LaurentMazare/ocaml-torch

OCaml bindings for PyTorch

34
/ 100
Emerging

Bindings leverage PyTorch's C++ API with mostly auto-generated stubs to expose tape-based automatic differentiation and GPU-accelerated tensor operations. Includes a vision library with pre-trained ResNet, DenseNet, EfficientNet, and other models, plus examples spanning MNIST classification, neural style transfer, GANs, and stable diffusion implementations. Supports both CPU and CUDA execution through libtorch, with interactive development via utop and ocaml-jupyter.

439 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 15 / 25

How are scores calculated?

Stars

439

Forks

38

Language

OCaml

License

Apache-2.0

Category

minimal-autograd-engines

Last pushed

Oct 17, 2024

Commits (30d)

0

GitHub
Minimal Autograd Engines · 64 frameworks

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/LaurentMazare/ocaml-torch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Higher-rated alternatives

JonathanRaiman/theano_lstm

:microscope: Nano size Theano LSTM module

55

google/tangent

Source-to-Source Debuggable Derivatives in Pure Python

43

pranftw/neograd

A deep learning framework created from scratch with Python and NumPy

40

ahrefs/ocannl

OCANNL: OCaml Compiles Algorithms for Neural Networks Learning

40

yoshoku/numo-openblas

Numo::OpenBLAS builds and uses OpenBLAS as a background library for Numo::Linalg

39

Explore ML Frameworks

All categories Trending ML Framework directory Insights