Package org.jetbrains.kotlinx.dl.dataset.preprocessor

Helper class to keep widely used shape of image object presented as a 4D tensor (batchSize = 1, width, height, channels). null values are allowed for width, height and channels, indicating that the dimension size is unknown.

This preprocessor defines normalizing operation. Given mean and std for n channels, this operation normalizes each channel of the input array, i.e.

The data preprocessing pipeline presented as Kotlin DSL on receivers.

Basic interface for the data preprocessing.

This preprocessor defines the Rescaling operation. It scales each pixel pixel_i = pixel_i / scalingCoefficient.

Represents the tensor preprocessing stage of the Preprocessing. Consists of the operations implementing Preprocessor which are applied to the tensor one by one.

Computes mean value for each channel of the array. Array size should be divisible by the passed channels number.

Computes mean value for each channel of the provided arrays.

Applies Normalizing preprocessor to the tensor to normalize it with given mean and std values.

Defines preprocessing operations.

Applies Rescaling preprocessor to the tensor to scale each value by a given coefficient.

Computes std value for each channel of the array. Array size should be divisible by the passed channels number.

Computes std value for each channel of the provided arrays.

Defines preprocessing operations on the image.

Defines preprocessing operations on the tensor.