Download
When to use TensorFlowSharp is a .NET binding for the TensorFlow machine learning framework that allows developers to run TensorFlow models directly from C# and other .NET languages. The project exposes TensorFlow’s native C API through a strongly typed interface designed to integrate naturally with the .NET ecosystem. Its primary purpose is to enable developers working in Microsoft-based environments to load trained TensorFlow models and perform inference or additional training within .NET applications. The library focuses mainly on providing access to the low-level TensorFlow runtime rather than offering the high-level abstractions commonly available in Python libraries like Keras. This design allows applications written in C# or F# to execute machine learning graphs produced by Python workflows while maintaining compatibility with the TensorFlow runtime.
Features
- .NET bindings that expose the TensorFlow C API to C# and F#
- Ability to load and execute trained TensorFlow models inside .NET applications
- Integration with the .NET ecosystem using familiar naming conventions
- Compatibility with models trained in Python frameworks such as TensorFlow or Keras
- NuGet package distribution including required native runtime libraries
- Low-level access to TensorFlow operations and computational graphs
Project Samples
