resize3dLayer

3-D resize layer

Description

A 3-D resize layer resizes 3-D input by a scale factor, to a specified height, width, and depth, or to the size of a reference input feature map. Use of this layer requires Deep Learning Toolbox™.

Creation

Syntax

layer = resize3dLayer(Scale=sc)

layer = resize3dLayer(OutputSize=sz)

layer = resize3dLayer("EnableReferenceInput",tf)

layer = resize3dLayer(___,Name=Value)

Description

layer = resize3dLayer(Scale=sc) creates a 3-D resize layer and sets the Scale property as the scale factor specified by sc.

example

layer = resize3dLayer(OutputSize=sz) creates a 3-D resize layer and sets the OutputSize property with the height, width, and depth specified by sz.

example

layer = resize3dLayer("EnableReferenceInput",tf) creates a 3-D resize layer and sets the EnableReferenceInput property with the boolean specified by tf. When you specify the value as true, the layer adds an additional input that accepts a reference feature map and resizes the input to the size of the reference feature map.

example

layer = resize3dLayer(___,Name=Value) also sets one or more of the properties Method, GeometricTransformMode, NearestRoundingMode, and Name by using name-value arguments. You can specify multiple name-value arguments.

Example: layer = resize3dLayer(OutputSize=[128 128 36],Method="trilinear") creates a 3-D resize layer that resizes input to 128-by-128-by-36 pixels using trilinear interpolation.

example

Properties

expand all

Resize

`Scale` — Scale factor to resize input
3-element row vector of positive numbers

Scale factor to resize input, specified as 3-element row vector of positive numbers. The scale factors are for the row, column, and plane dimensions, respectively. When creating the layer, you can specify Scale as a scalar to use the same value for all dimensions.

`OutputSize` — Output size of resized input
3-element row vector of positive integers

Output size of resized input, specified as a 3-element row vector of positive integers of the form [nrows ncols nplanes]. You can specify one element as a positive integer and the other two elements as NaN, in which case the layer computes the output size automatically to preserve the aspect ratio of the input.

`EnableReferenceInput` — Add reference feature map as input
`false` or `0` | `true` or `1`

Add reference feature map as input to the layer, specified as a numeric or logical 0 (false) or 1 (true). When you specify the value as true, the layer resizes the height, width, and depth of the input to match the height, width, and depth of the reference feature map. The resizing operation does not change the number of channels of the input.

When you enable a reference feature map, the inputs to the layer have the names 'in1' and 'ref', where 'ref' is the name of the reference feature map. Use the input names when connecting or disconnecting the layer by using connectLayers (Deep Learning Toolbox) or disconnectLayers (Deep Learning Toolbox).

`Method` — Interpolation method
`"nearest"` (default) | `"trilinear"`

Interpolation method, specified as "nearest" for nearest neighbor interpolation or "trilinear" for trilinear interpolation.

`GeometricTransformMode` — Geometric transformation mode
`"half-pixel"` (default) | `"asymmetric"`

Geometric transformation mode to map points from input space to output space, specified as"half-pixel" or "asymmetric".

`NearestRoundingMode` — Rounding mode for nearest neighbor interpolation
`"round"` (default) | `"floor"` | `"onnx-10"`

Rounding mode for nearest neighbor interpolation, specified as one of the following.

"round" — use the same rounding behavior as the MATLAB^® round function.
"floor" — use the same rounding behavior as the MATLAB floor function.
"onnx-10" — reproduce the resizing behavior of the ONNX™ (Open Neural Network Exchange) opset 10 Resize operator.

This property is valid when the Method property is "nearest".

Layer

`Name` — Layer name
`''` (default) | character vector

Layer name, specified as a character vector. For Layer array input, the trainnet (Deep Learning Toolbox) and dlnetwork (Deep Learning Toolbox) functions automatically assign names to unnamed layers.

Data Types: char

`NumInputs` — Number of inputs
`1` (default) | `2`

Number of inputs of the layer, specified as 1 when the EnableReferenceInput property is false or 2 when the EnableReferenceInput property is true.

Data Types: double

`InputNames` — Input names
`{'in'}` (default) | `{'in','ref'}`

Input names of the layer, specified as {'in'} when the EnableReferenceInput property is false or {'in','ref'} when the EnableReferenceInput property is true.

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

collapse all

Create 3-D Resize Layer Specifying Scale Factor

Open Live Script

Create a 3-D resize layer. Specify a horizontal and vertical scale factor of 2 and a depthwise scale factor of 4.

layer = resize3dLayer('Scale',[2 2 4])

layer = 
  Resize3DLayer with properties:

                      Name: ''
                     Scale: [2 2 4]
                OutputSize: []
      EnableReferenceInput: 0
                    Method: 'nearest'
    GeometricTransformMode: 'half-pixel'
       NearestRoundingMode: 'round'

   Learnable Parameters
    No properties.

   State Parameters
    No properties.

  Show all properties

Create 3-D Resize Layer Specifying Output Size

Open Live Script

Create a 3-D resize layer named 'resize224' with an output size of [224 224 224].

layer = resize3dLayer('OutputSize',[224 224 224],'Name','resize224')

layer = 
  Resize3DLayer with properties:

                      Name: 'resize224'
                     Scale: []
                OutputSize: [224 224 224]
      EnableReferenceInput: 0
                    Method: 'nearest'
    GeometricTransformMode: 'half-pixel'
       NearestRoundingMode: 'round'

   Learnable Parameters
    No properties.

   State Parameters
    No properties.

  Show all properties

Create 3-D Resize Layer with Reference Port

This example uses:

Open Live Script

Create a dlnetwork object.

net = dlnetwork;

Create an array of layers that includes a 3-D resize layer that accepts a reference input feature map. Add the layers to the network.

layers = [
    image3dInputLayer([32 32 32 3],Name="image")
    resize3dLayer(EnableReferenceInput=true,Name="resize")]

layers = 
  2×1 Layer array with layers:

     1   'image'    3-D Image Input   32×32×32×3 images with 'zerocenter' normalization
     2   'resize'   Resize            nnet.cnn.layer.Resize3DLayer

net = addLayers(net,layers);

Connect the "ref" input of the 3-D resize layer to the output of a layer that provides a reference feature map by using the connectLayers function. This example shows a trivial connection in which the "ref" input is also connected to the output of the image input layer.

net = connectLayers(net,"image","resize/ref");

Create 3-D Resize Layer with Trilinear Interpolation

Open Live Script

Create a 3-D resize layer named 'rescale0.5' with a uniform scale factor of 0.5. Specify the interpolation method as trilinear interpolation.

layer = resize3dLayer('Scale',0.5,'Method','trilinear','Name','rescale0.5')

layer = 
  Resize3DLayer with properties:

                      Name: 'rescale0.5'
                     Scale: [0.5000 0.5000 0.5000]
                OutputSize: []
      EnableReferenceInput: 0
                    Method: 'trilinear'
    GeometricTransformMode: 'half-pixel'
       NearestRoundingMode: 'round'

   Learnable Parameters
    No properties.

   State Parameters
    No properties.

  Show all properties

References

[1] Open Neural Network Exchange. https://github.com/onnx/.

[2] ONNX. https://onnx.ai/.

Extended Capabilities

expand all

C/C++ Code Generation
Generate C and C++ code using MATLAB® Coder™.

Resize3DLayer supports the generation of C and C++ code (requires MATLAB Coder™). For more information, see Code Generation for Image Processing.

GPU Code Generation
Generate CUDA® code for NVIDIA® GPUs using GPU Coder™.

To generate CUDA^® or C++ code by using GPU Coder™, you must first construct and train a deep neural network. Once the network is trained and evaluated, you can configure the code generator to generate code and deploy the convolutional neural network on platforms that use NVIDIA^® or ARM^® GPU processors. For more information, see Deep Learning with GPU Coder (GPU Coder).

Version History

Introduced in R2020b

expand all

R2026a: Generate C code using MATLAB Coder

resize3dLayer now supports the generation of C code (requires MATLAB Coder).

R2026a: Generate CUDA code using GPU Coder

resize3dLayer now supports the generation of optimized CUDA code (requires GPU Coder).

R2021a: Support for resizing data to match feature map

The resize2dLayer layer now supports resizing input to the size of a second input feature map connected to the layer. To use this resizing mode, specify the EnableReferenceInput property of the layer as true.

resize3dLayer

Description

Creation

Syntax

Description

Properties

Resize

`Scale` — Scale factor to resize input
3-element row vector of positive numbers

`OutputSize` — Output size of resized input
3-element row vector of positive integers

`EnableReferenceInput` — Add reference feature map as input
`false` or `0` | `true` or `1`

`Method` — Interpolation method
`"nearest"` (default) | `"trilinear"`

`GeometricTransformMode` — Geometric transformation mode
`"half-pixel"` (default) | `"asymmetric"`

`NearestRoundingMode` — Rounding mode for nearest neighbor interpolation
`"round"` (default) | `"floor"` | `"onnx-10"`

Layer

`Name` — Layer name
`''` (default) | character vector

`NumInputs` — Number of inputs
`1` (default) | `2`

`InputNames` — Input names
`{'in'}` (default) | `{'in','ref'}`

`NumOutputs` — Number of outputs
Read-only: `1` (default)

`OutputNames` — Output names
Read-only: `{'out'}` (default)

Examples

Create 3-D Resize Layer Specifying Scale Factor

Create 3-D Resize Layer Specifying Output Size

Create 3-D Resize Layer with Reference Port

Create 3-D Resize Layer with Trilinear Interpolation

References

Extended Capabilities

C/C++ Code Generation
Generate C and C++ code using MATLAB® Coder™.

GPU Code Generation
Generate CUDA® code for NVIDIA® GPUs using GPU Coder™.

Version History

R2026a: Generate C code using MATLAB Coder

R2026a: Generate CUDA code using GPU Coder

R2021a: Support for resizing data to match feature map

See Also

Topics

resize3dLayer

Description

Creation

Syntax

Description

Properties

Resize

Scale — Scale factor to resize input 3-element row vector of positive numbers

OutputSize — Output size of resized input 3-element row vector of positive integers

EnableReferenceInput — Add reference feature map as input false or 0 | true or 1

Method — Interpolation method "nearest" (default) | "trilinear"

GeometricTransformMode — Geometric transformation mode "half-pixel" (default) | "asymmetric"

NearestRoundingMode — Rounding mode for nearest neighbor interpolation "round" (default) | "floor" | "onnx-10"

Layer

Name — Layer name '' (default) | character vector

NumInputs — Number of inputs 1 (default) | 2

InputNames — Input names {'in'} (default) | {'in','ref'}

NumOutputs — Number of outputs Read-only: 1 (default)

OutputNames — Output names Read-only: {'out'} (default)

Examples

Create 3-D Resize Layer Specifying Scale Factor

Create 3-D Resize Layer Specifying Output Size

Create 3-D Resize Layer with Reference Port

Create 3-D Resize Layer with Trilinear Interpolation

References

Extended Capabilities

C/C++ Code Generation Generate C and C++ code using MATLAB® Coder™.

GPU Code Generation Generate CUDA® code for NVIDIA® GPUs using GPU Coder™.

Version History

R2026a: Generate C code using MATLAB Coder

R2026a: Generate CUDA code using GPU Coder

R2021a: Support for resizing data to match feature map

See Also

Topics

`Scale` — Scale factor to resize input
3-element row vector of positive numbers

`OutputSize` — Output size of resized input
3-element row vector of positive integers

`EnableReferenceInput` — Add reference feature map as input
`false` or `0` | `true` or `1`

`Method` — Interpolation method
`"nearest"` (default) | `"trilinear"`

`GeometricTransformMode` — Geometric transformation mode
`"half-pixel"` (default) | `"asymmetric"`

`NearestRoundingMode` — Rounding mode for nearest neighbor interpolation
`"round"` (default) | `"floor"` | `"onnx-10"`

`Name` — Layer name
`''` (default) | character vector

`NumInputs` — Number of inputs
`1` (default) | `2`

`InputNames` — Input names
`{'in'}` (default) | `{'in','ref'}`

`NumOutputs` — Number of outputs
Read-only: `1` (default)

`OutputNames` — Output names
Read-only: `{'out'}` (default)

C/C++ Code Generation
Generate C and C++ code using MATLAB® Coder™.

GPU Code Generation
Generate CUDA® code for NVIDIA® GPUs using GPU Coder™.