Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/tensorly/tensorly
TensorLy: Tensor Learning in Python.
https://github.com/tensorly/tensorly
cupy decomposition jax machine-learning mxnet numpy python pytorch regression tensor tensor-algebra tensor-decomposition tensor-factorization tensor-learning tensor-methods tensor-regression tensorflow tensorly
Last synced: 4 days ago
JSON representation
TensorLy: Tensor Learning in Python.
- Host: GitHub
- URL: https://github.com/tensorly/tensorly
- Owner: tensorly
- License: other
- Created: 2016-10-21T23:14:52.000Z (about 8 years ago)
- Default Branch: main
- Last Pushed: 2024-10-28T16:16:36.000Z (about 2 months ago)
- Last Synced: 2024-10-29T15:46:42.324Z (about 2 months ago)
- Topics: cupy, decomposition, jax, machine-learning, mxnet, numpy, python, pytorch, regression, tensor, tensor-algebra, tensor-decomposition, tensor-factorization, tensor-learning, tensor-methods, tensor-regression, tensorflow, tensorly
- Language: Python
- Homepage: http://tensorly.org
- Size: 16 MB
- Stars: 1,553
- Watchers: 45
- Forks: 289
- Open Issues: 60
-
Metadata Files:
- Readme: README.rst
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.rst
- License: LICENSE.txt
- Citation: CITATION.cff
- Authors: AUTHORS.rst
Awesome Lists containing this project
- Awesome-MXNet - tensorly
- awesome-list - TensorLy - A Python library that aims at making tensor learning simple and accessible. (Linear Algebra / Statistics Toolkit / General Purpose Tensor Library)
- awesome-jax - TensorLy - Tensor learning made simple. <img src="https://img.shields.io/github/stars/tensorly/tensorly?style=social" align="center"> (Libraries)
- StarryDivineSky - tensorly/tensorly
README
.. image:: https://badge.fury.io/py/tensorly.svg
:target: https://badge.fury.io/py/tensorly
.. image:: https://anaconda.org/tensorly/tensorly/badges/version.svg
:target: https://anaconda.org/tensorly/tensorly
.. image:: https://github.com/tensorly/tensorly/actions/workflows/test.yml/badge.svg?branch=main
:target: https://github.com/tensorly/tensorly/actions/workflows/test.yml
.. image:: https://codecov.io/gh/tensorly/tensorly/branch/master/graph/badge.svg?token=mnZ234sGSA
:target: https://codecov.io/gh/tensorly/tensorly
.. image:: https://img.shields.io/badge/Slack-join-brightgreen
:target: https://join.slack.com/t/tensorly/shared_invite/zt-wqnts2sk-wbiRX6ml~Xt6~GDYWRPFfg
========
TensorLy
========
TensorLy is a Python library that aims at making tensor learning simple and accessible. It allows to easily perform tensor decomposition, tensor learning and tensor algebra. Its backend system allows to seamlessly perform computation with NumPy, PyTorch, JAX, TensorFlow, CuPy or Paddle, and run methods at scale on CPU or GPU.
- **Website:** https://tensorly.org
- **Source-code:** https://github.com/tensorly/tensorly
- **Jupyter Notebooks:** https://github.com/JeanKossaifi/tensorly-notebooks
----------------------------
Installing TensorLy
===================
The only pre-requisite is to have **Python 3** installed. The easiest way is via the `Anaconda distribution `_.
+-------------------------------------------+---------------------------------------------------+
| **With pip** (recommended) | **With conda** |
+-------------------------------------------+---------------------------------------------------+
| | |
| .. code:: | .. code:: |
| | |
| pip install -U tensorly | conda install -c tensorly tensorly |
| | |
| | |
+-------------------------------------------+---------------------------------------------------+
| **Development (from git)** |
+-------------------------------------------+---------------------------------------------------+
| |
| .. code:: |
| |
| # clone the repository |
| git clone https://github.com/tensorly/tensorly |
| cd tensorly |
| # Install in editable mode with `-e` or, equivalently, `--editable` |
| pip install -e . |
| |
+-----------------------------------------------------------------------------------------------+
**Note:** TensorLy depends on NumPy by default. If you want to use other backends, you will need to install these packages separately.
For detailed instruction, please see the `documentation `_.
------------------
Quickstart
==========
Creating tensors
----------------
Create a small third order tensor of size 3 x 4 x 2, from a NumPy array and perform simple operations on it:
.. code:: python
import tensorly as tl
import numpy as np
tensor = tl.tensor(np.arange(24).reshape((3, 4, 2)), dtype=tl.float64)
unfolded = tl.unfold(tensor, mode=0)
tl.fold(unfolded, mode=0, shape=tensor.shape)
You can also create random tensors:
.. code:: python
from tensorly import random
# A random tensor
tensor = random.random_tensor((3, 4, 2))
# A random CP tensor in factorized form
cp_tensor = random.random_tensor(shape=(3, 4, 2), rank='same')
You can also create tensors in TT-format, Tucker, etc, see `random tensors `_.
Setting the backend
-------------------
You can change the backend to perform computation with a different framework. By default, the backend is NumPy, but you can also perform the computation using PyTorch, TensorFlow, JAX, CuPy or Paddle (requires to have installed them first). For instance, after setting the backend to PyTorch, all the computation is done by PyTorch, and tensors can be created on GPU:
.. code:: python
tl.set_backend('pytorch') # Or 'numpy', 'tensorflow', 'cupy' or 'jax'
tensor = tl.tensor(np.arange(24).reshape((3, 4, 2)), device='cuda:0')
type(tensor) # torch.Tensor
Tensor decomposition
--------------------
Applying tensor decomposition is easy:
.. code:: python
from tensorly.decomposition import tucker
# Apply Tucker decomposition
tucker_tensor = tucker(tensor, rank=[2, 2, 2])
# Reconstruct the full tensor from the decomposed form
tl.tucker_to_tensor(tucker_tensor)
We have `many more decompositions `_ available, be sure to check them out!
Next steps
----------
This is just a very quick introduction to some of the basic features of TensorLy.
For more information on getting started, checkout the `user-guide `_ and for a detailed reference of the functions and their documentation, refer to
the `API `_
If you see a bug, open an `issue `_, or better yet, a `pull-request `_!
--------------------------
Contributing code
=================
All contributions are welcome! So if you have a cool tensor method you want to add, if you spot a bug or even a typo or mistake in the documentation, please report it, and even better, open a Pull-Request on `GitHub `_.
Before you submit your changes, you should make sure your code adheres to our style-guide. The easiest way to do this is with `black`:
.. code:: bash
pip install black
black .
Running the tests
=================
Testing and documentation are an essential part of this package and all functions come with uni-tests and documentation.
The tests are ran using the `pytest` package.
First install `pytest`::
pip install pytest
Then to run the test, simply run, in the terminal:
.. code::
pytest -v tensorly
Alternatively, you can specify for which backend you wish to run the tests:
.. code::
TENSORLY_BACKEND='numpy' pytest -v tensorly
------------------
Citing
======
If you use TensorLy in an academic paper, please cite [1]_::
@article{tensorly,
author = {Jean Kossaifi and Yannis Panagakis and Anima Anandkumar and Maja Pantic},
title = {TensorLy: Tensor Learning in Python},
journal = {Journal of Machine Learning Research},
year = {2019},
volume = {20},
number = {26},
pages = {1-6},
url = {http://jmlr.org/papers/v20/18-277.html}
}
.. [1] Jean Kossaifi, Yannis Panagakis, Anima Anandkumar and Maja Pantic, **TensorLy: Tensor Learning in Python**, *Journal of Machine Learning Research (JMLR)*, 2019, volume 20, number 26.