Skip to main content

A high level tensor network API for accelerated tensor network calculations.

Project description

Build Status

A tensor network wrapper for TensorFlow, JAX, PyTorch, and Numpy.

For an overview of tensor networks please see the following:

More information can be found in our TensorNetwork papers:

Installation

pip3 install tensornetwork

Documentation

For details about the TensorNetwork API, see the reference documentation.

Tutorials

Basic API tutorial

Tensor Networks inside Neural Networks using Keras

Basic Example

Here, we build a simple 2 node contraction.

import numpy as np
import tensornetwork as tn

# Create the nodes
a = tn.Node(np.ones((10,))) 
b = tn.Node(np.ones((10,)))
edge = a[0] ^ b[0] # Equal to tn.connect(a[0], b[0])
final_node = tn.contract(edge)
print(final_node.tensor) # Should print 10.0

Optimized Contractions.

Usually, it is more computationally effective to flatten parallel edges before contracting them in order to avoid trace edges. We have contract_between and contract_parallel that do this automatically for your convenience.

# Contract all of the edges between a and b
# and create a new node `c`.
c = tn.contract_between(a, b)
# This is the same as above, but much shorter.
c = a @ b

# Contract all of edges that are parallel to edge 
# (parallel means connected to the same nodes).
c = tn.contract_parallel(edge)

Split Node

You can split a node by doing a singular value decomposition.

# This will return two nodes and a tensor of the truncation error.
# The two nodes are the unitary matrices multiplied by the square root of the
# singular values.
# The `left_edges` are the edges that will end up on the `u_s` node, and `right_edges`
# will be on the `vh_s` node.
u_s, vh_s, trun_error = tn.split_node(node, left_edges, right_edges)
# If you want the singular values in it's own node, you can use `split_node_full_svd`.
u, s, vh, trun_error = tn.split_node_full_svd(node, left_edges, right_edges)

Node and Edge names.

You can optionally name your nodes/edges. This can be useful for debugging, as all error messages will print the name of the broken edge/node.

node = tn.Node(np.eye(2), name="Identity Matrix")
print("Name of node: {}".format(node.name))
edge = tn.connect(node[0], node[1], name="Trace Edge")
print("Name of the edge: {}".format(edge.name))
# Adding name to a contraction will add the name to the new edge created.
final_result = tn.contract(edge, name="Trace Of Identity")
print("Name of new node after contraction: {}".format(final_result.name))

Named axes.

To make remembering what an axis does easier, you can optionally name a node's axes.

a = tn.Node(np.zeros((2, 2)), axis_names=["alpha", "beta"])
edge = a["beta"] ^ a["alpha"]

Edge reordering.

To assert that your result's axes are in the correct order, you can reorder a node at any time during computation.

a = tn.Node(np.zeros((1, 2, 3)))
e1 = a[0]
e2 = a[1]
e3 = a[2]
a.reorder_edges([e3, e1, e2])
# If you already know the axis values, you can equivalently do
# a.reorder_axes([2, 0, 1])
print(a.tensor.shape) # Should print (3, 1, 2)

NCON interface.

For a more compact specification of a tensor network and its contraction, there is ncon(). For example:

from tensornetwork import ncon
a = np.ones((2, 2))
b = np.ones((2, 2))
c = ncon([a, b], [(-1, 1), (1, -2)])
print(c)

Different backend support.

Currently, we support JAX, TensorFlow, PyTorch and NumPy as TensorNetwork backends. We also support tensors with Abelian symmetries via a symmetric backend, see the reference documentation for more details.

To change the default global backend, you can do:

tn.set_default_backend("jax") # tensorflow, pytorch, numpy, symmetric

Or, if you only want to change the backend for a single Node, you can do:

tn.Node(tensor, backend="jax")

If you want to run your contractions on a GPU, we highly recommend using JAX, as it has the closet API to NumPy.

Disclaimer

This library is in alpha and will be going through a lot of breaking changes. While releases will be stable enough for research, we do not recommend using this in any production environment yet.

TensorNetwork is not an official Google product. Copyright 2019 The TensorNetwork Developers.

Citation

If you are using TensorNetwork for your research please cite this work using the following bibtex entry:

@misc{roberts2019tensornetwork,
      title={TensorNetwork: A Library for Physics and Machine Learning}, 
      author={Chase Roberts and Ashley Milsted and Martin Ganahl and Adam Zalcman and Bruce Fontaine and Yijian Zou and Jack Hidary and Guifre Vidal and Stefan Leichenauer},
      year={2019},
      eprint={1905.01330},
      archivePrefix={arXiv},
      primaryClass={physics.comp-ph}
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

tensornetwork-0.4.6.tar.gz (184.9 kB view details)

Uploaded Source

Built Distribution

tensornetwork-0.4.6-py3-none-any.whl (364.3 kB view details)

Uploaded Python 3

File details

Details for the file tensornetwork-0.4.6.tar.gz.

File metadata

  • Download URL: tensornetwork-0.4.6.tar.gz
  • Upload date:
  • Size: 184.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.8.6

File hashes

Hashes for tensornetwork-0.4.6.tar.gz
Algorithm Hash digest
SHA256 c5af810bf6c2480e1b1f3d98ccf262c5ffb5c3c513be6611f4fdd2258bbc7704
MD5 185b6051b17d7f90cfee33a1da1ba4ec
BLAKE2b-256 933255c2af4e7a6257a55e6598dd199ff3aa3ca567785c67948b2dfeb5019ae7

See more details on using hashes here.

File details

Details for the file tensornetwork-0.4.6-py3-none-any.whl.

File metadata

  • Download URL: tensornetwork-0.4.6-py3-none-any.whl
  • Upload date:
  • Size: 364.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.2 importlib_metadata/4.8.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.8.6

File hashes

Hashes for tensornetwork-0.4.6-py3-none-any.whl
Algorithm Hash digest
SHA256 33f777ea6b9579d010806b3a1ef02f4f9ff5f0707f0ceb681591ee6eb7a01b03
MD5 32814b21ce672b4b68958dec4297fa2b
BLAKE2b-256 628575c4733e9fd7832aac61a6f7d1a473ead56769951344bacf6b4be379254f

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page