ImageRecognitionModel

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

Constructors

jvm

fun ImageRecognitionModel(internalModel: InferenceModel, inputColorMode: ColorMode, channelsFirst: Boolean, preprocessor: Operation<Pair<FloatArray, TensorShape>, Pair<FloatArray, TensorShape>> = Identity(), modelKindDescription: String? = null)

jvm

open override fun close()

copy

jvm

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

predict

jvm

open override fun predict(inputData: FloatArray): Int

predictObject

jvm

Predicts object for the given imageFile. Default preprocessing Operation is applied to an image.

Predicts object for the given image. Default preprocessing Operation is applied to an image.

predictSoftly

jvm

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

predictTopKObjects

jvm

Predicts topK objects for the given imageFile. Default preprocessing Operation is applied to an image.

Predicts topK objects for the given image. Default preprocessing Operation is applied to an image.

reshape

jvm

open override fun reshape(vararg dims: Long)

summary

jvm

open override fun summary(): ModelSummary

inputDimensions

jvm