crop3dLayer

3-D crop layer

Description

A 3-D crop layer crops a 3-D volume to the size of the input feature map.

Specify the number of inputs to the layer when you create it. The inputs to the layer have the names 'in' and 'ref'. Use the input names when connecting or disconnecting the layer by using connectLayers or disconnectLayers. All inputs to a 3-D crop layer must have the same number of dimensions.

Creation

Syntax

layer = crop3dLayer

layer = crop3dLayer([X Y Z])

layer = crop3dLayer(___,'Name',Name)

Description

layer = crop3dLayer creates a 3-D crop layer that crops an input feature map from the center of the feature map. The size of the cropped region is equal to the size of a second reference input feature map.

layer = crop3dLayer([X Y Z]) also sets the cropLocation property with the (X,Y,Z) coordinate of the crop window. X is the coordinate in the horizontal direction, Y is the coordinate in the vertical direction, and Z is the coordinate in the depth direction.

layer = crop3dLayer(___,'Name',Name) also sets the Name property. To create a network containing a 3-D crop layer, you must specify a layer name.

Properties

Crop

cropLocation — Crop location

'centercrop' (default) | three-element numeric vector

Crop location, specified as 'centercrop' or a three-element numeric vector representing the (x,y,z) coordinate of the crop window.

Layer

Name — Layer name

'' (default) | character vector | string scalar

Layer name, specified as a character vector or a string scalar. For Layer array input, the trainnet and dlnetwork functions automatically assign names to unnamed layers.

The Crop3DLayer object stores this property as a character vector.

Data Types: char | string

NumInputs — Number of inputs

2 (default)

Number of inputs of the layer. This layer accepts two inputs.

Data Types: double

InputNames — Input names

{'in','ref'} (default)

Input names of the layer, specified as {'in','ref'}. This layer accepts two inputs.

Data Types: cell

NumOutputs — Number of outputs

Read-only: 1 (default)

This property is read-only.

Number of outputs from the layer, stored as 1. This layer has a single output only.

Data Types: double

OutputNames — Output names

Read-only: {'out'} (default)

This property is read-only.

Output names, stored as {'out'}. This layer has a single output only.

Data Types: cell

Examples

Create and Connect 3-D Crop Layer

Create a 3-D crop layer.

layer = crop3dLayer

layer = 
  Crop3DLayer with properties:

            Name: ''
    CropLocation: 'centercrop'
       NumInputs: 2
      InputNames: {'in'  'ref'}

Create a neural network containing a 3-D crop layer.

net = dlnetwork;

layers = [
    image3dInputLayer([32 32 32 3],Name="image")
    convolution3dLayer(3,16,Padding="same")
    crop3dLayer(Name="crop")
    concatenationLayer(4,2,Name="concat")];

net = addLayers(net,layers);

Add a max pooling layer to the neural network.

layer = maxPooling3dLayer(2,Stride=2,Name="pool");
net = addLayers(net,layer);
net = connectLayers(net,"image","pool");

Connect the second input of the crop layer to the output of the max pooling layer.

net = connectLayers(net,"pool","crop/ref");

Concatenate the crop layer output and the max pooling layer output.

net = connectLayers(net,"pool","concat/in2");

Display the neural network in a plot.

plot(net)

Algorithms

Layer Input and Output Formats

Layers in a layer array or layer graph pass data to subsequent layers as formatted dlarray objects. The format of a dlarray object is a string of characters in which each character describes the corresponding dimension of the data. The format consists of one or more of these characters:

• "S" — Spatial

• "C" — Channel

• "B" — Batch

• "T" — Time

• "U" — Unspecified

For example, you can describe 2-D image data that is represented as a 4-D array, where the first two dimensions correspond to the spatial dimensions of the images, the third dimension corresponds to the channels of the images, and the fourth dimension corresponds to the batch dimension, as having the format "SSCB" (spatial, spatial, channel, batch).

You can interact with these dlarray objects in automatic differentiation workflows, such as those for developing a custom layer, using a functionLayer object, or using the forward and predict functions with dlnetwork objects.

This table shows the supported input formats of Crop3DLayer objects and the corresponding output format. If the software passes the output of the layer to a custom layer that does not inherit from the nnet.layer.Formattable class, or a FunctionLayer object with the Formattable property set to 0 (false), then the layer receives an unformatted dlarray object with dimensions ordered according to the formats in this table. The formats listed here are only a subset. The layer may support additional formats such as formats with additional "S" (spatial) or "U" (unspecified) dimensions.

Input Format	Output Format
""SSCB" (spatial, spatial, spatial, channel, batch)	""SSCB" (spatial, spatial, spatial, channel, batch)
"SSSC" (spatial, spatial, spatial, channel)	"SSSC" (spatial, spatial, spatial, channel)

In dlnetwork objects, Crop3DLayer objects also support these input and output format combinations.

Input Format	Output Format
"SSSCBT" (spatial, spatial, spatial, channel, batch, time)	"SSSCBT" (spatial, spatial, spatial, channel, batch, time)
"SSSCT" (spatial, spatial, spatial, channel, time)	"SSSCT" (spatial, spatial, spatial, channel, time)

Complex Numbers

Crop3DLayer objects support complex-valued input and outputs. (since R2024a) The layer applies the same underlying operation to complex-valued input as it does to real-valued input and outputs complex-valued data where applicable.

Version History

Introduced in R2019b

R2024a: Support for complex-valued inputs and outputs

Crop3DLayer objects support complex-valued input and outputs. The layer applies the same underlying operation to complex-valued input as it does to real-valued input and outputs complex-valued data where applicable.