rpnSoftmaxLayer

Softmax layer for region proposal network (RPN)

expand all in page

Description

A region proposal network (RPN) softmax layer applies a softmax activation function to the input. Use this layer to create a Faster R-CNN object detection network.

Creation

Syntax

layer = rpnSoftmaxLayer
layer = rpnSoftmaxLayer('Name',Name)

Description

layer = rpnSoftmaxLayer creates a softmax layer for a Faster R-CNN object detection network.

example

layer = rpnSoftmaxLayer('Name',Name) creates a softmax layer and sets the optional Name property.

Properties

expand all

Layer name, specified as a character vector or a string scalar. To include a layer in a layer graph, you must specify a nonempty unique layer name. If you train a series network with the layer and Name is set to '', then the software automatically assigns a name to the layer at training time.

Data Types: char | string

Number of inputs of the layer. This layer accepts a single input only.

Data Types: double

Input names of the layer. This layer accepts a single input only.

Data Types: cell

Number of outputs of the layer. This layer has a single output only.

Data Types: double

Output names of the layer. This layer has a single output only.

Data Types: cell

Examples

collapse all

Open Live Script

Create an RPN softmax layer with the name 'rpn_softmax'.

rpnSoftmax = rpnSoftmaxLayer('Name','rpn_softmax')
rpnSoftmax = 
  RPNSoftmaxLayer with properties:

    Name: 'rpn_softmax'

Create an RPN classification layer with the name 'rpn_cls'.

rpnClassification = rpnClassificationLayer('Name','rpn_cls')
rpnClassification = 
  RPNClassificationLayer with properties:

    Name: 'rpn_cls'

Add the RPN softmax and RPN classification layers to a Layer array, to form the classification branch of an RPN.

numAnchors = 3;
rpnClassLayers = [
    convolution2dLayer(1,numAnchors*2,'Name','conv1x1_box_cls')
    rpnSoftmax
    rpnClassification
    ]
rpnClassLayers = 
  3x1 Layer array with layers:

     1   'conv1x1_box_cls'   Convolution                 6 1x1 convolutions with stride [1  1] and padding [0  0  0  0]
     2   'rpn_softmax'       RPN Softmax                 rpn softmax
     3   'rpn_cls'           RPN Classification Output   cross-entropy loss with 'object' and 'background' classes

See Also

| | (Deep Learning Toolbox)

Topics

Introduced in R2018b

Computer Vision Toolbox Documentation

Support