DACUS1995/gradflow
A small, educational autograd system with deep neural networks support
This is an educational toolkit designed for developers to understand the fundamentals of deep neural networks. It takes raw numerical data and model definitions as input, allowing you to train simple neural networks and produce predictions. It's best suited for someone who wants to learn the mechanics of deep learning frameworks by building models from the ground up.
No commits in the last 6 months.
Use this if you are a developer or student interested in how deep learning frameworks compute gradients and train models at a fundamental level.
Not ideal if you need a robust, high-performance deep learning framework for production-grade applications or complex research.
Stars
13
Forks
3
Language
Python
License
MIT
Category
Last pushed
Apr 29, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/DACUS1995/gradflow"
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