tbox98/freegrad

PyTorch extension for alternative backward rules and gradient transforms (STE, gradient jamming, non-standard activations).

/ 100

Experimental

No Package No Dependents

Maintenance 6 / 25

Adoption 0 / 25

Maturity 9 / 25

Community 0 / 25

Stars

—

Forks

—

Language

Python

License

MIT

Category

Last pushed

Nov 30, 2025

Commits (30d)

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tbox98/freegrad"

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

pranftw/neograd

A deep learning framework created from scratch with Python and NumPy

statusfailed/catgrad

a categorical deep learning compiler