Examples with SimpleLossNetwork com.simiacryptus.mindseye.network.SimpleLossNetwork used on opensource projects

Example 6 with SimpleLossNetwork

use of com.simiacryptus.mindseye.network.SimpleLossNetwork in project MindsEye by SimiaCryptus.

the class SimpleStochasticGradientDescentTest method train.

@Override
public void train(@Nonnull final NotebookOutput log, @Nonnull final Layer network, @Nonnull final Tensor[][] trainingData, final TrainingMonitor monitor) {
    log.p("Training a model involves a few different components. First, our model is combined mapCoords a loss function. " + "Then we take that model and combine it mapCoords our training data to define a trainable object. " + "Finally, we use a simple iterative scheme to refine the weights of our model. " + "The final output is the last output value of the loss function when evaluating the last batch.");
    log.code(() -> {
        @Nonnull final SimpleLossNetwork supervisedNetwork = new SimpleLossNetwork(network, new EntropyLossLayer());
        @Nonnull final Trainable trainable = new SampledArrayTrainable(trainingData, supervisedNetwork, 10000);
        return new IterativeTrainer(trainable).setMonitor(monitor).setOrientation(new GradientDescent()).setTimeout(5, TimeUnit.MINUTES).setMaxIterations(500).runAndFree();
    });
}

Example 7 with SimpleLossNetwork

use of com.simiacryptus.mindseye.network.SimpleLossNetwork in project MindsEye by SimiaCryptus.

the class ClassifyProblem method run.

@Nonnull
@Override
public ClassifyProblem run(@Nonnull final NotebookOutput log) {
    @Nonnull final TrainingMonitor monitor = TestUtil.getMonitor(history);
    final Tensor[][] trainingData = getTrainingData(log);
    @Nonnull final DAGNetwork network = fwdFactory.imageToVector(log, categories);
    log.h3("Network Diagram");
    log.code(() -> {
        return Graphviz.fromGraph(TestUtil.toGraph(network)).height(400).width(600).render(Format.PNG).toImage();
    });
    log.h3("Training");
    @Nonnull final SimpleLossNetwork supervisedNetwork = new SimpleLossNetwork(network, new EntropyLossLayer());
    TestUtil.instrumentPerformance(supervisedNetwork);
    int initialSampleSize = Math.max(trainingData.length / 5, Math.min(10, trainingData.length / 2));
    @Nonnull final ValidatingTrainer trainer = optimizer.train(log, new SampledArrayTrainable(trainingData, supervisedNetwork, initialSampleSize, getBatchSize()), new ArrayTrainable(trainingData, supervisedNetwork, getBatchSize()), monitor);
    log.code(() -> {
        trainer.setTimeout(timeoutMinutes, TimeUnit.MINUTES).setMaxIterations(10000).run();
    });
    if (!history.isEmpty()) {
        log.code(() -> {
            return TestUtil.plot(history);
        });
        log.code(() -> {
            return TestUtil.plotTime(history);
        });
    }
    try {
        @Nonnull String filename = log.getName() + "_" + ClassifyProblem.modelNo++ + "_plot.png";
        ImageIO.write(Util.toImage(TestUtil.plot(history)), "png", log.file(filename));
        @Nonnull File file = new File(log.getResourceDir(), filename);
        log.appendFrontMatterProperty("result_plot", file.toString(), ";");
    } catch (IOException e) {
        throw new RuntimeException(e);
    }
    TestUtil.extractPerformance(log, supervisedNetwork);
    @Nonnull final String modelName = "classification_model_" + ClassifyProblem.modelNo++ + ".json";
    log.appendFrontMatterProperty("result_model", modelName, ";");
    log.p("Saved model as " + log.file(network.getJson().toString(), modelName, modelName));
    log.h3("Validation");
    log.p("If we apply our model against the entire validation dataset, we get this accuracy:");
    log.code(() -> {
        return data.validationData().mapToDouble(labeledObject -> predict(network, labeledObject)[0] == parse(labeledObject.label) ? 1 : 0).average().getAsDouble() * 100;
    });
    log.p("Let's examine some incorrectly predicted results in more detail:");
    log.code(() -> {
        try {
            @Nonnull final TableOutput table = new TableOutput();
            Lists.partition(data.validationData().collect(Collectors.toList()), 100).stream().flatMap(batch -> {
                @Nonnull TensorList batchIn = TensorArray.create(batch.stream().map(x -> x.data).toArray(i -> new Tensor[i]));
                TensorList batchOut = network.eval(new ConstantResult(batchIn)).getData();
                return IntStream.range(0, batchOut.length()).mapToObj(i -> toRow(log, batch.get(i), batchOut.get(i).getData()));
            }).filter(x -> null != x).limit(10).forEach(table::putRow);
            return table;
        } catch (@Nonnull final IOException e) {
            throw new RuntimeException(e);
        }
    });
    return this;
}

Example 8 with SimpleLossNetwork

use of com.simiacryptus.mindseye.network.SimpleLossNetwork in project MindsEye by SimiaCryptus.

the class BisectionLineSearchTest method train.

@Override
public void train(@Nonnull final NotebookOutput log, @Nonnull final Layer network, @Nonnull final Tensor[][] trainingData, final TrainingMonitor monitor) {
    log.code(() -> {
        @Nonnull final SimpleLossNetwork supervisedNetwork = new SimpleLossNetwork(network, new EntropyLossLayer());
        @Nonnull final Trainable trainable = new SampledArrayTrainable(trainingData, supervisedNetwork, 1000);
        return new IterativeTrainer(trainable).setMonitor(monitor).setOrientation(new GradientDescent()).setLineSearchFactory((@Nonnull final CharSequence name) -> new BisectionSearch()).setTimeout(3, TimeUnit.MINUTES).setMaxIterations(500).runAndFree();
    });
}

Example 9 with SimpleLossNetwork

use of com.simiacryptus.mindseye.network.SimpleLossNetwork in project MindsEye by SimiaCryptus.

the class LBFGSTest method train.

@Override
public void train(@Nonnull final NotebookOutput log, @Nonnull final Layer network, @Nonnull final Tensor[][] trainingData, final TrainingMonitor monitor) {
    log.code(() -> {
        @Nonnull final SimpleLossNetwork supervisedNetwork = new SimpleLossNetwork(network, new EntropyLossLayer());
        @Nonnull ValidatingTrainer trainer = new ValidatingTrainer(new SampledArrayTrainable(trainingData, supervisedNetwork, 1000, 10000), new ArrayTrainable(trainingData, supervisedNetwork).cached()).setMonitor(monitor);
        trainer.getRegimen().get(0).setOrientation(new LBFGS()).setLineSearchFactory(name -> name.toString().contains("LBFGS") ? new QuadraticSearch().setCurrentRate(1.0) : new QuadraticSearch());
        return trainer.setTimeout(5, TimeUnit.MINUTES).setMaxIterations(500).run();
    });
}

Example 10 with SimpleLossNetwork

use of com.simiacryptus.mindseye.network.SimpleLossNetwork in project MindsEye by SimiaCryptus.

the class OWLQNTest method train.

@Override
public void train(@Nonnull final NotebookOutput log, @Nonnull final Layer network, @Nonnull final Tensor[][] trainingData, final TrainingMonitor monitor) {
    log.code(() -> {
        @Nonnull final SimpleLossNetwork supervisedNetwork = new SimpleLossNetwork(network, new EntropyLossLayer());
        @Nonnull final Trainable trainable = new SampledArrayTrainable(trainingData, supervisedNetwork, 10000);
        return new IterativeTrainer(trainable).setIterationsPerSample(100).setMonitor(monitor).setOrientation(new ValidatingOrientationWrapper(new OwlQn())).setTimeout(5, TimeUnit.MINUTES).setMaxIterations(500).runAndFree();
    });
}