OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Infer.NET

Infer.NET is a C# framework for probabilistic programming and Bayesian inference in graphical models, with packages for inference execution, model compilation and machine-learning learners.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Infer.NET — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Consider Infer.NET when a .NET application needs probabilistic modeling and Bayesian inference, especially for classification, recommendation, clustering or a customized machine-learning task.

Who it is for

  • C# and .NET developers building machine-learning applications.
  • Developers who need to express probabilistic models, use Bayesian inference, or adapt models to domain-specific problems.

Documented uses

  • Build classification applications using Bayesian inference.
  • Create recommendation systems with probabilistic models.
  • Develop clustering solutions.
  • Translate Infer.NET API model descriptions into inference code.
  • Create custom models for tasks such as inferring document relevance from click sequences.
Before you choose

Requirements & limits

The repository identifies the project as MIT-licensed. Pre-built binaries are distributed through NuGet.

  • The documented core packages target .NET Standard 2.0 and can be used from projects targeting .NET Framework 4.6.2 or .NET Core 3.1.
  • The Compiler package generates inference code from model descriptions written with the Infer.NET API.
  • The Learners package includes a classifier and recommender system.
  • The Windows visualizers are a separate package and are specific to .NET Framework and Windows.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Add Infer.NET packages to a .NET project

Reference the documented Infer.NET core, compiler and learner packages in an existing project.

Before you start

  • An existing .NET project file.
  • .NET Core 3.1 command-line tools, as specified in the repository instructions.

Steps

  1. Add a reference to Microsoft.ML.Probabilistic.

  2. Add a reference to Microsoft.ML.Probabilistic.Compiler.

  3. Add a reference to Microsoft.ML.Probabilistic.Learners.

Expected outcome

The project file contains references to the core inference library, compiler and learner package; NuGet downloads the binaries when the project is compiled.

Guide limitations

  • These steps add package references; they do not describe implementing or running a particular model.
  • The Windows-specific visualization package is separate and is not included in these steps.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Model inference and serving

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Infer.NETBuild classification applications using Bayesian inference.The repository identifies the project as MIT-licensed. Pre-built binaries are distributed through NuGet.
HyperposeCustomize pose-estimation architectures and datasets.Docker, Linux, macOS, Windows
Multi Task NlpDefine multiple tasks and their data and model settings in a YAML file.Linux, macOS, WindowsThe project is an open-source library under the Apache-2.0 license, distributed through its public GitHub repository.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
dotnet/infer · Official homepage title · retained in its source language
How we review sourcesSuggest a correction