YoloDotNet 🚀

Blazing-fast, production-ready YOLO inference for .NET

YoloDotNet is a fully featured C# library for real-time computer vision using YOLOv5u–v12, YOLO-World, and YOLO-E models.
Built on .NET 8 and ONNX Runtime, it delivers high-performance, predictable inference on Windows, Linux, and macOS — with explicit control over execution, memory, and preprocessing.

No Python. No magic. Just fast, deterministic YOLO — done properly for .NET.

⭐ Why YoloDotNet?

YoloDotNet is designed for developers who need:

• ✅ Pure .NET — no Python runtime, no scripts
• ✅ Real performance — CPU, CUDA / TensorRT, OpenVINO, CoreML
• ✅ Explicit configuration — predictable accuracy and memory usage
• ✅ Production readiness — engine caching, long-running stability
• ✅ Large image support — not limited to toy resolutions
• ✅ Multiple vision tasks — detection, OBB, segmentation, pose, classification

Ideal for desktop apps, backend services, and real-time vision pipelines that require deterministic behavior and full control.

🆕 What’s New v4

• Modular execution providers (CPU, CUDA/TensorRT, OpenVINO, CoreML)
• New OpenVINO and CoreML providers
• Cleaner dependency graph
• Improved GPU behavior and predictability
• Grayscale ONNX model support

📖 Full release history: CHANGELOG.md

🚀 Quick Start

1️⃣ Install the core package

dotnet add package YoloDotNet

2️⃣ Install exactly one execution provider

# CPU (recommended starting point)
dotnet add package YoloDotNet.ExecutionProvider.Cpu

# Hardware-accelerated execution (choose one)
dotnet add package YoloDotNet.ExecutionProvider.Cuda
dotnet add package YoloDotNet.ExecutionProvider.OpenVino
dotnet add package YoloDotNet.ExecutionProvider.CoreML

💡 Note: The CUDA execution provider includes optional TensorRT acceleration.
No separate TensorRT package is required.

3️⃣ Run object detection

using SkiaSharp;
using YoloDotNet;
using YoloDotNet.ExecutionProvider.Cpu;

using var yolo = new Yolo(new YoloOptions
{
    ExecutionProvider = new CpuExecutionProvider("model.onnx")
});

using var image = SKBitmap.Decode("image.jpg");

var results = yolo.RunObjectDetection(image, confidence: 0.25, iou: 0.7);

image.Draw(results);
image.Save("result.jpg");

You’re now running YOLO inference in pure C#.

💡 Important: Accuracy Depends on Configuration

YOLO inference accuracy is not automatic.

Preprocessing settings such as image resize mode, sampling method, and confidence/IoU thresholds must match how the model was trained.
These settings directly control the accuracy–performance tradeoff and should be treated as part of the model itself.

📖 Before tuning models or comparing results, read:
👉 Accuracy & Configuration Guide

Supported Tasks

Classification	Object Detection	OBB Detection	Segmentation	Pose Estimation
pexels.com	pexels.com	pexels.com	pexels.com	pexels.com

📁 Demos

Hands-on examples are available in the demo folder:

👉 Browse the demo projects

Includes image inference, video streams, GPU acceleration, segmentation, and large-image workflows.

Execution Providers

Provider	Windows	Linux	macOS	Documentation
CPU	✅	✅	✅	CPU README
CUDA / TensorRT	✅	✅	❌	CUDA README
OpenVINO	✅	✅	❌	OpenVINO README
CoreML	❌	❌	✅	CoreML README

ℹ️ Only one execution provider package may be referenced.
Mixing providers will cause native runtime conflicts.

⚡ Performance Characteristics

YoloDotNet focuses on stable, low-overhead inference where runtime cost is dominated by the execution provider and model.

📊 Benchmarks: /test/YoloDotNet.Benchmarks

• Stable latency after warm-up
• Clean scaling from CPU → GPU → TensorRT
• Predictable allocation behavior
• Suitable for real-time and long-running services

🚀 Modular Execution Providers

• Core package is provider-agnostic
• Execution providers are separate NuGet packages
• Native ONNX Runtime dependencies are isolated

Why this matters: fewer conflicts, predictable deployment, and production-safe behavior.

Support YoloDotNet

⭐ Star the repo
💬 Share feedback
🤝 Sponsor development

GitHub Sponsors
PayPal

License

© 2023–2025 Niklas Swärd
Licensed under GPL v3.0 or later.

See LICENSE for full details.