WOLFRAM

Wolfram Language & System Documentation Center

NetArrayLayer[]

represents a layer that has no input and produces as output a constant array.

NetArrayLayer[opts]

includes options for the initial value of the array or output size.

Details and Options
Details and Options Details and Options
Examples  
Basic Examples  
Scope  
Arguments  
Ports  
Parameters  
"Array"  
Possible Issues  
See Also
Tech Notes
Related Guides
History
Cite this Page

NetArrayLayer

NetArrayLayer[]

represents a layer that has no input and produces as output a constant array.

NetArrayLayer[opts]

includes options for the initial value of the array or output size.

Details and Options

  • NetArrayLayer is typically used in a NetGraph and allows a learned array to be used as an ordinary input to other layers. Without NetArrayLayer, all layer inputs must ultimately be derived from inputs to the entire net.
  • The array stored by NetArrayLayer will be learned during training.
  • The constant array stored in NetArrayLayer has the same dimensions as the output of NetArrayLayer.
  • NetArrayLayer["Array"->array] can be used to give an explicit value of the constant array.
  • When the constant array is not explicitly specified or is given as Automatic, it is added automatically when NetInitialize or NetTrain is used.
  • NetArrayLayer["Output"->{d1,d2,…}] can be used to fix the output size of the layer, which also fixes the size of the constant array.
  • The following training parameter can also be included:
  • LearningRateMultipliersAutomaticlearning rate multipliers for the array
  • NetArrayLayer[…][] returns the constant array.
  • The constant array can also be obtained from an initialized NetArrayLayer using NetExtract[layer,"Array"].
  • Options[NetArrayLayer] gives the list of default options to construct the layer. Options[NetArrayLayer[…]] gives the list of default options to evaluate the layer on some data.
  • Information[NetArrayLayer[…]] gives a report about the layer.
  • Information[NetArrayLayer[…],prop] gives the value of the property prop of NetArrayLayer[…]. Possible properties are the same as for NetGraph.

Examples

open all close all

Basic Examples  (2)

Create a NetArrayLayer:

Wolfram Language code: NetArrayLayer[]

Create an initialized NetArrayLayer with output dimensions specified:

Wolfram Language code: layer = NetInitialize@NetArrayLayer["Output" -> 3]

Extract the initialized array:

Wolfram Language code: NetExtract[layer, "Array"]

Scope  (7)

Arguments  (4)

Create a NetArrayLayer with unspecified output size:

Wolfram Language code: NetArrayLayer[]

Create a NetArrayLayer with output dimensions specified:

Wolfram Language code: NetArrayLayer[3]

Define a higher-dimensional output:

Wolfram Language code: NetArrayLayer[{3, 4}]

Specify only some output sizes:

Wolfram Language code: NetArrayLayer[{3, Automatic, Automatic, 4}]

Ports  (1)

Provide the output sizes directly as an "Output" port specification:

Wolfram Language code: NetArrayLayer["Output" -> {3, Automatic, Automatic}]

Parameters  (2)

"Array"  (2)

Create a NetArrayLayer with a specific initial value for the array:

Wolfram Language code: layer = NetArrayLayer["Array" -> {1, 2, 3}]

Use the array in an elementwise operation in a NetGraph:

Wolfram Language code: graph = NetGraph[{layer, ThreadingLayer[#1 ^ #2&]}, {{NetPort["Input"], 1} -> 2}]

Evaluate the graph:

Wolfram Language code: graph[{1, 2, 3}]

Create a NetArrayLayer with fixed output array that is not changing during the training:

Wolfram Language code: NetArrayLayer["Array" -> {2, 3, 4}, LearningRateMultipliers -> 0]

Possible Issues  (3)

NetArrayLayer does not accept symbolic arrays:

Wolfram Language code: NetArrayLayer["Array" -> {z, 2}]

Dimensions of "Array" specification should be consistent with dims specification:

Wolfram Language code: NetArrayLayer[3, "Array" -> {.1, .2}]
Wolfram Language code: NetArrayLayer[3, "Array" -> {.1, .2, .3}]

"Output" dimensions need to be fully specified in order to use NetInitialize:

Wolfram Language code: NetInitialize@NetArrayLayer["Output" -> {3, Automatic}]
Wolfram Language code: NetInitialize@NetArrayLayer["Output" -> {3, 2}]
Wolfram Research (2020), NetArrayLayer, Wolfram Language function, https://reference.wolfram.com/language/ref/NetArrayLayer.html.

Text

Wolfram Research (2020), NetArrayLayer, Wolfram Language function, https://reference.wolfram.com/language/ref/NetArrayLayer.html.

CMS

Wolfram Language. 2020. "NetArrayLayer." Wolfram Language & System Documentation Center. Wolfram Research. https://reference.wolfram.com/language/ref/NetArrayLayer.html.

APA

Wolfram Language. (2020). NetArrayLayer. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/NetArrayLayer.html

BibTeX

@misc{reference.wolfram_2026_netarraylayer, author="Wolfram Research", title="{NetArrayLayer}", year="2020", howpublished="\url{https://reference.wolfram.com/language/ref/NetArrayLayer.html}", note=[Accessed: 15-June-2026]}

BibLaTeX

@online{reference.wolfram_2026_netarraylayer, organization={Wolfram Research}, title={NetArrayLayer}, year={2020}, url={https://reference.wolfram.com/language/ref/NetArrayLayer.html}, note=[Accessed: 15-June-2026]}