anchorBoxLayer

(Removed) Create anchor box layer for object detection

Since R2020a

anchorBoxLayer function has been removed. Use the ssdObjectDetector object to specify the anchor boxes for training a SSD object detection network, instead.

Description

An anchor box layer stores anchor boxes for a feature map used in object detection networks.

Creation

Syntax

layer = anchorBoxLayer(anchorBoxes)

layer = anchorBoxLayer(anchorBoxes,Name,Value)

Description

layer = anchorBoxLayer(anchorBoxes) creates an anchor box layer, specifying the size of the anchor boxes by using anchorBoxes. The anchorBoxes input sets the AnchorBoxes property.

layer = anchorBoxLayer(anchorBoxes,Name,Value) set properties of the anchor box layer by using one or more name-value arguments. Enclose each property name in quotes.

For example, anchorBoxLayer(anchorBoxes,'Name','anchorboxlayer') creates an anchor box layer with the name "anchorboxlayer" from anchor boxes specified by anchorBoxes.

Properties

AnchorBoxes — Size of anchor boxes

M-by-2 matrix

Size of anchor boxes, specified as an M-by-2 matrix of M anchor boxes. Each row of the matrix is of the form [height width].

Name — Layer name

"" (default) | character vector | string scalar

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

The AnchorBoxLayer object stores this property as a character vector.

Data Types: char | string

Examples

Create Anchor Box Layer

Specify the size of four anchor boxes.

anchorBoxes = [50 50; 100 100; 50 100; 100 50];

Create an anchor box layer named "anchorboxlayer" and display the results.

layer = anchorBoxLayer(anchorBoxes,'Name','anchorboxlayer')

layer = 
  AnchorBoxLayer with properties:

           Name: 'anchorboxlayer'

   Hyperparameters
    AnchorBoxes: [4x2 double]

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™.

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.

Version History

Introduced in R2020a

R2024b: anchorBoxLayer function has been removed

anchorBoxLayer function has been removed. You can use the ssdObjectDetector object to specify the anchor boxes for training a SSD object detection network, instead.

R2023b: anchorBoxLayer function will be removed

anchorBoxLayer function will be removed in a future release. You can use the ssdObjectDetector object to specify the anchor boxes for training a SSD object detection network, instead.

R2022a: anchorBoxLayer function is not recommended

anchorBoxLayer function is not recommended. You can use the ssdObjectDetector object to specify the anchor boxes for training a SSD object detection network, instead.