arogozhnikov/einops
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
This tool helps machine learning engineers and researchers manage complex data structures efficiently. It takes in multi-dimensional data arrays (tensors) and allows you to intuitively reshape, combine, or extract information from them using a clear, descriptive notation. The output is your data transformed precisely as needed for your machine learning models.
9,425 stars. Used by 211 other packages. Actively maintained with 1 commit in the last 30 days. Available on PyPI.
Use this if you frequently manipulate multi-dimensional data in deep learning, need to make your tensor operations more readable, or want to reduce errors in reshaping and transposing data.
Not ideal if your work doesn't involve multi-dimensional array operations or you're not a developer working with machine learning frameworks.
Stars
9,425
Forks
396
Language
Python
License
MIT
Category
Last pushed
Feb 20, 2026
Commits (30d)
1
Reverse dependents
211
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/arogozhnikov/einops"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
pymc-devs/pytensor
PyTensor allows you to define, optimize, and efficiently evaluate mathematical expressions...
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
tensorlayer/TensorLayerX
TensorLayerX: A Unified Deep Learning and Reinforcement Learning Framework for All Hardwares,...