Deep.Net


Mnist

Namespace: Datasets

Module containing functions to load the MNIST dataset.

Functions and values

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

Loads the MNIST 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 -> MnistRawT

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

Fork me on GitHub