can-lehmann/exprgrad

An experimental deep learning framework for Nim based on a differentiable array programming language

28
/ 100
Experimental

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.

deep-learning neural-networks custom-models machine-learning-development Nim-programming
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 2 / 25

How are scores calculated?

Stars

121

Forks

1

Language

Nim

License

Apache-2.0

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.