Code from BasicOptimizer.scala:75 executed in 228.89 seconds (2.401 gc):
val lineSearchInstance: LineSearchStrategy = lineSearchFactory
IterativeTrainer.wrap(trainable)
.setOrientation(orientation())
.setMonitor(new TrainingMonitor() {
override def clear(): Unit = trainingMonitor.clear()
override def log(msg: String): Unit = trainingMonitor.log(msg)
override def onStepFail(currentPoint: Step): Boolean = {
BasicOptimizer.this.onStepFail(trainable, currentPoint)
}
override def onStepComplete(currentPoint: Step): Unit = {
if (0 < logEvery && (0 == currentPoint.iteration % logEvery || currentPoint.iteration < logEvery)) {
val image = currentImage
timelineAnimation += image
val caption = "Iteration " + currentPoint.iteration
out.p(caption + "\n" + out.jpg(image, caption))
}
BasicOptimizer.this.onStepComplete(trainable, currentPoint)
trainingMonitor.onStepComplete(currentPoint)
super.onStepComplete(currentPoint)
}
})
.setTimeout(trainingMinutes, TimeUnit.MINUTES)
.setMaxIterations(trainingIterations)
.setLineSearchFactory((_: CharSequence) => lineSearchInstance)
.setTerminateThreshold(java.lang.Double.NEGATIVE_INFINITY)
.runAndFree
.asInstanceOf[lang.Double]
Reset training subject: 908286397770100
Reset training subject: 908291719101500
Adding measurement afb7791 to history. Total: 0
LBFGS Accumulation History: 1 points
Constructing line search parameters: GD+Trust
th(0)=0.5102303326129913;dx=-6.559880556170697E-9
Armijo: th(2.154434690031884)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
Armijo: th(1.077217345015942)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
Armijo: th(0.3590724483386473)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
Armijo: th(0.08976811208466183)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
Armijo: th(0.017953622416932366)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
WOLFE (weak): th(0.002992270402822061)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
Armijo: th(0.010472946409877214)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
WOLFE (weak): th(0.006732608406349637)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
Armijo: th(0.008602777408113426)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
WOLFE (weak): th(0.0076676929072315315)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
WOLFE (weak): th(0.008135235157672479)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
WOLFE (weak): th(0.008369006282892952)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
Armijo: th(0.008485891845503189)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
WOLFE (weak): th(0.00842744906419807)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
WOLFE (weak): th(0.008456670454850629)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
Armijo: th(0.00847128115017691)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
Armijo: th(0.00846397580251377)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
WOLFE (weak): th(0.008460323128682199)=0.5102303326129913; dx=-6.538932698754571E-9
...skipping 1580 bytes...
98754571E-9 evalInputDelta=0.0
Armijo: th(0.04557833200272036)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
WOLFE (weak): th(0.04102049880244832)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
Armijo: th(0.043299415402584335)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
WOLFE (weak): th(0.04215995710251633)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
Armijo: th(0.04272968625255033)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
Armijo: th(0.04244482167753333)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
WOLFE (weak): th(0.04230238939002483)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
Armijo: th(0.04237360553377908)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
Armijo: th(0.04233799746190195)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
Armijo: th(0.04232019342596339)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
Armijo: th(0.04231129140799411)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
WOLFE (weak): th(0.04230684039900947)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
WOLFE (weak): th(0.042309065903501794)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
WOLFE (weak): th(0.04231017865574795)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
WOLFE (weak): th(0.042310735031871036)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
WOLFE (weak): th(0.042311013219932574)=0.5102303326129913; dx=-6.538932698754571E-9 evalInputDelta=0.0
mu ~= nu (0.042311013219932574): th(0.0)=0.5102303326129913
Fitness changed from 0.5102303326129913 to 0.5102303326129913
Static Iteration Total: 105.7100; Orientation: 0.0588; Line Search: 97.3606
Iteration 2 failed. Error: 0.5102303326129913
Previous Error: 0.0 -> 0.5102303326129913
Optimization terminated 2
Final threshold in iteration 2: 0.5102303326129913 (> -Infinity) after 228.892s (< 720.000s)
0.5102303326129913