SavedModel

open class SavedModel : TensorFlowInferenceModel

Inference model built on SavedModelBundle format to predict on images.

Constructors

SavedModel

fun SavedModel()

Types

Companion

object Companion

Functions

open override fun close()

Closes internal resources: session and kGraph.

copy

open override fun copy(copiedModelName: String?, saveOptimizerState: Boolean, copyWeights: Boolean): TensorFlowInferenceModel

Creates a copy.

evaluate

fun evaluate(dataset: Dataset, metric: Metrics): Double

Evaluates dataset via metric.

graphToString

fun graphToString(): String

Forms the graph description in string format.

input

fun input(inputOp: Input)

Chain-like setter to set up inputOp.

output

fun output(outputOp: Output)

Chain-like setter to set up outputOp.

predict

open override fun predict(inputData: FloatArray): Int

Generates output prediction for the input sample.

fun predict(dataset: Dataset): List<Int>

Predicts labels for all observation in dataset.

fun predict(inputData: FloatArray, inputTensorName: String, outputTensorName: String): Int

Predicts the class of inputData.

fun predict(dataset: OnHeapDataset, inputTensorName: String, outputTensorName: String): List<Int>

Predicts labels for all observation in dataset.

predictSoftly

open override fun predictSoftly(inputData: FloatArray, predictionTensorName: String): FloatArray

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

reshape

open override fun reshape(vararg dims: Long)

Chain-like setter to set up input shape.

toString

open override fun toString(): String

Properties

inputDimensions

open override val inputDimensions: LongArray

Input specification for this model.

isModelInitialized

var isModelInitialized: Boolean = false

Is true when model is initialized.

kGraph

lateinit var kGraph: KGraph

TensorFlow wrapped computational graph.

name

var name: String? = null

Model name.

shape

lateinit var shape: LongArray

Data shape for prediction.