OnnxStack.Core 0.23.0

The ID prefix of this package has been reserved for one of the owners of this package by NuGet.org. Prefix Reserved
dotnet add package OnnxStack.Core --version 0.23.0
NuGet\Install-Package OnnxStack.Core -Version 0.23.0
This command is intended to be used within the Package Manager Console in Visual Studio, as it uses the NuGet module's version of Install-Package.
<PackageReference Include="OnnxStack.Core" Version="0.23.0" />
For projects that support PackageReference, copy this XML node into the project file to reference the package.
paket add OnnxStack.Core --version 0.23.0
#r "nuget: OnnxStack.Core, 0.23.0"
#r directive can be used in F# Interactive and Polyglot Notebooks. Copy this into the interactive tool or source code of the script to reference the package.
// Install OnnxStack.Core as a Cake Addin
#addin nuget:?package=OnnxStack.Core&version=0.23.0

// Install OnnxStack.Core as a Cake Tool
#tool nuget:?package=OnnxStack.Core&version=0.23.0

OnnxStack.Core - Onnx Services for .NET Applications

OnnxStack.Core is a library that provides higher-level ONNX services for use in .NET applications. It offers extensive support for features such as dependency injection, .NET configuration implementations, ASP.NET Core integration, and IHostedService support.

You can configure a model set for runtime, offloading individual models to different devices to make better use of resources or run on lower-end hardware. The first use-case is StableDiffusion; however, it will be expanded, and other model sets, such as object detection and classification, will be added.

Getting Started

OnnxStack.Core can be found via the nuget package manager, download and install it.

PM> Install-Package OnnxStack.Core

.NET Core Registration

You can easily integrate OnnxStack.Core into your application services layer. This registration process sets up the necessary services and loads the appsettings.json configuration.

Example: Registering OnnxStack

builder.Services.AddOnnxStack();

Dependencies

Video processing support requires FFMPEG and FFPROBE binaries, files must be present in your output folder or the destinations configured in the appsettings.json

https://ffbinaries.com/downloads
https://github.com/ffbinaries/ffbinaries-prebuilt/releases/download/v6.1/ffmpeg-6.1-win-64.zip
https://github.com/ffbinaries/ffbinaries-prebuilt/releases/download/v6.1/ffprobe-6.1-win-64.zip

Configuration example

The appsettings.json is the easiest option for configuring model sets. Below is an example of clip tokenizer.

{
	"Logging": {
		"LogLevel": {
			"Default": "Information",
			"Microsoft.AspNetCore": "Warning"
		}
	},
	"AllowedHosts": "*",

	"OnnxStackConfig": {
		"OnnxModelSets": [
			{
				"Name": "ClipTokenizer",
				"IsEnabled": true,
				"DeviceId": 0,
				"InterOpNumThreads": 0,
				"IntraOpNumThreads": 0,
				"ExecutionMode": "ORT_SEQUENTIAL",
				"ExecutionProvider": "DirectML",
				"ModelConfigurations": [
					{
						"Type": "Tokenizer",
						"OnnxModelPath": "cliptokenizer.onnx"
					},
				]
			}
		]
	}
}

Basic C# Example


// Tokenizer model Example
//----------------------//

// From DI
OnnxStackConfig _onnxStackConfig;
IOnnxModelService _onnxModelService;

// Get Model
var model = _onnxStackConfig.OnnxModelSets.First();

// Get Model Metadata
var metadata = _onnxModelService.GetModelMetadata(model, OnnxModelType.Tokenizer);

// Create Input
var text = "Text To Tokenize";
var inputTensor = new DenseTensor<string>(new string[] { text }, new int[] { 1 });

// Create  Inference Parameters container
using (var inferenceParameters = new OnnxInferenceParameters(metadata))
{
	// Set Inputs and Outputs
	inferenceParameters.AddInputTensor(inputTensor);
	inferenceParameters.AddOutputBuffer();

	// Run Inference
	using (var results = _onnxModelService.RunInference(model, OnnxModelType.Tokenizer, inferenceParameters))
	{
		// Extract Result
		var resultData = results[0].ToDenseTensor();
	}
}

Product Compatible and additional computed target framework versions.
.NET net7.0 is compatible.  net7.0-android was computed.  net7.0-ios was computed.  net7.0-maccatalyst was computed.  net7.0-macos was computed.  net7.0-tvos was computed.  net7.0-windows was computed.  net8.0 was computed.  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. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

NuGet packages (3)

Showing the top 3 NuGet packages that depend on OnnxStack.Core:

Package Downloads
OnnxStack.StableDiffusion The ID prefix of this package has been reserved for one of the owners of this package by NuGet.org.

Stable Diffusion Integration Library for .NET Core This repository harnesses the capabilities of both ONNX Runtime and Microsoft ML, offering a comprehensive solution that empowers developers to build, deploy, and execute machine learning models seamlessly in .NET environments, unlocking a world of possibilities for intelligent applications.

OnnxStack.ImageUpscaler The ID prefix of this package has been reserved for one of the owners of this package by NuGet.org.

OnnxRuntime Image Upscale Library for .NET Core

OnnxStack.FeatureExtractor The ID prefix of this package has been reserved for one of the owners of this package by NuGet.org.

OnnxRuntime Image Feature Extractor Library for .NET Core

GitHub repositories (1)

Showing the top 1 popular GitHub repositories that depend on OnnxStack.Core:

Repository Stars
saddam213/OnnxStack
C# Stable Diffusion using ONNX Runtime
Version Downloads Last updated
0.23.0 54 2/29/2024
0.22.0 109 2/23/2024
0.21.0 121 2/15/2024
0.19.0 135 2/1/2024
0.17.0 157 1/18/2024
0.16.0 112 1/11/2024
0.15.0 169 1/5/2024
0.14.0 112 12/27/2023
0.13.0 117 12/22/2023
0.12.0 122 12/15/2023
0.10.0 153 11/30/2023
0.9.0 126 11/23/2023
0.8.0 172 11/16/2023
0.7.0 127 11/9/2023
0.6.0 105 11/2/2023
0.5.0 117 10/27/2023
0.4.0 101 10/19/2023
0.3.1 122 10/9/2023
0.3.0 99 10/9/2023
0.2.0 103 10/3/2023
0.1.0 143 9/25/2023