Examples with TrainingMonitor com.simiacryptus.mindseye.opt.TrainingMonitor used on opensource projects

Example 1 with TrainingMonitor

use of com.simiacryptus.mindseye.opt.TrainingMonitor 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 2 with TrainingMonitor

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

the class EncodingUtil method getMonitor.

/**
 * Gets monitor.
 *
 * @param history the history
 * @return the monitor
 */
public static TrainingMonitor getMonitor(@Nonnull final List<StepRecord> history) {
    return new TrainingMonitor() {

        @Override
        public void clear() {
            super.clear();
        }

        @Override
        public void log(final String msg) {
            // Logged MnistProblemData
            log.info(msg);
            // Realtime MnistProblemData
            EncodingUtil.rawOut.println(msg);
        }

        @Override
        public void onStepComplete(@Nonnull final Step currentPoint) {
            history.add(new StepRecord(currentPoint.point.getMean(), currentPoint.time, currentPoint.iteration));
        }
    };
}

Example 3 with TrainingMonitor

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

the class BasicTrainable method eval.

/**
 * Eval point sample.
 *
 * @param list    the list
 * @param monitor the monitor
 * @return the point sample
 */
@Nonnull
protected PointSample eval(@Nonnull final List<Tensor[]> list, @Nullable final TrainingMonitor monitor) {
    @Nonnull final TimedResult<PointSample> timedResult = TimedResult.time(() -> {
        final Result[] nnContext = BasicTrainable.getNNContext(list, mask);
        final Result result = network.eval(nnContext);
        for (@Nonnull Result nnResult : nnContext) {
            nnResult.getData().freeRef();
            nnResult.freeRef();
        }
        final TensorList resultData = result.getData();
        @Nonnull final DeltaSet<Layer> deltaSet = new DeltaSet<Layer>();
        @Nonnull StateSet<Layer> stateSet = null;
        try {
            final DoubleSummaryStatistics statistics = resultData.stream().flatMapToDouble(x -> {
                double[] array = Arrays.stream(x.getData()).toArray();
                x.freeRef();
                return Arrays.stream(array);
            }).summaryStatistics();
            final double sum = statistics.getSum();
            result.accumulate(deltaSet, 1.0);
            stateSet = new StateSet<>(deltaSet);
            // log.info(String.format("Evaluated to %s delta buffers, %s mag", DeltaSet<LayerBase>.getMap().size(), DeltaSet<LayerBase>.getMagnitude()));
            return new PointSample(deltaSet, stateSet, sum, 0.0, list.size());
        } finally {
            if (null != stateSet)
                stateSet.freeRef();
            resultData.freeRefAsync();
            result.freeRefAsync();
            deltaSet.freeRefAsync();
        }
    });
    if (null != monitor && verbosity() > 0) {
        monitor.log(String.format("Device completed %s items in %.3f sec", list.size(), timedResult.timeNanos / 1e9));
    }
    @Nonnull PointSample normalize = timedResult.result.normalize();
    timedResult.result.freeRef();
    return normalize;
}

Example 4 with TrainingMonitor

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

the class TensorListTrainable method eval.

/**
 * Eval point sample.
 *
 * @param list    the list
 * @param monitor the monitor
 * @return the point sample
 */
@Nonnull
protected PointSample eval(@Nonnull final TensorList[] list, @Nullable final TrainingMonitor monitor) {
    int inputs = data.length;
    assert 0 < inputs;
    int items = data[0].length();
    assert 0 < items;
    @Nonnull final TimedResult<PointSample> timedResult = TimedResult.time(() -> {
        final Result[] nnContext = TensorListTrainable.getNNContext(list, mask);
        final Result result = network.eval(nnContext);
        for (@Nonnull Result nnResult : nnContext) {
            nnResult.getData().freeRef();
            nnResult.freeRef();
        }
        final TensorList resultData = result.getData();
        final DoubleSummaryStatistics statistics = resultData.stream().flatMapToDouble(x -> {
            double[] array = Arrays.stream(x.getData()).toArray();
            x.freeRef();
            return Arrays.stream(array);
        }).summaryStatistics();
        final double sum = statistics.getSum();
        @Nonnull final DeltaSet<Layer> deltaSet = new DeltaSet<Layer>();
        @Nonnull PointSample pointSample;
        try {
            result.accumulate(deltaSet, 1.0);
            // log.info(String.format("Evaluated to %s delta buffers, %s mag", DeltaSet<LayerBase>.getMap().size(), DeltaSet<LayerBase>.getMagnitude()));
            @Nonnull StateSet<Layer> stateSet = new StateSet<>(deltaSet);
            pointSample = new PointSample(deltaSet, stateSet, sum, 0.0, items);
            stateSet.freeRef();
        } finally {
            resultData.freeRef();
            result.freeRef();
            deltaSet.freeRef();
        }
        return pointSample;
    });
    if (null != monitor && verbosity() > 0) {
        monitor.log(String.format("Device completed %s items in %.3f sec", items, timedResult.timeNanos / 1e9));
    }
    @Nonnull PointSample normalize = timedResult.result.normalize();
    timedResult.result.freeRef();
    return normalize;
}

Example 5 with TrainingMonitor

use of com.simiacryptus.mindseye.opt.TrainingMonitor 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;
}