InferenceModel

The basic class for all models which defines the basic interfaces required for inference tasks only.

Constructors

InferenceModel

abstract fun close()

copy

abstract fun copy(copiedModelName: String? = null, saveOptimizerState: Boolean = false, copyWeights: Boolean = true): TensorFlowInferenceModel

Creates a copy.

evaluate

Evaluates dataset via metric.

predict

abstract fun predict(inputData: FloatArray): Int

Predicts the class of inputData.

Predicts labels for all observation in dataset.

predictSoftly

abstract fun predictSoftly(inputData: FloatArray, predictionTensorName: String = ""): FloatArray

Predicts vector of probabilities instead of specific class in predict method.

reshape

abstract fun reshape(vararg dims: Long)

Chain-like setter to set up input shape.

inputDimensions

Input specification for this model.

name

var name: String? = null

Model name.

TensorFlowInferenceModel

ImageRecognitionModel