danielsabinasz/TensorSlow
Re-implementation of TensorFlow in pure python, with an emphasis on code understandability
This project helps software developers understand the foundational concepts behind popular deep learning libraries like TensorFlow. You input Python code that mimics TensorFlow's API for building neural networks and training them, and it outputs a working, albeit simplified, machine learning model. This is for developers or students looking to grasp the 'under the hood' mechanics of deep learning frameworks.
678 stars. No commits in the last 6 months.
Use this if you are a software developer or student who wants to understand how deep learning libraries are implemented from scratch, focusing on the core algorithms and mathematical operations.
Not ideal if you are looking to build efficient or production-ready machine learning models, as this tool prioritizes clarity over performance.
Stars
678
Forks
88
Language
Jupyter Notebook
License
—
Category
Last pushed
Apr 11, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/danielsabinasz/TensorSlow"
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