One-vs-AllΒΆ

The documentation is generated based on the sources available at dotnet/machinelearning and released under MIT License.

Type: multiclassclassifiertrainer Aliases: OVA Namespace: Microsoft.ML.Trainers Assembly: Microsoft.ML.StandardLearners.dll Microsoft Documentation: One-vs-All

Description

In this strategy, a binary classification algorithm is used to train one classifier for each class, which distinguishes that class from all other classes. Prediction is then performed by running these binary classifiers, and choosing the prediction with the highest confidence score.

Parameters

Name Short name Default Description
calibrator cali Microsoft. ML. Runtime. Internal. Calibration. PlattCalibratorTrainerFactory Output calibrator
imputeMissingLabelsAsNegative missNeg False Whether to treat missing labels as having negative labels, instead of keeping them missing
maxCalibrationExamples numcali 1000000000 Number of instances to train the calibrator
predictorType p   Base predictor
useProbabilities useprob True Use probability or margins to determine max