SequenceMostLayer

SequenceMostLayer[]

represents a net that takes a sequence of inputs and removes its last element.

Details and Options

  • SequenceMostLayer[] represents a net that takes a sequence of arrays and outputs a sequence of arrays of length one less than the input sequence length.
  • SequenceMostLayer[…][input] explicitly computes the output NumericArray object from applying the layer.
  • SequenceMostLayer[…][{input1,input2,…}] explicitly computes an output for each of the inputi.
  • When given a NumericArray as input, the output will be a NumericArray.
  • SequenceMostLayer is typically used inside NetChain, NetGraph, etc.
  • The input and output ports of the net represented by SequenceMostLayer[] are:
  • "Input"a sequence of n arrays
    "Output"a sequence of n-1 arrays
  • SequenceMostLayer["Input"shape] allows the shape of the input to be specified. Possible forms for shape are:
  • na sequence of n numbers
    "Varying"a sequence of numbers of varying length
    {len,d1,d2,…}sequence of len arrays of dimensions d1×d2×…
    {"Varying",d1,d2,…}varying number of arrays of dimensions d1×d2×…
  • Options[SequenceMostLayer] gives the list of default options to construct the layer. Options[SequenceMostLayer[…]] gives the list of default options to evaluate the layer on some data.
  • Information[SequenceMostLayer[…]] gives a report about the layer.
  • Information[SequenceMostLayer[…],prop] gives the value of the property prop of SequenceMostLayer[…]. Possible properties are the same as for NetGraph.

Examples

open allclose all

Basic Examples  (2)

Create a SequenceMostLayer:

Create a SequenceMostLayer that expects a sequence of vectors of size 3:

Apply the layer to a sequence:

Scope  (3)

Ports  (3)

Create a SequenceMostLayer that expects a length-3 sequence of 2x2 matrices:

Apply the layer to a sequence:

Create a SequenceMostLayer that expects a sequence of real numbers:

Thread the layer across a batch of inputs:

Create a SequenceMostLayer that drops the last color channel from an RGB image, turning it into a two-channel image:

Apply it to an image:

Possible Issues  (1)

SequenceMostLayer cannot accept symbolic inputs:

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

Text

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

CMS

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

APA

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

BibTeX

@misc{reference.wolfram_2024_sequencemostlayer, author="Wolfram Research", title="{SequenceMostLayer}", year="2017", howpublished="\url{https://reference.wolfram.com/language/ref/SequenceMostLayer.html}", note=[Accessed: 13-November-2024 ]}

BibLaTeX

@online{reference.wolfram_2024_sequencemostlayer, organization={Wolfram Research}, title={SequenceMostLayer}, year={2017}, url={https://reference.wolfram.com/language/ref/SequenceMostLayer.html}, note=[Accessed: 13-November-2024 ]}