Examples with StepRecord com.simiacryptus.mindseye.test.StepRecord used on opensource projects

Example 6 with StepRecord

use of com.simiacryptus.mindseye.test.StepRecord 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;
}

Example 7 with StepRecord

use of com.simiacryptus.mindseye.test.StepRecord 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 8 with StepRecord

use of com.simiacryptus.mindseye.test.StepRecord 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;
}

Example 9 with StepRecord

use of com.simiacryptus.mindseye.test.StepRecord 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 10 with StepRecord

use of com.simiacryptus.mindseye.test.StepRecord in project MindsEye by SimiaCryptus.

the class TrainingTester method trainAll.

/**
 * Train all apply result.
 *
 * @param title         the title
 * @param log           the log
 * @param trainingInput the training input
 * @param layer         the layer
 * @param mask          the mask
 * @return the apply result
 */
@Nonnull
public TestResult trainAll(CharSequence title, @Nonnull NotebookOutput log, @Nonnull Tensor[][] trainingInput, @Nonnull Layer layer, boolean... mask) {
    try {
        log.h3("Gradient Descent");
        final List<StepRecord> gd = train(log, this::trainGD, layer.copy(), copy(trainingInput), mask);
        log.h3("Conjugate Gradient Descent");
        final List<StepRecord> cjgd = train(log, this::trainCjGD, layer.copy(), copy(trainingInput), mask);
        log.h3("Limited-Memory BFGS");
        final List<StepRecord> lbfgs = train(log, this::trainLBFGS, layer.copy(), copy(trainingInput), mask);
        log.h3("Experimental Optimizer");
        final List<StepRecord> magic = train(log, this::trainMagic, layer.copy(), copy(trainingInput), mask);
        @Nonnull final ProblemRun[] runs = { new ProblemRun("GD", gd, Color.GRAY, ProblemRun.PlotType.Line), new ProblemRun("CjGD", cjgd, Color.CYAN, ProblemRun.PlotType.Line), new ProblemRun("LBFGS", lbfgs, Color.GREEN, ProblemRun.PlotType.Line), new ProblemRun("Experimental", magic, Color.MAGENTA, ProblemRun.PlotType.Line) };
        @Nonnull ProblemResult result = new ProblemResult();
        result.put("GD", new TrainingResult(getResultType(gd), min(gd)));
        result.put("CjGD", new TrainingResult(getResultType(cjgd), min(cjgd)));
        result.put("LBFGS", new TrainingResult(getResultType(lbfgs), min(lbfgs)));
        result.put("Experimental", new TrainingResult(getResultType(magic), min(magic)));
        if (verbose) {
            final PlotCanvas iterPlot = log.code(() -> {
                return TestUtil.compare(title + " vs Iteration", runs);
            });
            final PlotCanvas timePlot = log.code(() -> {
                return TestUtil.compareTime(title + " vs Time", runs);
            });
            return new TestResult(iterPlot, timePlot, result);
        } else {
            @Nullable final PlotCanvas iterPlot = TestUtil.compare(title + " vs Iteration", runs);
            @Nullable final PlotCanvas timePlot = TestUtil.compareTime(title + " vs Time", runs);
            return new TestResult(iterPlot, timePlot, result);
        }
    } finally {
        layer.freeRef();
    }
}