MnistDataLoader<T>
Models & Types · AiDotNet.Data.Vision.Benchmarks
Loads the MNIST handwritten digit classification dataset (60k train / 10k test, 28x28 grayscale).
Inheritance: DataLoaderBase<T> → InputOutputDataLoaderBase<T, Tensor<T>, Tensor<T>> → MnistDataLoader<T>
For Beginners
This is the easiest way to get started with image classification:
How It Works
MNIST is the “Hello World” of machine learning - a dataset of handwritten digits (0-9). Each image is 28x28 pixels, grayscale, with a corresponding digit label.
Constructors
| Constructor | Summary |
|---|---|
MnistDataLoader(MnistDataLoaderOptions options) |
Creates a new MNIST data loader. |
Properties
| Property | Summary |
|---|---|
int FeatureCount { get; } |
|
int NumClasses { get; } |
Number of classes (digits 0-9). |
int OutputDimension { get; } |
|
int TotalCount { get; } |
|
string Description { get; } |
|
string Name { get; } |
Methods
| Method | Summary |
|---|---|
ValueTuple<IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>, IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>, IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>> Split(double trainRatio, double validationRatio, int? seed) |