SequenceRestLayer
represents a net that takes a sequence of inputs and removes its first element.
Details and Options
- SequenceRestLayer[] represents a net that takes a sequence of arrays and outputs a sequence of arrays of length one less than the input sequence length.
- SequenceRestLayer[…][input] explicitly computes the output from applying the layer.
- SequenceRestLayer[…][{input1,input2,…}] explicitly computes an output for each of the inputi.
- When given a NumericArray as input, the output will be a NumericArray.
- SequenceRestLayer is typically used inside NetChain, NetGraph, etc.
- The input and output ports of the net represented by SequenceRestLayer[] are:
-
"Input" a sequence of n arrays "Output" a sequence of n-1 arrays - SequenceRestLayer["Input"shape] allows the shape of the input to be specified. Possible forms for shape are:
-
n a 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[SequenceRestLayer] gives the list of default options to construct the layer. Options[SequenceRestLayer[…]] gives the list of default options to evaluate the layer on some data.
- Information[SequenceRestLayer[…]] gives a report about the layer.
- Information[SequenceRestLayer[…],prop] gives the value of the property prop of SequenceRestLayer[…]. Possible properties are the same as for NetGraph.
Examples
open allclose allBasic Examples (2)
Create a SequenceRestLayer:
Create a SequenceRestLayer that expects a sequence of vectors of size 3:
Scope (3)
Ports (3)
Create a SequenceRestLayer that expects a length-3 sequence of 2x2 matrices:
Apply the layer to a sequence:
Create a SequenceRestLayer that expects a sequence of real numbers:
Thread the layer across a batch of inputs:
Create a SequenceRestLayer that drops the first color channel from an RGB image, turning it into a two-channel image:
Possible Issues (2)
SequenceRestLayer cannot be applied to sequences of length less than 2:
SequenceRestLayer cannot accept symbolic inputs:
Text
Wolfram Research (2017), SequenceRestLayer, Wolfram Language function, https://reference.wolfram.com/language/ref/SequenceRestLayer.html.
CMS
Wolfram Language. 2017. "SequenceRestLayer." Wolfram Language & System Documentation Center. Wolfram Research. https://reference.wolfram.com/language/ref/SequenceRestLayer.html.
APA
Wolfram Language. (2017). SequenceRestLayer. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/SequenceRestLayer.html