nebHailemariam/NebTorch
NebTorch—a minimal Autograd engine built from scratch using NumPy
NebTorch helps deep learning practitioners understand how neural networks learn by providing a foundational automatic differentiation engine. It takes numerical data and a defined neural network model, then processes them through a training loop to output model predictions and performance metrics. This tool is designed for students and researchers exploring the underlying mechanics of deep learning frameworks.
No commits in the last 6 months.
Use this if you are studying deep learning and want to build a neural network from scratch to understand automatic differentiation.
Not ideal if you need a high-performance deep learning framework for production-ready applications or complex models.
Stars
9
Forks
—
Language
Python
License
—
Category
Last pushed
Sep 01, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nebHailemariam/NebTorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pymc-devs/pytensor
PyTensor allows you to define, optimize, and efficiently evaluate mathematical expressions...
arogozhnikov/einops
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
lava-nc/lava-dl
Deep Learning library for Lava
tensorly/tensorly
TensorLy: Tensor Learning in Python.
tensorpack/tensorpack
A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility