decoder

README

Decoder

The decoder package provides standalone decoders that can sample variables from emer network layers.

SoftMax

The SoftMax decoder is the best choice for a 1-hot classification decoder.

Call Init to initialize with number of categories and layers for input.

Call Decode

Documentation

Index

• type SoftMax
  • func (sm *SoftMax) Back()
  • func (sm *SoftMax) Decode(varNm string) int
  • func (sm *SoftMax) Forward()
  • func (sm *SoftMax) Init(ncats, ninputs int)
  • func (sm *SoftMax) InitLayer(ncats int, layers []emer.Layer)
  • func (sm *SoftMax) Input(varNm string)
  • func (sm *SoftMax) Sort()
  • func (sm *SoftMax) Train(targ int)
  • func (sm *SoftMax) ValsTsr(name string) *etensor.Float32
• type Unit

Types

type SoftMax

type SoftMax struct {
	Lrate    float32                     `def:"0.1" desc:"learning rate"`
	Layers   []emer.Layer                `desc:"layers to decode"`
	NCats    int                         `desc:"number of different categories to decode"`
	Units    []Unit                      `desc:"unit values"`
	Sorted   []int                       `` /* 183-byte string literal not displayed */
	NInputs  int                         `desc:"number of inputs -- total sizes of layer inputs"`
	Inputs   []float32                   `desc:"input values, copied from layers"`
	Targ     int                         `desc:"current target index of correct category"`
	ValsTsrs map[string]*etensor.Float32 `view:"-" desc:"for holding layer values"`
	Weights  etensor.Float32             `desc:"synaptic weights: outer loop is units, inner loop is inputs"`
}

SoftMax is a softmax decoder

func (*SoftMax) Back

func (sm *SoftMax) Back()

Back compute the backward error propagation pass

func (*SoftMax) Decode

func (sm *SoftMax) Decode(varNm string) int

Decode decodes the given variable name from layers (forward pass) See Sorted list of indexes for the decoding output -- i.e., Sorted[0] is the most likely -- that is returned here as a convenience.

func (*SoftMax) Forward

func (sm *SoftMax) Forward()

Forward compute the forward pass from input

func (*SoftMax) Init

func (sm *SoftMax) Init(ncats, ninputs int)

Init initializes detector with number of categories and number of inputs

func (*SoftMax) InitLayer

func (sm *SoftMax) InitLayer(ncats int, layers []emer.Layer)

InitLayer initializes detector with number of categories and layers

func (*SoftMax) Input

func (sm *SoftMax) Input(varNm string)

Input grabs the input from given variable in layers

func (*SoftMax) Sort

func (sm *SoftMax) Sort()

Sort updates Sorted indexes of the current Unit category activations sorted from highest to lowest. i.e., the 0-index value has the strongest decoded output category, 1 the next-strongest, etc.

func (*SoftMax) Train

func (sm *SoftMax) Train(targ int)

Train trains the decoder with given target correct answer (0..NCats-1)

func (*SoftMax) ValsTsr

func (sm *SoftMax) ValsTsr(name string) *etensor.Float32

ValsTsr gets value tensor of given name, creating if not yet made

type Unit

type Unit struct {
	Act float32 `desc:"final activation = e^Ge / sum e^Ge"`
	Net float32 `desc:"net input = sum x * w"`
	Exp float32 `desc:"exp(Net)"`
}

Unit has variables for decoder unit