do a CTRL + F5 to refresh the Dashboard page and the original list of modules will be restored.

Any new or updated module will be in this GitHub repo GitHub - MikeLud/MikeLud-CodeProject.AI-Modules: MikeLud-CodeProject.AI-Modules
The models will be stored on Hugging Face MikeLud (MikeLud)

The module will work with any GPU, CUDA is not needed. No Blue Iris setting changes are needed to use the new module if you are only using custom models ipcam-general. I still need to make all my custom models for the module, currently the only custom models ipcam-general

If you see any issues with this module let me know.

 

[MikeLud1]

ObjectDetectionYOLO11Net Release Notes

Version 1.3.0-DirectML (Latest)

Release Date: October 25, 2025

Overview
YOLO11 multi-task vision module with fixed explore.html interface. Resolves most issues with the exploration UI for better user experience when testing the module.

What's New in This Release

• Fixed explore.html: Resolved most issues with the exploration interface
• Improved UI Testing: Better user experience when testing object detection, pose, segmentation, and classification
• Documentation Updates: All markdown files synchronized to v1.3.0
• Version Consistency: Project files, module settings, and documentation all aligned

Features

• Multi-GPU Support: Select which GPU device to use (devices 0-4)
• DirectML GPU Acceleration: Hardware-accelerated inference using DirectX 12 and DirectML
• Multi-Task Support:
  • Object Detection - Detect 80 COCO object classes
  • Pose Estimation - Detect human poses with 17 keypoints
  • Instance Segmentation - Segment objects with polygon contours
  • Image Classification - Classify images into 1000 ImageNet categories
• YOLO11 Models: Full support for n/s/m/l/x model variants (20 models included)
• Custom Model Support: Load your own trained YOLO11 ONNX models with automatic task detection
• High Performance: Optimized tensor parsing with thread-safe inference and object pooling
• Clean Logging: Minimal console output focused on actual module operations

Configuration
The module supports device ID configuration via:

• Environment Variable: DEVICE_ID (default: "0")
• UI Dropdown: Device ID selector with options 0-4
• Valid Values: 0, 1, 2, 3, 4 (automatically falls back to 0 if invalid)

---

 

[Vettester]

It seems to be working well, thanks Mike!

 

[mvoss]

Mike,

Runs fine here, been running since last night. Thank you. Any idea how long until the ipcam-combined module will be available?

Thanks,
Michael

 

[pepperfr]

Working well for me. Thanks!

 

[Skinny1]

ObjectDetectionYOLO11Net Release Notes

Version 1.3.0-DirectML (Latest)

Release Date: October 25, 2025

Overview
YOLO11 multi-task vision module with fixed explore.html interface. Resolves most issues with the exploration UI for better user experience when testing the module.

What's New in This Release

• Fixed explore.html: Resolved most issues with the exploration interface
• Improved UI Testing: Better user experience when testing object detection, pose, segmentation, and classification
• Documentation Updates: All markdown files synchronized to v1.3.0
• Version Consistency: Project files, module settings, and documentation all aligned

Features

• Multi-GPU Support: Select which GPU device to use (devices 0-4)
• DirectML GPU Acceleration: Hardware-accelerated inference using DirectX 12 and DirectML
• Multi-Task Support:
  • Object Detection - Detect 80 COCO object classes
  • Pose Estimation - Detect human poses with 17 keypoints
  • Instance Segmentation - Segment objects with polygon contours
  • Image Classification - Classify images into 1000 ImageNet categories
• YOLO11 Models: Full support for n/s/m/l/x model variants (20 models included)
• Custom Model Support: Load your own trained YOLO11 ONNX models with automatic task detection
• High Performance: Optimized tensor parsing with thread-safe inference and object pooling
• Clean Logging: Minimal console output focused on actual module operations

Configuration
The module supports device ID configuration via:

• Environment Variable: DEVICE_ID (default: "0")
• UI Dropdown: Device ID selector with options 0-4
• Valid Values: 0, 1, 2, 3, 4 (automatically falls back to 0 if invalid)

---

Mike,

Does the IPcam-general model just have - person and vehicle?


Rick

 

[MikeLud1]

Does the IPcam-general model just have - person and vehicle?

Yes