Package smile.deep.metric

Class Accuracy

java.lang.Object
smile.deep.metric.Accuracy
All Implemented Interfaces:
Metric
public class Accuracy extends Object implements Metric
The accuracy is the proportion of true results (both true positives and true negatives) in the population.

  • Constructor Details

    • Accuracy

      public Accuracy()
      Constructor.

    • Accuracy

      public Accuracy(double threshold)
      Constructor.
      Parameters:
      threshold - The threshold for converting input into binary labels.

  • Method Details

    • toString

      public String toString()
      Overrides:
      toString in class Object

    • name

      public String name()
      Description copied from interface: Metric
      Returns the name of metric.
      Specified by:
      name in interface Metric
      Returns:
      the name of metric.

    • update

      public void update(Tensor output, Tensor target)
      Description copied from interface: Metric
      Updates the metric states with input data. This is often used when new data needs to be added for metric computation.
      Specified by:
      update in interface Metric
      Parameters:
      output - the model output.
      target - the ground truth.

    • compute

      public double compute()
      Description copied from interface: Metric
      Computes the metric value from the metric state, which are updated by previous update() calls. The compute frequency can be less than the update frequency.
      Specified by:
      compute in interface Metric
      Returns:
      the metric value.

    • reset

      public void reset()
      Description copied from interface: Metric
      Resets the metric state variables to their default value. Usually this is called at the end of every epoch to clean up metric states.
      Specified by:
      reset in interface Metric