Shrimp-AI/shrimpgrad
Yet another tensor library
This is a minimalist tensor library designed for deep learning engineers. It takes in numerical data as tensors and helps you build, train, and run neural networks. The library outputs trained models and predictions for various deep learning tasks. It is ideal for those who want a fine-grained understanding of their deep learning computations.
No commits in the last 6 months.
Use this if you are a deep learning engineer looking for a lightweight, performant, and transparent framework to build and experiment with neural network architectures.
Not ideal if you are a data scientist or machine learning practitioner looking for a high-level API for off-the-shelf model training without diving into computation graph details.
Stars
11
Forks
—
Language
Python
License
GPL-3.0
Category
Last pushed
Nov 15, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Shrimp-AI/shrimpgrad"
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