WOLFRAM

Wolfram Language & System Documentation Center

ReplicateLayer[n]

represents a net layer that takes an input of dimensions {d1,d2,…} and replicates it n times to produce an output of dimensions {n,d1,d2,…}.

ReplicateLayer[{n1,n2,…,nm}]

represents a net layer that takes an input of dimensions {d1,d2,…} and replicates it to produce an output of dimensions {n1,n2,…,nm,d1,d2,…}.

ReplicateLayer[dims,m]

replicates so that dims appears at position m in the list of output dimensions.

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

ReplicateLayer

ReplicateLayer[n]

represents a net layer that takes an input of dimensions {d1,d2,…} and replicates it n times to produce an output of dimensions {n,d1,d2,…}.

ReplicateLayer[{n1,n2,…,nm}]

represents a net layer that takes an input of dimensions {d1,d2,…} and replicates it to produce an output of dimensions {n1,n2,…,nm,d1,d2,…}.

ReplicateLayer[dims,m]

replicates so that dims appears at position m in the list of output dimensions.

Details and Options

  • ReplicateLayer[n] is equivalent to ReplicateLayer[n,1].
  • For ReplicateLayer[n], the rank of the output array is one larger than the rank of the input array.
  • For ReplicateLayer[{n1,…,nm}], the rank of the output array is m larger than the rank of the input array.
  • Any of the n or ni can have the value Automatic, leaving the exact output dimension to be inferred from its context in NetChain etc.
  • ReplicateLayer[…][input] explicitly computes the output from applying the layer to input.
  • ReplicateLayer[…][{input1,input2,…}] explicitly computes outputs for each of the inputi.
  • When given a NumericArray as input, the output will be a NumericArray.
  • ReplicateLayer exposes the following ports for use in NetGraph etc.:
  • "Input"an array of arbitrary rank
    "Output"an array of greater rank than the input
  • ReplicateLayer is typically used inside NetChain, NetGraph, etc.
  • ReplicateLayer normally infers the dimensions of its input from its context in NetChain etc. To specify the dimensions explicitly as {n1,n2,…}, use ReplicateLayer["Input"->{n1,n2,…}].
  • Options[ReplicateLayer] gives the list of default options to construct the layer. Options[ReplicateLayer[…]] gives the list of default options to evaluate the layer on some data.
  • Information[ReplicateLayer[…]] gives a report about the layer.
  • Information[ReplicateLayer[…],prop] gives the value of the property prop of ReplicateLayer[…]. Possible properties are the same as for NetGraph.

Examples

open all close all

Basic Examples  (2)

Create a ReplicateLayer that replicates its input 4 times:

Wolfram Language code: ReplicateLayer[4]

Create a ReplicateLayer that replicates its input 3 times:

Wolfram Language code: repl = ReplicateLayer[3]

Apply the layer to data:

Wolfram Language code: repl[{1, 2}]

Scope  (6)

Arguments  (2)

Create a ReplicateLayer that replicates its input 3×4 times:

Wolfram Language code: repl = ReplicateLayer[{3, 4}]

Apply the layer to a vector:

Wolfram Language code: repl[{1, 2}]//MatrixForm

Create a ReplicateLayer that replicates the elements of a vector into rows of length 3:

Wolfram Language code: repl = ReplicateLayer[3, 2]

Apply the layer to an input:

Wolfram Language code: repl[{1, 2}]//MatrixForm

The elements can be replicated into columns instead:

Wolfram Language code: repl2 = ReplicateLayer[3, 1]
Wolfram Language code: repl2[{1, 2}]//MatrixForm

Ports  (4)

Create a ReplicateLayer that takes an input of specific size:

Wolfram Language code: repl = ReplicateLayer[3, "Input" -> {2, 2}]

Apply the layer to an input:

Wolfram Language code: repl[{{1, 2}, {3, 4}}]//MatrixForm

Create a NetGraph containing a ReplicateLayer that automatically broadcasts a vector to a matrix of given size:

Wolfram Language code: graph = NetGraph[{AggregationLayer[Mean], ReplicateLayer[Automatic, 2], ThreadingLayer[Plus]}, {1 -> 2 -> 3, NetPort["Input"] -> 3} ]

This NetGraph is now valid for multiple input dimensions:

Wolfram Language code: NetReplacePart[graph, "Input" -> {3, 2}]
Wolfram Language code: NetReplacePart[graph, "Input" -> {100, 23}]

Create a ReplicateLayer that replicates a single number to form a vector:

Wolfram Language code: repl = ReplicateLayer[3, "Input" -> "Real"]

Apply the layer to a number:

Wolfram Language code: repl[2.9]

The layer threads across a batch of inputs:

Wolfram Language code: repl[{2.9, 3.5}]

Create a NetChain that makes four copies of an image by replicating and then flattening both spatial dimensions in turn:

Wolfram Language code: repl = NetChain[{TransposeLayer[1 -> 3], ReplicateLayer[2], FlattenLayer[1], TransposeLayer[2 -> 1], ReplicateLayer[2], FlattenLayer[1], TransposeLayer[{3 -> 1, 2 -> 3}]}, "Input" -> NetEncoder["Image"], "Output" -> NetDecoder["Image"]]
Wolfram Language code: repl[[image]]

Possible Issues  (2)

ReplicateLayer cannot accept non-numeric inputs:

Wolfram Language code: repl = ReplicateLayer[2, "Input" -> 2]; repl[{1, 2}]
Wolfram Language code: repl[{1, "x"}]

ReplicateLayer[dims,pos] will fail when pos is more than one greater than the rank of the input:

Wolfram Language code: repl = ReplicateLayer[{3}, 5, "Input" -> {3, 2, 4}]
Wolfram Research (2017), ReplicateLayer, Wolfram Language function, https://reference.wolfram.com/language/ref/ReplicateLayer.html (updated 2017).

Text

Wolfram Research (2017), ReplicateLayer, Wolfram Language function, https://reference.wolfram.com/language/ref/ReplicateLayer.html (updated 2017).

CMS

Wolfram Language. 2017. "ReplicateLayer." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2017. https://reference.wolfram.com/language/ref/ReplicateLayer.html.

APA

Wolfram Language. (2017). ReplicateLayer. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/ReplicateLayer.html

BibTeX

@misc{reference.wolfram_2026_replicatelayer, author="Wolfram Research", title="{ReplicateLayer}", year="2017", howpublished="\url{https://reference.wolfram.com/language/ref/ReplicateLayer.html}", note=[Accessed: 12-June-2026]}

BibLaTeX

@online{reference.wolfram_2026_replicatelayer, organization={Wolfram Research}, title={ReplicateLayer}, year={2017}, url={https://reference.wolfram.com/language/ref/ReplicateLayer.html}, note=[Accessed: 12-June-2026]}