ImageRecognitionModel

The light-weight API for solving Image Recognition task with one of the Model Hub models trained on ImageNet dataset.

Constructors

open override fun close()

Releases internal resources.

copy

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

Creates a copy.

evaluate

Evaluates dataset via metric.

predict

open override fun predict(inputData: FloatArray): Int

Predicts the class of inputData.

Predicts labels for all observation in dataset.

predictObject

Predicts object for the given imageFile.

predictSoftly

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

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

predictTopKObjects

Predicts topK objects for the given imageFile.

reshape

open override fun reshape(vararg dims: Long)

Chain-like setter to set up input shape.

imageNetClassLabels

Class labels for ImageNet dataset.

inputDimensions

Input specification for this model.

name

var name: String? = null

Model name.