conv1x1

Documentation

Overview

Package conv1x1 implements a 1-dimensional 1-kernel convolution model

Index

• type Config
• type Model
  • func New[T float.DType](config Config) *Model
  • func (m *Model) Forward(xs ...mat.Tensor) []mat.Tensor

Types

type Config

type Config struct {
	InputChannels  int
	OutputChannels int
}

Config provides configuration parameters for Model.

type Model

type Model struct {
	nn.Module
	Config Config
	W      *nn.Param
	B      *nn.Param
}

Model is a superficial depth-wise 1-dimensional convolution model. The following values are fixed: kernel size = 1; stride = 1; padding = 0,

func New

func New[T float.DType](config Config) *Model

New returns a new Model.

func (*Model) Forward

func (m *Model) Forward(xs ...mat.Tensor) []mat.Tensor

Forward performs the forward step. Each "x" is a channel.