convolution

Documentation

Index

• type Config
• type Model
  • func New(config Config) *Model
  • func (m *Model) Forward(xs ...ag.Node) []ag.Node

Types

type Config

type Config struct {
	KernelSizeX    int
	KernelSizeY    int
	XStride        int
	YStride        int
	InputChannels  int
	OutputChannels int
	Mask           []int
	Activation     ag.OpName
}

Config provides configuration settings for a convolution Model.

type Model

type Model struct {
	nn.BaseModel
	Config Config
	K      []nn.Param `spago:"type:weights"`
	B      []nn.Param `spago:"type:biases"`
}

Model contains the serializable parameters for a convolutional neural network model.

func New

func New(config Config) *Model

New returns a new convolution Model, initialized according to the given configuration.

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.