predictSoftly

fun predictSoftly(dataset: Dataset, batchSize: Int, callback: Callback): Array<FloatArray>
Content copied to clipboard

Generates output predictions for the input samples. Each prediction is a vector of probabilities instead of specific class in predict method.

Return

Array of labels. All labels are vectors that represents the probability distributions of a list of potential outcomes. The length is equal to the Number of samples on the dataset.

Parameters

dataset

Data to predict on.

batchSize

Number of samples per batch of computation.

callback

Callback to be used during prediction phase.

abstract fun predictSoftly(dataset: Dataset, batchSize: Int, callbacks: List<Callback> = listOf()): Array<FloatArray>
Content copied to clipboard

Generates output predictions for the input samples. Each prediction is a vector of probabilities instead of specific class in predict method.

Return

Array of labels. All labels are vectors that represents the probability distributions of a list of potential outcomes. The length is equal to the Number of samples on the dataset.

Parameters

dataset

Data to predict on.

batchSize

Number of samples per batch of computation.

callbacks

Callbacks to be used during prediction phase.