func (s *LogSoftmaxLayer) ApplyR(v autofunc.RVector, in autofunc.RResult) autofunc.RResult {
return autofunc.PoolR(in, func(in autofunc.RResult) autofunc.RResult {
// See comment in Apply() for details on how this works.
maxIdx := maxVecIdx(in.Output())
maxValue := autofunc.SliceR(in, maxIdx, maxIdx+1)
exponents := autofunc.AddFirstR(in, autofunc.ScaleR(maxValue, -1))
expSum := autofunc.SumAllR(autofunc.Exp{}.ApplyR(v, exponents))
expLog := autofunc.Log{}.ApplyR(v, expSum)
denomLog := autofunc.AddR(expLog, maxValue)
return autofunc.AddFirstR(in, autofunc.ScaleR(denomLog, -1))
})
}
func (_ SigmoidCECost) CostR(v autofunc.RVector, x linalg.Vector,
a autofunc.RResult) autofunc.RResult {
logsig := autofunc.LogSigmoid{}
log := logsig.ApplyR(v, a)
invLog := logsig.ApplyR(v, autofunc.ScaleR(a, -1))
xVar := autofunc.NewRVariable(&autofunc.Variable{x}, v)
oneMinusX := autofunc.AddScalerR(autofunc.ScaleR(xVar, -1), 1)
sums := autofunc.AddR(autofunc.MulR(xVar, log), autofunc.MulR(oneMinusX, invLog))
return autofunc.ScaleR(autofunc.SumAllR(sums), -1)
}
func (_ CrossEntropyCost) CostR(v autofunc.RVector, x linalg.Vector,
a autofunc.RResult) autofunc.RResult {
return autofunc.PoolR(a, func(a autofunc.RResult) autofunc.RResult {
xVar := autofunc.NewRVariable(&autofunc.Variable{x}, autofunc.RVector{})
logA := autofunc.Log{}.ApplyR(v, a)
oneMinusA := autofunc.AddScalerR(autofunc.ScaleR(a, -1), 1)
oneMinusX := autofunc.AddScalerR(autofunc.ScaleR(xVar, -1), 1)
log1A := autofunc.Log{}.ApplyR(v, oneMinusA)
errorVec := autofunc.AddR(autofunc.MulR(xVar, logA),
autofunc.MulR(oneMinusX, log1A))
return autofunc.ScaleR(autofunc.SumAllR(errorVec), -1)
})
}
func (d *DropoutLayer) ApplyR(v autofunc.RVector, in autofunc.RResult) autofunc.RResult {
if d.Training {
mask := d.dropoutMask(len(in.Output()))
maskVar := autofunc.NewRVariable(mask, v)
return autofunc.MulR(in, maskVar)
} else {
return autofunc.ScaleR(in, d.KeepProbability)
}
}
func (r *RegularizingCost) CostR(v autofunc.RVector, a linalg.Vector,
x autofunc.RResult) autofunc.RResult {
regFunc := autofunc.SquaredNorm{}
cost := r.CostFunc.CostR(v, a, x)
for _, variable := range r.Variables {
norm := regFunc.ApplyR(v, autofunc.NewRVariable(variable, v))
cost = autofunc.AddR(cost, autofunc.ScaleR(norm, r.Penalty))
}
return cost
}
// ApplyBlockR applies the block to an input.
func (g *GRU) ApplyBlockR(rv autofunc.RVector, s []RState, in []autofunc.RResult) BlockRResult {
stateVars, stateRes := PoolVecRStates(s)
var gateInputs []autofunc.RResult
for i, x := range stateRes {
gateInputs = append(gateInputs, in[i], x)
}
n := len(in)
gateInput := autofunc.ConcatR(gateInputs...)
stateIn := autofunc.ConcatR(stateRes...)
resetMask := g.resetGate.BatchR(rv, gateInput, n)
updateMask := g.updateGate.BatchR(rv, gateInput, n)
maskedByReset := autofunc.MulR(resetMask, stateIn)
inputValue := autofunc.PoolSplitR(n, maskedByReset,
func(newStates []autofunc.RResult) autofunc.RResult {
var newGateInputs []autofunc.RResult
for i, input := range in {
newGateInputs = append(newGateInputs, input, newStates[i])
}
newIn := autofunc.ConcatR(newGateInputs...)
return g.inputValue.BatchR(rv, newIn, n)
})
newState := autofunc.PoolR(updateMask, func(umask autofunc.RResult) autofunc.RResult {
updateComplement := autofunc.AddScalerR(autofunc.ScaleR(umask, -1), 1)
return autofunc.AddR(autofunc.MulR(umask, stateIn),
autofunc.MulR(updateComplement, inputValue))
})
return &gruRResult{
InStates: stateVars,
Output: newState,
}
}
func (r *RescaleLayer) ApplyR(v autofunc.RVector, in autofunc.RResult) autofunc.RResult {
return autofunc.ScaleR(autofunc.AddScalerR(in, r.Bias), r.Scale)
}
func (_ HyperbolicTangent) ApplyR(v autofunc.RVector, r autofunc.RResult) autofunc.RResult {
stretched := autofunc.ScaleR(autofunc.Sigmoid{}.ApplyR(v, autofunc.ScaleR(r, 2)), 2)
return autofunc.AddScalerR(stretched, -1)
}
func (_ DotCost) CostR(v autofunc.RVector, x linalg.Vector,
a autofunc.RResult) autofunc.RResult {
xVar := autofunc.NewRVariable(&autofunc.Variable{x}, v)
return autofunc.ScaleR(autofunc.SumAllR(autofunc.MulR(xVar, a)), -1)
}