use of com.simiacryptus.mindseye.opt.IterativeTrainer in project MindsEye by SimiaCryptus.
the class StyleTransfer method styleTransfer.
/**
* Style transfer buffered image.
*
* @param server the server
* @param log the log
* @param canvasImage the canvas image
* @param styleParameters the style parameters
* @param trainingMinutes the training minutes
* @param measureStyle the measure style
* @return the buffered image
*/
public BufferedImage styleTransfer(final StreamNanoHTTPD server, @Nonnull final NotebookOutput log, final BufferedImage canvasImage, final StyleSetup<T> styleParameters, final int trainingMinutes, final NeuralSetup measureStyle) {
BufferedImage result = ArtistryUtil.logExceptionWithDefault(log, () -> {
log.p("Input Content:");
log.p(log.image(styleParameters.contentImage, "Content Image"));
log.p("Style Content:");
styleParameters.styleImages.forEach((file, styleImage) -> {
log.p(log.image(styleImage, file));
});
log.p("Input Canvas:");
log.p(log.image(canvasImage, "Input Canvas"));
System.gc();
Tensor canvas = Tensor.fromRGB(canvasImage);
TestUtil.monitorImage(canvas, false, false);
log.p("Input Parameters:");
log.code(() -> {
return ArtistryUtil.toJson(styleParameters);
});
Trainable trainable = log.code(() -> {
PipelineNetwork network = fitnessNetwork(measureStyle);
network.setFrozen(true);
ArtistryUtil.setPrecision(network, styleParameters.precision);
TestUtil.instrumentPerformance(network);
if (null != server)
ArtistryUtil.addLayersHandler(network, server);
return new ArrayTrainable(network, 1).setVerbose(true).setMask(true).setData(Arrays.asList(new Tensor[][] { { canvas } }));
});
log.code(() -> {
@Nonnull ArrayList<StepRecord> history = new ArrayList<>();
new IterativeTrainer(trainable).setMonitor(TestUtil.getMonitor(history)).setOrientation(new TrustRegionStrategy() {
@Override
public TrustRegion getRegionPolicy(final Layer layer) {
return new RangeConstraint().setMin(1e-2).setMax(256);
}
}).setIterationsPerSample(100).setLineSearchFactory(name -> new BisectionSearch().setSpanTol(1e-1).setCurrentRate(1e6)).setTimeout(trainingMinutes, TimeUnit.MINUTES).setTerminateThreshold(Double.NEGATIVE_INFINITY).runAndFree();
return TestUtil.plot(history);
});
return canvas.toImage();
}, canvasImage);
log.p("Output Canvas:");
log.p(log.image(result, "Output Canvas"));
return result;
}
use of com.simiacryptus.mindseye.opt.IterativeTrainer in project MindsEye by SimiaCryptus.
the class TrainingTester method trainGD.
/**
* Train gd list.
*
* @param log the log
* @param trainable the trainable
* @return the list
*/
@Nonnull
public List<StepRecord> trainGD(@Nonnull final NotebookOutput log, final Trainable trainable) {
log.p("First, we train using basic gradient descent method apply weak line search conditions.");
@Nonnull final List<StepRecord> history = new ArrayList<>();
@Nonnull final TrainingMonitor monitor = TrainingTester.getMonitor(history);
try {
log.code(() -> {
return new IterativeTrainer(trainable).setLineSearchFactory(label -> new ArmijoWolfeSearch()).setOrientation(new GradientDescent()).setMonitor(monitor).setTimeout(30, TimeUnit.SECONDS).setMaxIterations(250).setTerminateThreshold(0).runAndFree();
});
} catch (Throwable e) {
if (isThrowExceptions())
throw new RuntimeException(e);
}
return history;
}
use of com.simiacryptus.mindseye.opt.IterativeTrainer in project MindsEye by SimiaCryptus.
the class TrainingTester method trainMagic.
/**
* Train lbfgs list.
*
* @param log the log
* @param trainable the trainable
* @return the list
*/
@Nonnull
public List<StepRecord> trainMagic(@Nonnull final NotebookOutput log, final Trainable trainable) {
log.p("Now we train using an experimental optimizer:");
@Nonnull final List<StepRecord> history = new ArrayList<>();
@Nonnull final TrainingMonitor monitor = TrainingTester.getMonitor(history);
try {
log.code(() -> {
return new IterativeTrainer(trainable).setLineSearchFactory(label -> new StaticLearningRate(1.0)).setOrientation(new RecursiveSubspace() {
@Override
public void train(@Nonnull TrainingMonitor monitor, Layer macroLayer) {
@Nonnull Tensor[][] nullData = { { new Tensor() } };
@Nonnull BasicTrainable inner = new BasicTrainable(macroLayer);
@Nonnull ArrayTrainable trainable1 = new ArrayTrainable(inner, nullData);
inner.freeRef();
new IterativeTrainer(trainable1).setOrientation(new QQN()).setLineSearchFactory(n -> new QuadraticSearch().setCurrentRate(n.equals(QQN.CURSOR_NAME) ? 1.0 : 1e-4)).setMonitor(new TrainingMonitor() {
@Override
public void log(String msg) {
monitor.log("\t" + msg);
}
}).setMaxIterations(getIterations()).setIterationsPerSample(getIterations()).runAndFree();
trainable1.freeRef();
for (@Nonnull Tensor[] tensors : nullData) {
for (@Nonnull Tensor tensor : tensors) {
tensor.freeRef();
}
}
}
}).setMonitor(monitor).setTimeout(30, TimeUnit.SECONDS).setIterationsPerSample(100).setMaxIterations(250).setTerminateThreshold(0).runAndFree();
});
} catch (Throwable e) {
if (isThrowExceptions())
throw new RuntimeException(e);
}
return history;
}
use of com.simiacryptus.mindseye.opt.IterativeTrainer in project MindsEye by SimiaCryptus.
the class ImageClassifier method deepDream.
/**
* Deep dream.
*
* @param log the log
* @param image the image
* @param targetCategoryIndex the target category index
* @param totalCategories the total categories
* @param config the config
* @param network the network
* @param lossLayer the loss layer
* @param targetValue the target value
*/
public void deepDream(@Nonnull final NotebookOutput log, final Tensor image, final int targetCategoryIndex, final int totalCategories, Function<IterativeTrainer, IterativeTrainer> config, final Layer network, final Layer lossLayer, final double targetValue) {
@Nonnull List<Tensor[]> data = Arrays.<Tensor[]>asList(new Tensor[] { image, new Tensor(1, 1, totalCategories).set(targetCategoryIndex, targetValue) });
log.code(() -> {
for (Tensor[] tensors : data) {
ImageClassifier.log.info(log.image(tensors[0].toImage(), "") + tensors[1]);
}
});
log.code(() -> {
@Nonnull ArrayList<StepRecord> history = new ArrayList<>();
@Nonnull PipelineNetwork clamp = new PipelineNetwork(1);
clamp.add(new ActivationLayer(ActivationLayer.Mode.RELU));
clamp.add(new LinearActivationLayer().setBias(255).setScale(-1).freeze());
clamp.add(new ActivationLayer(ActivationLayer.Mode.RELU));
clamp.add(new LinearActivationLayer().setBias(255).setScale(-1).freeze());
@Nonnull PipelineNetwork supervised = new PipelineNetwork(2);
supervised.wrap(lossLayer, supervised.add(network.freeze(), supervised.wrap(clamp, supervised.getInput(0))), supervised.getInput(1));
// TensorList[] gpuInput = data.stream().map(data1 -> {
// return CudnnHandle.apply(gpu -> {
// Precision precision = Precision.Float;
// return CudaTensorList.wrap(gpu.getPtr(TensorArray.wrap(data1), precision, MemoryType.Managed), 1, image.getDimensions(), precision);
// });
// }).toArray(i -> new TensorList[i]);
// @Nonnull Trainable trainable = new TensorListTrainable(supervised, gpuInput).setVerbosity(1).setMask(true);
@Nonnull Trainable trainable = new ArrayTrainable(supervised, 1).setVerbose(true).setMask(true, false).setData(data);
config.apply(new IterativeTrainer(trainable).setMonitor(getTrainingMonitor(history, supervised)).setOrientation(new QQN()).setLineSearchFactory(name -> new ArmijoWolfeSearch()).setTimeout(60, TimeUnit.MINUTES)).setTerminateThreshold(Double.NEGATIVE_INFINITY).runAndFree();
return TestUtil.plot(history);
});
}
use of com.simiacryptus.mindseye.opt.IterativeTrainer in project MindsEye by SimiaCryptus.
the class TrainingTester method trainCjGD.
/**
* Train cj gd list.
*
* @param log the log
* @param trainable the trainable
* @return the list
*/
@Nonnull
public List<StepRecord> trainCjGD(@Nonnull final NotebookOutput log, final Trainable trainable) {
log.p("First, we use a conjugate gradient descent method, which converges the fastest for purely linear functions.");
@Nonnull final List<StepRecord> history = new ArrayList<>();
@Nonnull final TrainingMonitor monitor = TrainingTester.getMonitor(history);
try {
log.code(() -> {
return new IterativeTrainer(trainable).setLineSearchFactory(label -> new QuadraticSearch()).setOrientation(new GradientDescent()).setMonitor(monitor).setTimeout(30, TimeUnit.SECONDS).setMaxIterations(250).setTerminateThreshold(0).runAndFree();
});
} catch (Throwable e) {
if (isThrowExceptions())
throw new RuntimeException(e);
}
return history;
}
Aggregations