Wolfram Language Paclet Repository

Community-contributed installable additions to the Wolfram Language

Primary Navigation

    • Cloud & Deployment
    • Core Language & Structure
    • Data Manipulation & Analysis
    • Engineering Data & Computation
    • External Interfaces & Connections
    • Financial Data & Computation
    • Geographic Data & Computation
    • Geometry
    • Graphs & Networks
    • Higher Mathematical Computation
    • Images
    • Knowledge Representation & Natural Language
    • Machine Learning
    • Notebook Documents & Presentation
    • Scientific and Medical Data & Computation
    • Social, Cultural & Linguistic Data
    • Strings & Text
    • Symbolic & Numeric Computation
    • System Operation & Setup
    • Time-Related Computation
    • User Interface Construction
    • Visualization & Graphics
    • Random Paclet
    • Alphabetical List
  • Using Paclets
    • Get Started
    • Download Definition Notebook
  • Learn More about Wolfram Language

TensorNetworks

Guides

  • TensorNetworks

Tech Notes

  • Building Tensor Networks
  • Contraction Paths and Execution
  • Matrix Product States
  • A Working Tour of the Symmetry Functions
  • Tensor Networks Overview
  • Young Tableaux and Tensor Symmetries

Symbols

  • ActivateTensors
  • BinaryTensorNetwork
  • BinaryTensorNetworkQ
  • CanonicalPath
  • CanonicalPathQ
  • ContractIndices
  • ContractionTree
  • EinsteinSummation
  • GreedyContractionPath
  • HookFactor
  • HookLength
  • HookLengths
  • IndexedMultiply
  • InitializeTensorNetwork
  • MetricTensor
  • MetricTensorQ
  • MPSCanonicalForm
  • MPSCanonicalQ
  • MPSEntanglementEntropy
  • MPSNormalize
  • MPSNorm
  • MPSOverlap
  • MPSSchmidtValues
  • MPSTruncate
  • OptimalContractionPath
  • PartitionQ
  • PathIndexContractions
  • PathQ
  • PathToTreePath
  • RandomTensorNetwork
  • SchurDimension
  • SparseTensorNetwork
  • TableauColumns
  • TableauDimension
  • TableauRows
  • TableauShape
  • TableauSize
  • TableauWeylDimension
  • TensorNetworkAdd
  • TensorNetworkContraction
  • TensorNetworkContractions
  • TensorNetworkContract
  • TensorNetworkData
  • TensorNetworkDelete
  • TensorNetworkFreeIndices
  • TensorNetworkGraphData
  • TensorNetworkGraphQ
  • TensorNetworkIndexDimensions
  • TensorNetworkIndexGraph
  • TensorNetworkIndices
  • TensorNetwork
  • TensorNetworkQ
  • TensorNetworkRemoveCycles
  • TensorNetworkReplaceIndices
  • TensorNetworkSize
  • TensorNetworkTensors
  • TensorNetworkToNetGraph
  • ToTensorNetworkGraph
  • TransposePartition
  • TreePathQ
  • TreePathToPath
  • YoungProject
  • YoungSymmetrize
  • YoungTableau
  • YoungTableauQ
Wolfram`TensorNetworks`
TensorNetworkToNetGraph
​
TensorNetworkToNetGraph
[net]
converts the tensor-network graph
net
into a Wolfram Neural
NetGraph
, using
OptimalContractionPath
to choose the contraction order.
​
​
TensorNetworkToNetGraph
[net,path]
uses the explicit contraction
path
.
​
Details and Options
Examples  
(5)
Scope  
(3)
Default path  
(1)
When called with no
path
argument,
TensorNetworkToNetGraph
selects a contraction order via
OptimalContractionPath
:
In[1]:=
SeedRandom[7];g=
ToTensorNetworkGraph

RandomTensorNetwork
["MPS"[4,2,2]];
In[2]:=
TensorNetworkToNetGraph
[g]
Out[3]=
NetGraph
Number of inputs:
0
Outputport:
array(size: 2×2×2×2)

​
Explicit path  
(1)

Symbolic parameters  
(1)

Applications  
(1)

Properties & Relations  
(1)

SeeAlso
ToTensorNetworkGraph
 
▪
TensorNetworkGraphQ
 
▪
TensorNetworkContract
 
▪
OptimalContractionPath
 
▪
NetGraph
 
▪
NetTrain
 
▪
NetExtract
 
▪
NetArrayLayer
 
▪
DotLayer
 
▪
TransposeLayer
TechNotes
▪
Building Tensor Networks
RelatedGuides
▪
TensorNetworks
Convert a small tensor network to a Wolfram Neural
NetGraph
:
In[1]:=
g=
ToTensorNetworkGraph

RandomTensorNetwork
["MPS"[3,2,2]];
In[2]:=
netGraph=
TensorNetworkToNetGraph
[g]
Out[2]=
NetGraph
Number of inputs:
0
Outputport:
array(size: 2×2×2)

​
Evaluating the returned
NetGraph
contracts the tensor network and returns the resulting numeric tensor:
In[3]:=
netGraph=
TensorNetworkToNetGraph
[g];​​netGraph[]
Out[3]=
{{{0.189001,0.252466},{-0.0582617,-0.059773}},{{0.0994449,0.136426},{0.0873661,0.120097}}}
​
The result agrees with
TensorNetworkContract
to single-precision floating-point accuracy:
In[4]:=
netGraph=
TensorNetworkToNetGraph
[g];​​MaxAbsFlattenNnetGraph[]-
TensorNetworkContract
[g]
Out[4]=
1.85725×
-8
10
​
Build the
NetGraph
with an explicit contraction path:
In[5]:=
TensorNetworkToNetGraph
g,
OptimalContractionPath
[g,Method"flops"]
Out[5]=
NetGraph
Number of inputs:
0
Outputport:
array(size: 2×2×2)

""

© 2026 Wolfram. All rights reserved.

  • Legal & Privacy Policy
  • Contact Us
  • WolframAlpha.com
  • WolframCloud.com