Package org.jetbrains.kotlinx.dl.dataset.embedded
Functions
Returns paths to images and its labels for the Cifar'10 dataset.
Returns path to images of the Dogs-vs-Cats dataset.
Returns path to images of the subset of the Dogs-vs-Cats dataset.
Loads images from archiveName to heap memory and applies basic normalization preprocessing.
Loads labels from pathToLabels csv file to heap memory and converts to Floats.
Loads labels from pathToLabels csv file to heap memory and converts to Floats, after that it sorts it to have the same order as image files.
Extracts Fashion Mnist images from archivePath.
Extracts Fashion Mnist labels from archivePath with number of classes numClasses.
Extracts (Fashion) Mnist images from archivePath.
Extracts (Fashion) Mnist labels from archivePath with number of classes numClasses.
Loads the Fashion-MNIST dataset.
Returns path to sound data files from Free Spoken Digits Dataset.
Loads the Free Spoken Digits Dataset. This is a dataset of wav sound files of the 10 digits spoken by different people many times each. The test set officially consists of the first 10% of the recordings. Recordings numbered 0-4 (inclusive) are in the test and 5-49 are in the training set.
Loads the MNIST dataset. This is a dataset of 60,000 28x28 grayscale images of the 10 digits, along with a test set of 10,000 images. More info can be found at the MNIST homepage.
Loads the MNIST 3D dataset. This is a dataset of 10,000 16x16x16 grayscale 3D images of the 10 digits, along with a test set of 2,000 3D images.
Properties
Data size of Free Spoken Digits Dataset.