spaceToDepthLayer

R2026b

Space to depth layer

Description

A space to depth layer permutes the spatial blocks of the input into the depth dimension. Use this layer when you need to combine feature maps of different size without discarding any feature data.

Given an input feature map of size [H W C] and blocks of size [height width], the output feature map size is [floor(H/height) floor(W/width) C*height*width].

This object requires Deep Learning Toolbox™.

Creation

Syntax

layer = spaceToDepthLayer(blockSize)

layer = spaceToDepthLayer(blockSize,Name=name)

Description

layer = spaceToDepthLayer(blockSize) creates a space to depth layer, specifying the block size to reorder the input activation.

layer = spaceToDepthLayer(blockSize,Name=name) creates a space to depth layer and sets the Name property as the value name.

Input Arguments

blockSize — Block size to reorder input activation

vector of two positive integers

Block size to reorder the input activation, specified as a vector of two positive integers [h w], where h is the height and w is the width. When creating the layer, you can specify BlockSize as a scalar to use the same value for both dimensions.

This argument sets the BlockSize property.

Example: [2 1] specifies blocks of height 2 and width 1.

Properties

BlockSize — Block size to reorder input activation

vector of two positive integers

Block size to reorder the input activation, specified as a vector of two positive integers [h w], where h is the height and w is the width. When creating the layer, you can specify BlockSize as a scalar to use the same value for both dimensions.

Example: [2 1] specifies blocks of height 2 and width 1.

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

Read-only: 1 (default)

This property is read-only.

Number of inputs to the layer, represented as 1. This layer has a single input only.

Data Types: double

InputNames — Input name

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

This property is read-only.

Input name, represented as {'in'}. This layer has a single input only.

NumOutputs — Number of outputs

Read-only: 1 (default)

This property is read-only.

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

Data Types: double

OutputNames — Output name

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

This property is read-only.

Output name, represented as {'out'}. This layer has a single output only.

Examples

Create Space to Depth Layer

Specify the block size to reorder input activations.

blockSize = [2 2];

Create a space to depth layer named 'spacetodepth'.

layer = spaceToDepthLayer(blockSize,Name="spacetodepth")

layer = 
  SpaceToDepthLayer with properties:

         Name: 'spacetodepth'
    BlockSize: [2 2]

   Learnable Parameters
    No properties.

   State Parameters
    No properties.

  Show all properties

Extended Capabilities

C/C++ Code Generation

Generate C and C++ code using MATLAB® Coder™.

SpaceToDepthLayer supports the generation of C code (requires MATLAB^® Coder™). Note that if you choose the generic MATLAB Host Computer target platform, SpaceToDepthLayer generates code that uses a precompiled, platform-specific shared library. Use of a shared library preserves performance optimizations but limits the target platforms for which code can be generated. For more information, see Types of Code Generation Support in Image Processing Toolbox.

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).

For this layer, you can generate code that takes advantage of the NVIDIA CUDA deep neural network library (cuDNN), NVIDIA TensorRT™ high performance inference library, or the ARM Compute Library for Mali GPU.

GPU Arrays
Accelerate code by running on a graphics processing unit (GPU) using Parallel Computing Toolbox™.

Version History

Introduced in R2020b

R2024b: Generate C code using MATLAB Coder

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

R2021a: Object no longer requires Computer Vision Toolbox

Starting in R2021a, the function no longer requires Computer Vision Toolbox™. The function requires Deep Learning Toolbox.