divideblock

(To be removed) Divide targets into three sets using blocks of indices

divideblock will be removed in a future release. For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.

For advice on updating your code, see Version History.

Syntax

[trainInd,valInd,testInd] = divideblock(Q,trainRatio,valRatio,testRatio)


Description

[trainInd,valInd,testInd] = divideblock(Q,trainRatio,valRatio,testRatio) separates targets into three sets: training, validation, and testing. It takes the following inputs:

Q	Number of targets to divide up.
trainRatio	Ratio of targets for training. Default = 0.7.
valRatio	Ratio of targets for validation. Default = 0.15.
testRatio	Ratio of targets for testing. Default = 0.15.

and returns

trainInd	Training indices
valInd	Validation indices
testInd	Test indices

Examples

[trainInd,valInd,testInd] = divideblock(3000,0.6,0.2,0.2);

Network Use

Here are the network properties that define which data division function to use, what its parameters are, and what aspects of targets are divided up, when train is called.

net.divideFcn
net.divideParam
net.divideMode

Version History

Introduced in R2008a

R2026a: divideblock will be removed

divideblock will be removed in a future release.

To learn more about data processing for neural networks, see these examples and topics:

• Preprocess Data for Domain-Specific Deep Learning Applications

• Datastores for Deep Learning

• Choose an App to Label Ground Truth Data

For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.