Examples with ArmijoWolfeSearch com.simiacryptus.mindseye.opt.line.ArmijoWolfeSearch used on opensource projects

Example 1 with ArmijoWolfeSearch

use of com.simiacryptus.mindseye.opt.line.ArmijoWolfeSearch in project MindsEye by SimiaCryptus.

the class ImageClassifier method deepDream.

/**
 * Deep dream.
 *
 * @param log   the log
 * @param image the image
 */
public void deepDream(@Nonnull final NotebookOutput log, final Tensor image) {
    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(1);
        supervised.add(getNetwork().freeze(), supervised.wrap(clamp, supervised.getInput(0)));
        // CudaTensorList gpuInput = CudnnHandle.apply(gpu -> {
        // Precision precision = Precision.Float;
        // return CudaTensorList.wrap(gpu.getPtr(TensorArray.wrap(image), precision, MemoryType.Managed), 1, image.getDimensions(), precision);
        // });
        // @Nonnull Trainable trainable = new TensorListTrainable(supervised, gpuInput).setVerbosity(1).setMask(true);
        @Nonnull Trainable trainable = new ArrayTrainable(supervised, 1).setVerbose(true).setMask(true, false).setData(Arrays.<Tensor[]>asList(new Tensor[] { image }));
        new IterativeTrainer(trainable).setMonitor(getTrainingMonitor(history, supervised)).setOrientation(new QQN()).setLineSearchFactory(name -> new ArmijoWolfeSearch()).setTimeout(60, TimeUnit.MINUTES).runAndFree();
        return TestUtil.plot(history);
    });
}

Example 2 with ArmijoWolfeSearch

use of com.simiacryptus.mindseye.opt.line.ArmijoWolfeSearch 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;
}

Example 3 with ArmijoWolfeSearch

use of com.simiacryptus.mindseye.opt.line.ArmijoWolfeSearch 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);
    });
}

Example 4 with ArmijoWolfeSearch

use of com.simiacryptus.mindseye.opt.line.ArmijoWolfeSearch in project MindsEye by SimiaCryptus.

the class TrainingTester method trainLBFGS.

/**
 * Train lbfgs list.
 *
 * @param log       the log
 * @param trainable the trainable
 * @return the list
 */
@Nonnull
public List<StepRecord> trainLBFGS(@Nonnull final NotebookOutput log, final Trainable trainable) {
    log.p("Next, we apply the same optimization using L-BFGS, which is nearly ideal for purely second-order or quadratic 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 ArmijoWolfeSearch()).setOrientation(new LBFGS()).setMonitor(monitor).setTimeout(30, TimeUnit.SECONDS).setIterationsPerSample(100).setMaxIterations(250).setTerminateThreshold(0).runAndFree();
        });
    } catch (Throwable e) {
        if (isThrowExceptions())
            throw new RuntimeException(e);
    }
    return history;
}

Example 5 with ArmijoWolfeSearch

use of com.simiacryptus.mindseye.opt.line.ArmijoWolfeSearch in project MindsEye by SimiaCryptus.

the class RecursiveSubspace method train.

/**
 * Train.
 *
 * @param monitor    the monitor
 * @param macroLayer the macro layer
 */
public void train(@Nonnull TrainingMonitor monitor, Layer macroLayer) {
    @Nonnull BasicTrainable inner = new BasicTrainable(macroLayer);
    // @javax.annotation.Nonnull Tensor tensor = new Tensor();
    @Nonnull ArrayTrainable trainable = new ArrayTrainable(inner, new Tensor[][] { {} });
    inner.freeRef();
    // tensor.freeRef();
    new IterativeTrainer(trainable).setOrientation(new LBFGS()).setLineSearchFactory(n -> new ArmijoWolfeSearch()).setMonitor(new TrainingMonitor() {

        @Override
        public void log(String msg) {
            monitor.log("\t" + msg);
        }
    }).setMaxIterations(getIterations()).setIterationsPerSample(getIterations()).setTerminateThreshold(terminateThreshold).runAndFree();
    trainable.freeRef();
}