eduardoleao052/Autograd-from-scratch
Documented and Unit Tested educational Deep Learning framework with Autograd from scratch.
This project offers a clear, educational deep learning framework, similar to PyTorch, built from scratch. It allows deep learning engineers and students to understand the inner workings of automatic differentiation and neural network layers. You can input raw data, define your model's architecture, and train it, receiving trained models and computed gradients as output.
125 stars. No commits in the last 6 months.
Use this if you are a deep learning engineer or student who wants to learn the foundational mechanics of how deep learning frameworks compute gradients and operate.
Not ideal if you need a high-performance, production-ready deep learning framework with GPU acceleration and extensive pre-built models.
Stars
125
Forks
4
Language
Python
License
MIT
Category
Last pushed
Apr 10, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/eduardoleao052/Autograd-from-scratch"
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