# SciSharp/TensorFlow.NET

.NET Standard bindings for Google's TensorFlow for developing, training and deploying Machine Learning models in C# and F#.

Repository: https://github.com/SciSharp/TensorFlow.NET
Canonical: https://ross.abutalabs.com/products/tensorflownet
Homepage: https://scisharp.github.io/tensorflow-net-docs
Language: C#
License: Apache-2.0
License Family: permissive
Topics: tensorflow, machine-learning, scisharp, deep-learning, dotnetcore, chatbot, csharp, keras
Last push: 2025-01-22T15:46:45+00:00

## Health v2 (maintenance only)
Score: 24/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 2, release rhythm 8, longevity 100
- inputs: {"age_days": 2823, "days_push": 588, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3398, forks 539 (observed 2026-08-28T04:08:02.722850+00:00)

## What it is
TensorFlow.NET provides .NET Standard bindings for Google's TensorFlow, aiming to implement the complete TensorFlow API in C# and F#. It includes a built-in Keras high-level interface (TensorFlow.Keras) so .NET developers can develop, train, and deploy machine learning models.

## Use cases
- train machine learning models in C#
- deploy TensorFlow models from .NET applications
- use Keras API in C# or F#
- build deep learning models without leaving the .NET ecosystem
- port Python TensorFlow code to C#
- develop ML models with .NET Standard cross-platform support

## When to choose
- your team works in C#/F# and wants TensorFlow's full API without switching to Python
- you need Keras-style high-level model building in .NET
- you want cross-platform ML development with .NET Standard

## When to avoid
- you need active maintenance and timely bug fixes - maintainers currently lack bandwidth
- you want the latest TensorFlow features - bindings track TensorFlow 2.10 on master
- you prefer PyTorch or Python-first ML tooling

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, sdk
- domain: machine-learning, deep-learning, cross-platform
- platform: dotnet, cross-platform, windows
- tags: tensorflow, keras, csharp, fsharp, net-standard, bindings, scisharp, linux, macos

## Member repositories
- SciSharp/TensorFlow.NET (main) score 24

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:02.722850+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:38:47.103183+00:00, confidence not recorded.
  - readme: https://github.com/SciSharp/TensorFlow.NET (fetched 2026-08-28T04:08:02.722850+00:00, sha ce5053448345)
  - homepage: https://scisharp.github.io/tensorflow-net-docs (fetched 2026-08-29T09:32:45.856635+00:00, sha 9df4195fa0f2)
- Data as of 2026-08-30T08:39:29.467469+00:00.