mnist

package
v0.0.0-...-f96ffc0 Latest Latest
Warning

This package is not in the latest version of its module.

Go to latest
Published: Jul 11, 2015 License: GPL-3.0 Imports: 6 Imported by: 0

Documentation

Overview

Package mnist loads the MNist dataset of handwritten digits.

Index

Constants

View Source
const (
	Scale   = 1
	Rotate  = 2
	Elastic = 4
)

supported types of distortion

Variables

This section is empty.

Functions

This section is empty.

Types

type Classify

type Classify struct{}

classification function

func (Classify) Apply

func (Classify) Apply(out, class blas.Matrix) blas.Matrix

type Loader

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

func (*Loader) Config

func (*Loader) Config() *network.Config

default configuration

func (*Loader) CreateNetwork

func (*Loader) CreateNetwork(cfg *network.Config, d *network.Dataset) *network.Network

func (*Loader) Debug

func (l *Loader) Debug(on bool)

func (*Loader) Distort

func (l *Loader) Distort(in, out blas.Matrix, mask int, severity float32)

Distort method is used to apply distortions to a batch of images. mask of -1 indicates all distortions are to be applied.

func (*Loader) DistortTypes

func (l *Loader) DistortTypes() []network.Distortion

DistortTypes returns the supported types of distortions

func (Loader) Load

func (Loader) Load(samples int) (*network.Dataset, error)

Load function loads and returns the iris dataset.

func (*Loader) Release

func (l *Loader) Release()

type Loader2

type Loader2 struct{ *Loader }

Alternative configuration

func (Loader2) Config

func (Loader2) Config() *network.Config

func (Loader2) CreateNetwork

func (Loader2) CreateNetwork(cfg *network.Config, d *network.Dataset) *network.Network

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL