Deep.Net


Cifar10

Namespace: Datasets

Module containing functions to load the Cifar 10 dataset from the binary version. The dataset can be found at https://www.cs.toronto.edu/~kriz/cifar.html

Functions and values

Function or valueDescription
load directory valRatio
Signature: directory:string -> valRatio:float<MeasureOne> -> TrnValTst<InputTargetSampleT>

Loads the Cifar10 dataset and splits the original training set into a training and validation set using the ratio valRatio (between 0 and 1) for the validation set.

loadRaw directory
Signature: directory:string -> CifarRawT

Loads the Cifar10 dataset and returns it as type MnistRawT. Use only if you need raw access to the Cifar10 data.

Fork me on GitHub