Error when executing bayesopt

10 次查看(过去 30 天)
Stephen Wu
Stephen Wu 2019-4-10
I am running bayesopt and have encoutered the following error several times. It happens only when I use the runParallel option. Could anyone help me with that?
Dot indexing is not supported for variables of this type.
Error in BayesianOptimization/fitObjectiveFcnGP (line 2657)
KernelParameters = ObjectiveFcnGP.KernelInformation.KernelParameters;
Error in BayesianOptimization/fitGPModels (line 2600)
this.ObjectiveFcnGP = fitObjectiveFcnGP(this, BullAdjustment, BullAdjustmentN, useFitMethodNone);
Error in BayesianOptimization/chooseNextPoint (line 2295)
this = fitGPModels(this, true, BullAdjustmentN, false);
Error in BayesianOptimization/chooseNextPointParallel (line 2353)
BO2 = chooseNextPoint(BO2);
Error in BayesianOptimization/runParallel (line 2095)
this = chooseNextPointParallel(this);
Error in BayesianOptimization/run (line 1939)
this = runParallel(this);
Error in BayesianOptimization (line 457)
this = run(this);
Error in bayesopt (line 323)
Results = BayesianOptimization(Options);
  4 个评论
Walter Roberson
Walter Roberson 2020-7-16
A common cause of this kind of message is if a stage returns an empty array when the code expects it to return a struct or object.
Mohammad Beit Sadi
Mohammad Beit Sadi 2021-7-22
I get the same error and the XAtMinObjective is an empty array. I have rectified the issue by picking XAtMinEstimatedObjective when that happens.
I don't know why XAtMinObjective is an empty array though. Is it because there are multiple X values where the minimum happens?

请先登录,再进行评论。

回答(0 个)

类别

Help CenterFile Exchange 中查找有关 Model Building and Assessment 的更多信息

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by