rcnnBoxRegressionLayer

Box regression layer for Fast and Faster R-CNN

Description

A box regression layer refines bounding box locations by using a smooth L1 loss function. Use this layer to create a Fast or Faster R-CNN object detection network.

Creation

Syntax

layer = rcnnBoxRegressionLayer
layer = rcnnBoxRegressionLayer('Name',Name)

Description

layer = rcnnBoxRegressionLayer creates a box regression layer for a Fast or Faster R-CNN object detection network.

example

layer = rcnnBoxRegressionLayer('Name',Name) creates a box regression 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

Examples

collapse all

Create an R-CNN box regression layer with the name 'rcnn_box_reg'.

rcnnBoxRegression = rcnnBoxRegressionLayer('Name','rcnn_box_reg');

Introduced in R2018b