LabVIEW Analytics and Machine Learning Toolkit API Reference

Content Type
Programming Language
Current manual

Error Codes (Analytics and Machine Learning Toolkit)

Error Codes (Analytics and Machine Learning Toolkit)

The Analytics and Machine Learning VIs can return the following error codes. Refer to the KnowledgeBase for more information about correcting errors in LabVIEW.

Code Description
−388414 The number of rows in the first batch of data must be greater than or equal to number of components.
−388413 The number of columns of mean values must equal the number of columns in the current batch of input data.
−388412 The length of min values or max values must equal the number of features in the current batch of input data.
−388411 The length of mean values must equal the number of features in the current batch of input data.
−388410 The array size of weights or biases must equal the number of hidden layers. The array size of weight or bias must equal the number of neurons in each layer.
−388409 The array size of hidden layer type must equal the array size of number of hidden neurons.
−388408 The model fitting does not converge before reaching the maximum number of iterations.
−388407 The SVM model training fails. Normalize the training data or change the SVM parameters.
−388406 The GMM model training fails. Increase regulator.
−388405 The number of data samples must be greater than 1.
−388404 There must be at least one cluster in predicted labels that has more than one data samples for the Davies Bouldin Index metric and the Dunn Index metric.
−388403 predicted labels must have more than one clusters for the Davies Bouldin Index metric and the Dunn Index metric.
−388402 The number of predicted labels in predicted labels must equal the number of data samples.
−388401 The number of data samples must be no less than the number of clusters.
−388400 The covariance matrix in covariance matrix must be positive definite.
−388399 The covariance matrix in initial covariance matrix must be positive definite.
−388397 The covariance matrix in initial covariance matrix must be symmetric.
−388396 The number of rows or columns of initial covariance matrix must equal the number of features in the training data.
−388395 initial weights must be between 0 and 1.
−388394 The number of columns of initial mean values must equal the number of features in data.
−388393 threshold for T2 must be greater than or equal to 0.
−388392 The wrong Load Data (2D Array) VI instance is used to load data.
−388391 The array length of number of support vectors for each class must equal number of classes.
−388390 You must perform feature manipulation before training clustering, classification, and anomaly detection models.
−388389 nu is invalid. Reduce the value of nu.
−388388 The array size of variance must equal the number of eigenvectors.
−388387 MQE threshold must be greater than or equal to 0.
−388386 The number of features in the input data must equal the number of columns of support vectors.
−388385 The number of nodes, which equals row * column, must equal the number of columns of map vectors.
−388384 confidence level must be greater than 0 and less than 1.
−388383 initial learning rate must be greater than 0.
−388382 initial radius must be greater than 0.
−388381 The value of row and col must be greater than or equal to 0.
−388380 The number of features in the input data must equal the number of features in map vectors.
−388379 covariance matrix must be symmetric.
−388378 You must not choose the AIC metric or the BIC metric to evaluate the DBSCAN model and the K-Means model.
−388377 threshold for Q must be greater than or equal to 0.
−388376 The number of columns of the input data must equal the number of columns of centroids.
−388375 The number of columns of the input data must equal the number of columns of core samples.
−388374 The number of columns of the input data must equal the number of columns of mean values.
−388372 The size of predicted labels must equal the size of input labels.
−388371 centroids must not be empty and the number of rows of centroids must equal number of clusters.
−388370 The size of covariance values must equal number of clusters and the number of rows/columns of covariance matrix must equal the size of mean values.
−388369 The size of weights must equal number of clusters and the sum of weights must equal 1.
−388368 The number of rows of mean values must equal number of clusters.
−388367 The size of core samples labels must be greater than 0.
−388366 max must be greater than min.
−388365 The size of core sample labels must equal the number of rows of core samples.
−388364 initial method must not be empty.
−388362 attempts must be greater than 0.
−388361 p must be greater than 0.
−388360 min samples must be greater than 0.
−388359 max distance must be greater than 0.
−388358 number of clusters must be greater than 0.
−388357 regulator must be greater than 0.
−388356 Out of memory.
−388355 The sum of number of support vectors for each class must equal number of support vectors.
−388354 output layer type is empty.
−388353 The array size of probB must equal number of classes * (number of classes - 1)/2.
−388352 The array size of probA must equal number of classes * (number of classes - 1)/2.
−388351 The array size of decision function constants must equal number of classes * (number of classes - 1)/2.
−388350 The number of rows of coefficients of support vectors must be one less than number of classes, and the number of columns of coefficients of support vectors must equal number of support vectors.
−388349 The number of rows of support vectors must equal number of support vectors.
−388348 number of support vectors must be greater than 0.
−388347 The number of rows of H to O coefficients must equal number of output neurons, and the number of columns of H to O coefficients must be one greater than number of hidden neurons.
−388346 The number of rows of I to H coefficients must equal number of hidden neurons, and the number of columns of I to H coefficients must be one greater than number of input neurons.
−388345 number of output neurons must equal number of classes.
−388344 The number of features in the input data must equal number of input neurons.
−388343 number of input neurons must be greater than 0.
−388342 For multi-class classification, the number of rows of coefficients of support vectors must equal number of classes. For two-class classification, the number of rows of coefficients of support vectors must equal 1.
−388341 The array size of labels of each class must equal number of classes.
−388340 number of classes must be greater than 1.
−388339 The number of features in the input data must be one less than the number of columns of coefficients of support vectors.
−388338 The model is untrained before deployment.
−388337 cost function type must not be empty.
−388336 You must initialize the model before training.
−388335 coef0 must not be empty.
−388334 kernel type must not be empty.
−388333 SVM type must not be empty.
−388332 hidden layer type must not be empty.
−388331 There are repeated class labels in weighted c.
−388330 class weight of weighted c must be greater than 0.
−388329 label of weighted c cannot be found in the labels of the training data.
−388328 nu must be greater than 0 and less than or equal to 1.
−388327 c must be greater than 0.
−388326 number of hidden neurons must be greater than 0.
−388325 number of searches must be greater than 0 when search method is random search.
−388324 positive label cannot be found in the labels of the input data.
−388323 number of folds must be greater than 1 and equal to or less than the number of samples in the training data.
−388322 tolerance must be greater than 0.
−388321 max iteration must be greater than 0.
−388320 The input data must not be empty.
−388319 ratio of variance must be greater than 0 and no greater than 1.
−388318 The number of classes in the training data must be no greater than 2.
−388317 number of components must be greater than 0 and no greater than the number of features in training data.
−388316 The number of samples in the training data must equal number of labels.
−388315 The number of features in the input data must equal the number of rows of eigenvectors.
−388314 The number of rows of eigenvectors must equal the array size of mean values, and be no less than the number of columns of eigenvectors.
−388313 mean values and eigenvectors must not be empty.
−388312 selected feature index must be less than the number of features in the input data.
−388311 The selected feature indexes in selected feature index must be different from each other.
−388310 selected feature index must not be empty.
−388309 The number of features in the input data must equal the array size of min values or max values.
−388308 The number of features in the input data must equal the array size of mean values.
−388307 min values and max values must not be empty. The size of min values and max values must be the same.
−388306 mean values and standard deviation values must not be empty. The size of mean values and standard deviation values must be the same.
−388305 The number of features in the input data must equal that in the source data.
−388304 gamma must be greater than 0.
−388303 degree must be greater than 0.
−388302 The array sizes of source data, eigenvectors, and variance in the input model are not compatible with each other.
−388301 source data, eigenvectors, and variance in the input model must not be empty.
−388300 The data must be loaded.
388301 The PCA T2Q model is trained based on the data that is already transformed with PCA feature manipulation.
Was this information helpful?