org.deeplearning4j.nn.conf.layers.objdetect

Class Yolo2OutputLayer.Builder

java.lang.Object

org.deeplearning4j.nn.conf.layers.Layer.Builder<Yolo2OutputLayer.Builder>

org.deeplearning4j.nn.conf.layers.objdetect.Yolo2OutputLayer.Builder

Enclosing class:

Yolo2OutputLayer

public static class Yolo2OutputLayer.Builder
extends Layer.Builder<Yolo2OutputLayer.Builder>

Field Summary

Fields inherited from class org.deeplearning4j.nn.conf.layers.Layer.Builder

allParamConstraints, biasConstraints, iDropout, layerName, weightConstraints

Constructor Summary

Constructors

Constructor and Description
Builder()

Method Summary

Modifier and Type	Method and Description
Yolo2OutputLayer.Builder	boundingBoxPriors(INDArray boundingBoxes) Bounding box priors dimensions [width, height].
Yolo2OutputLayer	build()
Yolo2OutputLayer.Builder	lambdaCoord(double lambdaCoord) Loss function coefficient for position and size/scale components of the loss function.
Yolo2OutputLayer.Builder	lambdaNoObj(double lambdaNoObj) Loss function coefficient for the "no object confidence" components of the loss function.
Yolo2OutputLayer.Builder	lossClassPredictions(ILossFunction lossClassPredictions) Loss function for the class predictions - defaults to L2 loss (i.e., sum of squared errors, as per the paper), however Loss MCXENT could also be used (which is more common for classification).
Yolo2OutputLayer.Builder	lossPositionScale(ILossFunction lossPositionScale) Loss function for position/scale component of the loss function

Methods inherited from class org.deeplearning4j.nn.conf.layers.Layer.Builder

constrainAllParameters, constrainBias, constrainWeights, dropOut, dropOut, name

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

Builder

public Builder()

Method Detail

lambdaCoord

public Yolo2OutputLayer.Builder lambdaCoord(double lambdaCoord)

Loss function coefficient for position and size/scale components of the loss function. Default (as per paper): 5

Parameters:

lambdaCoord - Lambda value for size/scale component of loss function

lambdaNoObj

public Yolo2OutputLayer.Builder lambdaNoObj(double lambdaNoObj)

Loss function coefficient for the "no object confidence" components of the loss function. Default (as per paper): 0.5

Parameters:

lambdaNoObj - Lambda value for no-object (confidence) component of the loss function

lossPositionScale

public Yolo2OutputLayer.Builder lossPositionScale(ILossFunction lossPositionScale)

Loss function for position/scale component of the loss function

Parameters:

lossPositionScale - Loss function for position/scale

lossClassPredictions

public Yolo2OutputLayer.Builder lossClassPredictions(ILossFunction lossClassPredictions)

Loss function for the class predictions - defaults to L2 loss (i.e., sum of squared errors, as per the paper), however Loss MCXENT could also be used (which is more common for classification).

Parameters:

lossClassPredictions - Loss function for the class prediction error component of the YOLO loss function

boundingBoxPriors

public Yolo2OutputLayer.Builder boundingBoxPriors(INDArray boundingBoxes)

Bounding box priors dimensions [width, height]. For N bounding boxes, input has shape [rows, columns] = [N, 2] Note that dimensions should be specified as fraction of grid size. For example, a network with 13x13 output, a value of 1.0 would correspond to one grid cell; a value of 13 would correspond to the entire image.

Parameters:

boundingBoxes - Bounding box prior dimensions (width, height)

build

public Yolo2OutputLayer build()

Specified by:

build in class Layer.Builder<Yolo2OutputLayer.Builder>