Dristro/puretorch

Raw implementation of PyTorch using NumPy. Structured similar to PyTorch, used to create deep learning models without using PyTorch and/or TensorFlow.

39
/ 100
Emerging

PureTorch is a library for developers who want to build deep learning models without relying on established frameworks like PyTorch or TensorFlow. It takes numerical data as input and produces neural network models, offering a transparent, educational approach. This is intended for developers learning or experimenting with deep learning's inner workings.

Available on PyPI.

Use this if you are a developer seeking to understand the foundational mechanics of deep learning by building models from scratch using only NumPy, replicating PyTorch's structure.

Not ideal if you are a developer looking for a production-ready deep learning framework with extensive features, GPU support, and a large ecosystem.

deep-learning-development neural-network-implementation numerical-computation machine-learning-engineering
Maintenance 10 / 25
Adoption 4 / 25
Maturity 25 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Python

License

Apache-2.0

Last pushed

Feb 10, 2026

Commits (30d)

0

Dependencies

2

Get this data via API

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

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.