Code from BasicOptimizer.scala:75 executed in 6566.50 seconds (392.948 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: 1356595064296800
Reset training subject: 1357082714602700
Adding measurement 2762bd70 to history. Total: 0
LBFGS Accumulation History: 1 points
Constructing line search parameters: GD+Trust
th(0)=67.65549810230732;dx=-8.82386524190308E-6
New Minimum: 67.65549810230732 > 67.65549575537443
WOLFE (weak): th(2.154434690031884)=67.65549575537443; dx=-8.81940112365426E-6 evalInputDelta=2.346932888031006E-6
New Minimum: 67.65549575537443 > 67.65548592060804
WOLFE (weak): th(4.308869380063768)=67.65548592060804; dx=-8.819398191757341E-6 evalInputDelta=1.2181699275970459E-5
New Minimum: 67.65548592060804 > 67.65544886887074
WOLFE (weak): th(12.926608140191302)=67.65544886887074; dx=-8.819392473810712E-6 evalInputDelta=4.9233436584472656E-5
New Minimum: 67.65544886887074 > 67.65530490875244
WOLFE (weak): th(51.70643256076521)=67.65530490875244; dx=-8.819371157834872E-6 evalInputDelta=1.9319355487823486E-4
New Minimum: 67.65530490875244 > 67.65452904254198
WOLFE (weak): th(258.53216280382605)=67.65452904254198; dx=-8.819281097378201E-6 evalInputDelta=9.690597653388977E-4
New Minimum: 67.65452904254198 > 67.64966751635075
WOLFE (weak): th(1551.1929768229563)=67.64966751635075; dx=-8.818641528634363E-6 evalInputDelta=0.005830585956573486
New Minimum: 67.64966751635075 > 67.61468461155891
WOLFE (weak): th(10858.350837760694)=67.61468461155891; dx=-8.813783539948666E-6 evalInputDelta=0.04081349074840546
New Minimum: 67.61468461155891 > 67.32978339493275
WOLFE (weak): th(86866.80670208555)=67.32978339493275; dx=-8.774081881097135E-6 evalInputDelta=0.32571470737457275
New Minimum: 67.32978339493275 > 64.79137399792671
WOLFE (weak): th(781801.26031877)=64.79137399792671; dx=-8.403159701115219E-6 evalInputDelta=2.8641241043806076
New Minimum: 64.79137399792671 > 46.9392009600997
END: th(7818012.6031877)=46.9392009600997; dx=-3.860731738047514E-6 evalInputDelta=20.716297142207623
Fitness changed from 67.65549810230732 to 46.9392009600997
Iteration 1 complete. Error: 46.9392009600997 Total: 6565.2440; Orientation: 1.2743; Line Search: 5116.1812
<a id="p-3"></a>Iteration 1
<a id="p-2"></a>
Final threshold in iteration 1: 46.9392009600997 (> -Infinity) after 6566.491s (< 3600.000s)
46.9392009600997