mnist

package

v0.0.0-...-7ce53e0 Latest Latest Go to latest Published: May 31, 2022 License: MIT Imports: 7 Imported by: 0

Details

Valid go.mod file

The Go module system was introduced in Go 1.11 and is the official dependency management solution for Go.
Redistributable license

Redistributable licenses place minimal restrictions on how software can be used, modified, and redistributed.
Tagged version

Modules with tagged versions give importers more predictable builds.
Stable version

When a project reaches major version v1 it is considered stable.
Learn more about best practices

package mnist handles the mnist data set

View Source

const (

	// Width of the input tensor / picture
	Width = 28
	// Height of the input tensor / picture
	Height = 28
)

This section is empty.

func NewMnistDataset(dataloc string, epochs int) dataset.Dataset

NewMnistDataset wil create a new MnistDataset instance.

type Label uint8

Label is a digit label in 0 to 9

type MnistDataset struct {
	// contains filtered or unexported fields
}

MnistDataset is the object that describes the mnist dataset.

func (fd *MnistDataset) Epochs() int

Epochs returns the number of epochs that should run during training.

func (fd *MnistDataset) TestRatio() float64

TestRatio returns how much can of the dataset can be used for validating the network.

func (fd *MnistDataset) XY() (tensor.Tensor, tensor.Tensor, error)

XY returns the data to be trained.

type RawImage []byte

Image holds the pixel intensities of an image. 255 is foreground (black), 0 is background (white).