Dristro/puretorch
Raw implementation of PyTorch using NumPy. Structured similar to PyTorch, used to create deep learning models without using PyTorch and/or TensorFlow.
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.
Stars
8
Forks
—
Language
Python
License
Apache-2.0
Category
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.
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