Class ModelEvaluationInput<T, TInput, TOutput>

Namespace

AiDotNet.Models.Inputs

Assembly

AiDotNet.dll

Represents the input data required for evaluating a machine learning model.

public class ModelEvaluationInput<T, TInput, TOutput>

Type Parameters

T

The numeric type used for calculations (e.g., float, double).

TInput

The type of the input data for the model.

TOutput

The type of the output data from the model.

Inheritance

object

ModelEvaluationInput<T, TInput, TOutput>

Inherited Members

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Remarks

For Beginners: This class acts as a container for all the information needed to evaluate a model. It includes the model itself, the data to evaluate it with, and information about how the data is normalized.

- The Model property holds the actual machine learning model to be evaluated. - The InputData property contains the data used for evaluation, including inputs and expected outputs. - The NormInfo property holds information about how the data has been normalized, which is important for interpreting the results correctly.

Properties

InputData

Gets or sets the input data used for model evaluation.

public OptimizationInputData<T, TInput, TOutput> InputData { get; set; }

Property Value

OptimizationInputData<T, TInput, TOutput>

Remarks

This includes both the input features and the expected outputs for evaluation.

Model

Gets or sets the machine learning model to be evaluated.

public IFullModel<T, TInput, TOutput>? Model { get; set; }

Property Value

IFullModel<T, TInput, TOutput>

NormInfo

Gets or sets the normalization information for the input data.

public NormalizationInfo<T, TInput, TOutput> NormInfo { get; set; }

Property Value

NormalizationInfo<T, TInput, TOutput>

Remarks

This is crucial for correctly interpreting the model's outputs and calculating accurate metrics.

PredictionTypeOverride

Gets or sets an optional override for the prediction type used when calculating metrics.

public PredictionType? PredictionTypeOverride { get; set; }

Property Value

PredictionType?

Remarks

If this is not provided, evaluators may infer the prediction type from the target values or model configuration.

For Beginners: This tells the evaluator what kind of problem you're solving (classification vs regression), so it can compute the right metrics by default.