YoloDotNet.ExecutionProvider.CoreML
1.1.0
dotnet add package YoloDotNet.ExecutionProvider.CoreML --version 1.1.0
NuGet\Install-Package YoloDotNet.ExecutionProvider.CoreML -Version 1.1.0
<PackageReference Include="YoloDotNet.ExecutionProvider.CoreML" Version="1.1.0" />
<PackageVersion Include="YoloDotNet.ExecutionProvider.CoreML" Version="1.1.0" />
<PackageReference Include="YoloDotNet.ExecutionProvider.CoreML" />
paket add YoloDotNet.ExecutionProvider.CoreML --version 1.1.0
#r "nuget: YoloDotNet.ExecutionProvider.CoreML, 1.1.0"
#:package YoloDotNet.ExecutionProvider.CoreML@1.1.0
#addin nuget:?package=YoloDotNet.ExecutionProvider.CoreML&version=1.1.0
#tool nuget:?package=YoloDotNet.ExecutionProvider.CoreML&version=1.1.0
Information
YoloDotNet uses modular execution providers to run inference on different hardware backends. Each provider targets a specific platform or accelerator and may require additional system-level dependencies such as runtimes, drivers, or SDKs.
Installing the NuGet package alone is not always sufficient — proper setup depends on the selected provider and the target system.
This document describes the installation and usage of the CoreML execution provider.
Core Library Requirement
All execution providers require the core YoloDotNet package.
NuGet Package
dotnet add package YoloDotNet
Execution Provider - CoreML
The CoreML execution provider enables hardware-accelerated inference on Apple devices using Apple’s Core ML framework.
It automatically leverages Apple Silicon accelerators such as the Neural Engine, GPU, or CPU depending on device capabilities.
⚠️ Note
CoreML is only available on Apple platforms and is supported on macOS 10.15 or later.
Requirements
- macOS 10.15 or later
Installation
No additional installation or configuration is required.
CoreML is included with macOS and is automatically available at runtime on supported devices.
YoloDotNet.ExecutionProvider.CoreML v1.1 requires YoloDotNet version 4.1.
NuGet Package
dotnet add package YoloDotNet.ExecutionProvider.CoreML
Usage Example:
using YoloDotNet;
using YoloDotNet.ExecutionProvider.CoreML;
using var yolo = new Yolo(new YoloOptions
{
ExecutionProvider = new CoreMLExecutionProvider(
model: "path/to/model.onnx",
// Automatically selects the best available CoreML compute units
// (Neural Engine, GPU, or CPU)
adaptive: true
),
// ...other options
});
| Product | Versions Compatible and additional computed target framework versions. |
|---|---|
| .NET | net8.0 is compatible. net8.0-android was computed. net8.0-browser was computed. net8.0-ios was computed. net8.0-maccatalyst was computed. net8.0-macos was computed. net8.0-tvos was computed. net8.0-windows was computed. net9.0 was computed. net9.0-android was computed. net9.0-browser was computed. net9.0-ios was computed. net9.0-maccatalyst was computed. net9.0-macos was computed. net9.0-tvos was computed. net9.0-windows was computed. net10.0 was computed. net10.0-android was computed. net10.0-browser was computed. net10.0-ios was computed. net10.0-maccatalyst was computed. net10.0-macos was computed. net10.0-tvos was computed. net10.0-windows was computed. |
-
net8.0
- Microsoft.ML.OnnxRuntime (>= 1.23.0)
- YoloDotNet (>= 4.0.0)
NuGet packages
This package is not used by any NuGet packages.
GitHub repositories
This package is not used by any popular GitHub repositories.
This release updates the internal execution provider architecture to align with YoloDotNet v4.1. Model parsing and validation are now handled exclusively by the YoloDotNet core library, simplifying execution provider implementations and ensuring consistent model handling across all backends. This execution provider requires YoloDotNet version 4.1.