batchnorm

Documentation

Index

• type Model
  • func New(size int) *Model
  • func NewWithMomentum(size int, momentum float64) *Model
  • func (m *Model) NewProc(ctx nn.Context) nn.Processor
• type Processor
  • func (p *Processor) Forward(xs ...ag.Node) []ag.Node
  • func (p *Processor) Mean(xs []ag.Node) ag.Node
  • func (p *Processor) StdDev(meanVector ag.Node, xs []ag.Node) ag.Node

Types

type Model

type Model struct {
	W        *nn.Param `type:"weights"`
	B        *nn.Param `type:"biases"`
	Mean     *nn.Param `type:"undefined"`
	StdDev   *nn.Param `type:"undefined"`
	Momentum *nn.Param `type:"undefined"`
}

Model contains the serializable parameters.

func New

func New(size int) *Model

New returns a new model with the supplied size and default momentum

func NewWithMomentum

func NewWithMomentum(size int, momentum float64) *Model

New returns a new model with supplied size and momentum

func (*Model) NewProc

func (m *Model) NewProc(ctx nn.Context) nn.Processor

NewProc returns a new processor to execute the forward step.

type Processor

type Processor struct {
	nn.BaseProcessor
	// contains filtered or unexported fields
}

func (*Processor) Forward

func (p *Processor) Forward(xs ...ag.Node) []ag.Node

Forward performs the forward step for each input and returns the result.

func (*Processor) Mean

func (p *Processor) Mean(xs []ag.Node) ag.Node

func (*Processor) StdDev

func (p *Processor) StdDev(meanVector ag.Node, xs []ag.Node) ag.Node