can-lehmann/exprgrad
An experimental deep learning framework for Nim based on a differentiable array programming language
This is an experimental deep learning framework for the Nim programming language. It simplifies the process of creating and training neural networks by allowing you to define models using a custom differentiable array programming language. You provide your input data and desired output, and the framework helps you build, train, and get predictions from a neural network. It's intended for developers who want to build custom deep learning models and layers in Nim.
121 stars. No commits in the last 6 months.
Use this if you are a Nim developer wanting to build and experiment with custom neural network architectures and layers, and you appreciate automatic gradient computation.
Not ideal if you need a stable, production-ready deep learning framework with extensive community support, multi-threading, or GPU acceleration.
Stars
121
Forks
1
Language
Nim
License
Apache-2.0
Category
Last pushed
Dec 30, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/can-lehmann/exprgrad"
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
google/tangent
Source-to-Source Debuggable Derivatives in Pure Python
ahrefs/ocannl
OCANNL: OCaml Compiles Algorithms for Neural Networks Learning
yoshoku/numo-openblas
Numo::OpenBLAS builds and uses OpenBLAS as a background library for Numo::Linalg
statusfailed/catgrad
a categorical deep learning compiler