Code from BasicOptimizer.scala:75 executed in 245.42 seconds (2.346 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: 910132135767800
Reset training subject: 910137173895800
Adding measurement 23159091 to history. Total: 0
LBFGS Accumulation History: 1 points
Constructing line search parameters: GD+Trust
th(0)=1.1233377009630203;dx=-3.02404573146465E-8
Armijo: th(2.154434690031884)=1.1233377009630203; dx=-3.024045724863911E-8 evalInputDelta=0.0
Armijo: th(1.077217345015942)=1.1233377009630203; dx=-3.024045728443829E-8 evalInputDelta=0.0
Armijo: th(0.3590724483386473)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
Armijo: th(0.08976811208466183)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
Armijo: th(0.017953622416932366)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
WOLFE (weak): th(0.002992270402822061)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
Armijo: th(0.010472946409877214)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
Armijo: th(0.006732608406349637)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
Armijo: th(0.004862439404585849)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
Armijo: th(0.003927354903703955)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
WOLFE (weak): th(0.0034598126532630075)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
Armijo: th(0.003693583778483481)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
WOLFE (weak): th(0.0035766982158732443)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
WOLFE (weak): th(0.0036351409971783627)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
WOLFE (weak): th(0.003664362387830922)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
Armijo: th(0.0036789730831572015)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
Armijo: th(0.0036716677354940615)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
WOLFE (weak): th(0.0036680150616624917)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
...skipping 1657 bytes...
-3.02404573146465E-8 evalInputDelta=0.0
Armijo: th(0.01977399959728679)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
WOLFE (weak): th(0.01779659963755811)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
Armijo: th(0.018785299617422452)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
WOLFE (weak): th(0.018290949627490283)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
Armijo: th(0.018538124622456367)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
Armijo: th(0.018414537124973325)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
WOLFE (weak): th(0.018352743376231804)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
Armijo: th(0.018383640250602566)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
Armijo: th(0.018368191813417187)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
Armijo: th(0.018360467594824494)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
Armijo: th(0.01835660548552815)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
WOLFE (weak): th(0.01835467443087998)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
WOLFE (weak): th(0.018355639958204065)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
WOLFE (weak): th(0.018356122721866108)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
WOLFE (weak): th(0.018356364103697127)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
WOLFE (weak): th(0.01835648479461264)=1.1233377009630203; dx=-3.02404573146465E-8 evalInputDelta=0.0
mu ~= nu (0.01835648479461264): th(0.0)=1.1233377009630203
Fitness changed from 1.1233377009630203 to 1.1233377009630203
Static Iteration Total: 111.0027; Orientation: 0.0639; Line Search: 102.2164
Iteration 2 failed. Error: 1.1233377009630203
Previous Error: 0.0 -> 1.1233377009630203
Optimization terminated 2
Final threshold in iteration 2: 1.1233377009630203 (> -Infinity) after 245.417s (< 720.000s)
1.1233377009630203