linear

Documentation

Index

• type Model
  • func New(in, out int, options ...Option) *Model
  • func (m *Model) Forward(xs ...ag.Node) []ag.Node
• type Option
  • func BiasGrad(enable bool) Option

Types

type Model

type Model struct {
	nn.BaseModel
	W nn.Param `spago:"type:weights"`
	B nn.Param `spago:"type:biases"`
}

Model contains the serializable parameters.

func New

func New(in, out int, options ...Option) *Model

New returns a new model with parameters initialized to zeros.

func (*Model) Forward

func (m *Model) Forward(xs ...ag.Node) []ag.Node

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

type Option

type Option func(*Model)

Option allows to configure a new Model with your specific needs.

func BiasGrad

func BiasGrad(enable bool) Option

BiasGrad allows you to enable or disable gradient propagation on bias (enabled by default).