WOLFRAM

Wolfram Language & System Documentation Center
Wolfram Language Home Page »

ExtractLayer
✖
ExtractLayer

[Experimental]

✖

represents a net layer that takes an array and a position specification as inputs and extracts the specified parts from the array.

Details and Options

  • ExtractLayer exposes the following ports for use in NetGraph etc.:
  • "Input"input array
    "Position"integer array of part specifications
    "Output"output array
  • ExtractLayer is typically used inside NetChain, NetGraph, etc.
  • ExtractLayer normally infers the dimensions of its input from its context in NetChain etc. To specify the dimensions explicitly as {n1,n2,…} and {m1,m2,…}, use ExtractLayer["Input"->{n1,n2,…},"Position"->{m1,m2,…}].
  • ExtractLayer["Port"shape] allows the shape of the "Input" or "Position" port to be specified. Possible forms of shape are:
  • na vector of length n
    {n1,n2,…}an array of dimensions n1×n2×…
    {"Varying",n2,n3,…}an array whose first dimension is variable and whose remaining dimensions are n2×n3×…
    NetEncoder[…]an encoder
  • The shape of the "Position" port can also be set to "Integer" to specify a single integer.
  • The input to the port "Position" is an arbitrary array of part specifications. Given an input of dimensions {n1,n2,…,nd } and a position specification of dimensions {m1,m2,…,mp,s}, the output will have dimensions {m1,m2,…,mp,ns+1,…,nd}.
  • The last dimension of the position specification s is used to specify elements of the input, and so it cannot be greater than the input rank d. In the case of s=d, the output dimensions will just be {m1,m2,…,mp}.
  • ExtractLayer[…][<|"Input"input,"Position"position|>] explicitly computes the output from applying the layer to input and position.
  • ExtractLayer[…][<|"Input"{input1,input2,…},"Input"{pos1,pos2,…}|> explicitly computes output for each of the inputi and the posi.
  • Negative integers in the position specification are counted from the last element progressing backward.
  • When given a NumericArray as input, the output will be a NumericArray.
  • Options[ExtractLayer] gives the list of default options to construct the layer. Options[ExtractLayer[…]] gives the list of default options to evaluate the layer on some data.
  • Information[ExtractLayer[…]] gives a report about the layer.
  • Information[ExtractLayer[…],prop] gives the value of the property prop of ExtractLayer[…]. Possible properties are the same as for NetGraph.

Examples

open allclose all

Basic Examples  (1)Summary of the most common use cases

Create an ExtractLayer:

In[1]:=1
✖
https://wolfram.com/xid/0mk946n73e6q-bue9j6
Out[1]=1

Apply the layer to a vector and a part specification:

In[2]:=2
✖
https://wolfram.com/xid/0mk946n73e6q-dn4mx9
Out[2]=2

Scope  (2)Survey of the scope of standard use cases

Arguments  (1)

Create an ExtractLayer:

In[1]:=1
✖
https://wolfram.com/xid/0mk946n73e6q-8hhuo1
Out[1]=1

Specify a list of parts:

In[2]:=2
✖
https://wolfram.com/xid/0mk946n73e6q-mxmszv
Out[2]=2
In[3]:=3
✖
https://wolfram.com/xid/0mk946n73e6q-nmgand
Out[3]=3

Ports  (1)

Create an ExtractLayer and specify the shape of its "Input" and "Position" ports:

In[1]:=1
✖
https://wolfram.com/xid/0mk946n73e6q-td64i9
Out[1]=1

Apply the layer to an input-position pair:

In[2]:=2
✖
https://wolfram.com/xid/0mk946n73e6q-wqvf4b
Out[2]=2

Apply the layer to a batch of input-position pairs:

In[3]:=3
✖
https://wolfram.com/xid/0mk946n73e6q-oaiwaz
Out[3]=3

Properties & Relations  (2)Properties of the function, and connections to other functions

ExtractLayer performs the same computation as Extract:

In[1]:=1
✖
https://wolfram.com/xid/0mk946n73e6q-jdfgmt
In[2]:=2
✖
https://wolfram.com/xid/0mk946n73e6q-ssqozk
In[3]:=3
✖
https://wolfram.com/xid/0mk946n73e6q-6zir0r
Out[3]=3
In[4]:=4
✖
https://wolfram.com/xid/0mk946n73e6q-ldtqg2
Out[4]=4

ExtractLayer selects parts of an array based on the current specification, while PartLayer has a fixed-part specification:

In[1]:=1
✖
https://wolfram.com/xid/0mk946n73e6q-z1xb8e
In[2]:=2
✖
https://wolfram.com/xid/0mk946n73e6q-7npalv
In[3]:=3
✖
https://wolfram.com/xid/0mk946n73e6q-tkyfzp
Out[3]=3
In[4]:=4
✖
https://wolfram.com/xid/0mk946n73e6q-omsf12
Out[4]=4
In[5]:=5
✖
https://wolfram.com/xid/0mk946n73e6q-ga8k4q
Out[5]=5
In[6]:=6
✖
https://wolfram.com/xid/0mk946n73e6q-1jarjw
Out[6]=6

PartLayer only supports a single-part specification and not an arbitrary array of those, but accepts Span to extract chunks of the input:

In[7]:=7
✖
https://wolfram.com/xid/0mk946n73e6q-bgte5h
Out[7]=7
In[8]:=8
✖
https://wolfram.com/xid/0mk946n73e6q-vc505d
Out[8]=8

Possible Issues  (3)Common pitfalls and unexpected behavior

The last dimension of the position specification selects the desired parts of the input; hence its size must not exceed the input rank:

In[1]:=1
✖
https://wolfram.com/xid/0mk946n73e6q-iw2dyz
Out[1]=1

If the "Position" specification has a rank of 1, its size cannot be variable:

In[1]:=1
✖
https://wolfram.com/xid/0mk946n73e6q-kztzt3
Out[1]=1

An unspecified ExtractLayer will always assume it is being evaluated on a single example and not on a batch. In the following, the arrays data and pos will be interpreted as a single 2×3 input array and a 2×1 part specification, respectively:

In[1]:=1
✖
https://wolfram.com/xid/0mk946n73e6q-y9cqwb
In[2]:=2
✖
https://wolfram.com/xid/0mk946n73e6q-v9xsdh
In[3]:=3
✖
https://wolfram.com/xid/0mk946n73e6q-5bb0ja
Out[3]=3

In order to have them interpreted as a batch of two lists of length 3 and 1, respectively, explicit shapes must be specified prior to evaluation:

In[4]:=4
✖
https://wolfram.com/xid/0mk946n73e6q-tp4j6u
Out[4]=4
Wolfram Research (2019), ExtractLayer, Wolfram Language function, https://reference.wolfram.com/language/ref/ExtractLayer.html.
✖
Wolfram Research (2019), ExtractLayer, Wolfram Language function, https://reference.wolfram.com/language/ref/ExtractLayer.html.

Text

Wolfram Research (2019), ExtractLayer, Wolfram Language function, https://reference.wolfram.com/language/ref/ExtractLayer.html.

✖
Wolfram Research (2019), ExtractLayer, Wolfram Language function, https://reference.wolfram.com/language/ref/ExtractLayer.html.

CMS

Wolfram Language. 2019. "ExtractLayer." Wolfram Language & System Documentation Center. Wolfram Research. https://reference.wolfram.com/language/ref/ExtractLayer.html.

✖
Wolfram Language. 2019. "ExtractLayer." Wolfram Language & System Documentation Center. Wolfram Research. https://reference.wolfram.com/language/ref/ExtractLayer.html.

APA

Wolfram Language. (2019). ExtractLayer. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/ExtractLayer.html

✖
Wolfram Language. (2019). ExtractLayer. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/ExtractLayer.html

BibTeX

@misc{reference.wolfram_2025_extractlayer, author="Wolfram Research", title="{ExtractLayer}", year="2019", howpublished="\url{https://reference.wolfram.com/language/ref/ExtractLayer.html}", note=[Accessed: 29-March-2025 ]}

✖
@misc{reference.wolfram_2025_extractlayer, author="Wolfram Research", title="{ExtractLayer}", year="2019", howpublished="\url{https://reference.wolfram.com/language/ref/ExtractLayer.html}", note=[Accessed: 29-March-2025 ]}

BibLaTeX

@online{reference.wolfram_2025_extractlayer, organization={Wolfram Research}, title={ExtractLayer}, year={2019}, url={https://reference.wolfram.com/language/ref/ExtractLayer.html}, note=[Accessed: 29-March-2025 ]}

✖
@online{reference.wolfram_2025_extractlayer, organization={Wolfram Research}, title={ExtractLayer}, year={2019}, url={https://reference.wolfram.com/language/ref/ExtractLayer.html}, note=[Accessed: 29-March-2025 ]}