dfx 

dfx, a tensor library for F# with support for differentiable programming, with the LibTorch CPU binaries for Windows (x64), Linux (x64) and macOS (Apple Silicon).

dfx, a tensor library for F# with support for differentiable programming, with the LibTorch CUDA 12.8 binaries for both Windows (x64) and Linux (x64). Large download.

dfx, a tensor library for F# with support for differentiable programming, without LibTorch binaries, for use with a LibTorch installed by other means, for example with PyTorch.

dfx, a tensor library for F# with support for differentiable programming, with the LibTorch CUDA 12.8 binaries for Linux (x64). Large download.

dfx, a tensor library for F# with support for differentiable programming, with the LibTorch CUDA 12.8 binaries for Windows (x64). Large download.

The core dfx library: tensors, forward, reverse and nested automatic differentiation, models, optimizers and probability distributions. Most applications should reference a package that includes the LibTorch... More information

The Torch backend for dfx, using LibTorch through TorchSharp. It does not include the LibTorch binaries. Most applications should reference a package that includes the LibTorch binaries, such as dfx-cpu,... More information

Datasets, data loaders, image and plotting utilities for dfx. Most applications should reference a package that includes the LibTorch binaries, such as dfx-cpu, instead.

The Reference backend for dfx, implemented in F#. It runs anywhere .NET runs and suits small tensors and testing. Most applications should reference a package that includes the LibTorch binaries, such as... More information