Skip to content

Latest commit

 

History

History
24 lines (17 loc) · 757 Bytes

README.md

File metadata and controls

24 lines (17 loc) · 757 Bytes

smalltensor

Inspired by minitorch and tinygrad, smalltensor is a toy implementation of an basic deep learning framework, with Tensor and Autograd engine.

As a learning project, its aims to be simple, readable and build from the ground up with few dependencies.

Install

Require Python version 3.8 or above.

git clone git@github.com:hbhungg/smalltensor.git
cd smalltensor
python3 -m pip install -e .

Examples

Example usage and training can be found at \examples.

TODOs:

  • Package as PyPi.
  • Create our own backend (no longer depend on numpy)! Good exercise.
  • Conv2d.

Welcome PRs and Issues.