Examples with MeanSqLossLayer com.simiacryptus.mindseye.layers.java.MeanSqLossLayer used on opensource projects

Example 1 with MeanSqLossLayer

use of com.simiacryptus.mindseye.layers.java.MeanSqLossLayer in project MindsEye by SimiaCryptus.

the class EncodingUtil method buildTrainingModel.

/**
 * Build training model dag network.
 *
 * @param innerModel       the heapCopy model
 * @param reproducedColumn the reproduced column
 * @param learnedColumn    the learned column
 * @return the dag network
 */
@Nonnull
public static DAGNetwork buildTrainingModel(final Layer innerModel, final int reproducedColumn, final int learnedColumn) {
    @Nonnull final PipelineNetwork network = new PipelineNetwork(Math.max(learnedColumn, reproducedColumn) + 1);
    // network.add(new NthPowerActivationLayer().setPower(0.5), );
    network.wrap(new MeanSqLossLayer(), network.add("image", innerModel, network.getInput(learnedColumn)), network.getInput(reproducedColumn));
    // addLogging(network);
    return network;
}

Example 2 with MeanSqLossLayer

use of com.simiacryptus.mindseye.layers.java.MeanSqLossLayer in project MindsEye by SimiaCryptus.

the class AutoencodingProblem method run.

@Nonnull
@Override
public AutoencodingProblem run(@Nonnull final NotebookOutput log) {
    @Nonnull final DAGNetwork fwdNetwork = fwdFactory.imageToVector(log, features);
    @Nonnull final DAGNetwork revNetwork = revFactory.vectorToImage(log, features);
    @Nonnull final PipelineNetwork echoNetwork = new PipelineNetwork(1);
    echoNetwork.add(fwdNetwork);
    echoNetwork.add(revNetwork);
    @Nonnull final PipelineNetwork supervisedNetwork = new PipelineNetwork(1);
    supervisedNetwork.add(fwdNetwork);
    @Nonnull final DropoutNoiseLayer dropoutNoiseLayer = new DropoutNoiseLayer().setValue(dropout);
    supervisedNetwork.add(dropoutNoiseLayer);
    supervisedNetwork.add(revNetwork);
    supervisedNetwork.add(new MeanSqLossLayer(), supervisedNetwork.getHead(), supervisedNetwork.getInput(0));
    log.h3("Network Diagrams");
    log.code(() -> {
        return Graphviz.fromGraph(TestUtil.toGraph(fwdNetwork)).height(400).width(600).render(Format.PNG).toImage();
    });
    log.code(() -> {
        return Graphviz.fromGraph(TestUtil.toGraph(revNetwork)).height(400).width(600).render(Format.PNG).toImage();
    });
    log.code(() -> {
        return Graphviz.fromGraph(TestUtil.toGraph(supervisedNetwork)).height(400).width(600).render(Format.PNG).toImage();
    });
    @Nonnull final TrainingMonitor monitor = new TrainingMonitor() {

        @Nonnull
        TrainingMonitor inner = TestUtil.getMonitor(history);

        @Override
        public void log(final String msg) {
            inner.log(msg);
        }

        @Override
        public void onStepComplete(final Step currentPoint) {
            dropoutNoiseLayer.shuffle(StochasticComponent.random.get().nextLong());
            inner.onStepComplete(currentPoint);
        }
    };
    final Tensor[][] trainingData = getTrainingData(log);
    // MonitoredObject monitoringRoot = new MonitoredObject();
    // TestUtil.addMonitoring(supervisedNetwork, monitoringRoot);
    log.h3("Training");
    TestUtil.instrumentPerformance(supervisedNetwork);
    @Nonnull final ValidatingTrainer trainer = optimizer.train(log, new SampledArrayTrainable(trainingData, supervisedNetwork, trainingData.length / 2, batchSize), new ArrayTrainable(trainingData, supervisedNetwork, batchSize), 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);
        });
    }
    TestUtil.extractPerformance(log, supervisedNetwork);
    {
        @Nonnull final String modelName = "encoder_model" + AutoencodingProblem.modelNo++ + ".json";
        log.p("Saved model as " + log.file(fwdNetwork.getJson().toString(), modelName, modelName));
    }
    @Nonnull final String modelName = "decoder_model" + AutoencodingProblem.modelNo++ + ".json";
    log.p("Saved model as " + log.file(revNetwork.getJson().toString(), modelName, modelName));
    // log.h3("Metrics");
    // log.code(() -> {
    // return TestUtil.toFormattedJson(monitoringRoot.getMetrics());
    // });
    log.h3("Validation");
    log.p("Here are some re-encoded examples:");
    log.code(() -> {
        @Nonnull final TableOutput table = new TableOutput();
        data.validationData().map(labeledObject -> {
            return toRow(log, labeledObject, echoNetwork.eval(labeledObject.data).getData().get(0).getData());
        }).filter(x -> null != x).limit(10).forEach(table::putRow);
        return table;
    });
    log.p("Some rendered unit vectors:");
    for (int featureNumber = 0; featureNumber < features; featureNumber++) {
        @Nonnull final Tensor input = new Tensor(features).set(featureNumber, 1);
        @Nullable final Tensor tensor = revNetwork.eval(input).getData().get(0);
        log.out(log.image(tensor.toImage(), ""));
    }
    return this;
}

Example 3 with MeanSqLossLayer

use of com.simiacryptus.mindseye.layers.java.MeanSqLossLayer in project MindsEye by SimiaCryptus.

the class EncodingProblem method run.

@Nonnull
@Override
public EncodingProblem run(@Nonnull final NotebookOutput log) {
    @Nonnull final TrainingMonitor monitor = TestUtil.getMonitor(history);
    Tensor[][] trainingData;
    try {
        trainingData = data.trainingData().map(labeledObject -> {
            return new Tensor[] { new Tensor(features).set(this::random), labeledObject.data };
        }).toArray(i -> new Tensor[i][]);
    } catch (@Nonnull final IOException e) {
        throw new RuntimeException(e);
    }
    @Nonnull final DAGNetwork imageNetwork = revFactory.vectorToImage(log, features);
    log.h3("Network Diagram");
    log.code(() -> {
        return Graphviz.fromGraph(TestUtil.toGraph(imageNetwork)).height(400).width(600).render(Format.PNG).toImage();
    });
    @Nonnull final PipelineNetwork trainingNetwork = new PipelineNetwork(2);
    @Nullable final DAGNode image = trainingNetwork.add(imageNetwork, trainingNetwork.getInput(0));
    @Nullable final DAGNode softmax = trainingNetwork.add(new SoftmaxActivationLayer(), trainingNetwork.getInput(0));
    trainingNetwork.add(new SumInputsLayer(), trainingNetwork.add(new EntropyLossLayer(), softmax, softmax), trainingNetwork.add(new NthPowerActivationLayer().setPower(1.0 / 2.0), trainingNetwork.add(new MeanSqLossLayer(), image, trainingNetwork.getInput(1))));
    log.h3("Training");
    log.p("We start by training apply a very small population to improve initial convergence performance:");
    TestUtil.instrumentPerformance(trainingNetwork);
    @Nonnull final Tensor[][] primingData = Arrays.copyOfRange(trainingData, 0, 1000);
    @Nonnull final ValidatingTrainer preTrainer = optimizer.train(log, (SampledTrainable) new SampledArrayTrainable(primingData, trainingNetwork, trainingSize, batchSize).setMinSamples(trainingSize).setMask(true, false), new ArrayTrainable(primingData, trainingNetwork, batchSize), monitor);
    log.code(() -> {
        preTrainer.setTimeout(timeoutMinutes / 2, TimeUnit.MINUTES).setMaxIterations(batchSize).run();
    });
    TestUtil.extractPerformance(log, trainingNetwork);
    log.p("Then our main training phase:");
    TestUtil.instrumentPerformance(trainingNetwork);
    @Nonnull final ValidatingTrainer mainTrainer = optimizer.train(log, (SampledTrainable) new SampledArrayTrainable(trainingData, trainingNetwork, trainingSize, batchSize).setMinSamples(trainingSize).setMask(true, false), new ArrayTrainable(trainingData, trainingNetwork, batchSize), monitor);
    log.code(() -> {
        mainTrainer.setTimeout(timeoutMinutes, TimeUnit.MINUTES).setMaxIterations(batchSize).run();
    });
    TestUtil.extractPerformance(log, trainingNetwork);
    if (!history.isEmpty()) {
        log.code(() -> {
            return TestUtil.plot(history);
        });
        log.code(() -> {
            return TestUtil.plotTime(history);
        });
    }
    try {
        @Nonnull String filename = log.getName().toString() + EncodingProblem.modelNo++ + "_plot.png";
        ImageIO.write(Util.toImage(TestUtil.plot(history)), "png", log.file(filename));
        log.appendFrontMatterProperty("result_plot", filename, ";");
    } catch (IOException e) {
        throw new RuntimeException(e);
    }
    // log.file()
    @Nonnull final String modelName = "encoding_model_" + EncodingProblem.modelNo++ + ".json";
    log.appendFrontMatterProperty("result_model", modelName, ";");
    log.p("Saved model as " + log.file(trainingNetwork.getJson().toString(), modelName, modelName));
    log.h3("Results");
    @Nonnull final PipelineNetwork testNetwork = new PipelineNetwork(2);
    testNetwork.add(imageNetwork, testNetwork.getInput(0));
    log.code(() -> {
        @Nonnull final TableOutput table = new TableOutput();
        Arrays.stream(trainingData).map(tensorArray -> {
            @Nullable final Tensor predictionSignal = testNetwork.eval(tensorArray).getData().get(0);
            @Nonnull final LinkedHashMap<CharSequence, Object> row = new LinkedHashMap<>();
            row.put("Source", log.image(tensorArray[1].toImage(), ""));
            row.put("Echo", log.image(predictionSignal.toImage(), ""));
            return row;
        }).filter(x -> null != x).limit(10).forEach(table::putRow);
        return table;
    });
    log.p("Learned Model Statistics:");
    log.code(() -> {
        @Nonnull final ScalarStatistics scalarStatistics = new ScalarStatistics();
        trainingNetwork.state().stream().flatMapToDouble(x -> Arrays.stream(x)).forEach(v -> scalarStatistics.add(v));
        return scalarStatistics.getMetrics();
    });
    log.p("Learned Representation Statistics:");
    log.code(() -> {
        @Nonnull final ScalarStatistics scalarStatistics = new ScalarStatistics();
        Arrays.stream(trainingData).flatMapToDouble(row -> Arrays.stream(row[0].getData())).forEach(v -> scalarStatistics.add(v));
        return scalarStatistics.getMetrics();
    });
    log.p("Some rendered unit vectors:");
    for (int featureNumber = 0; featureNumber < features; featureNumber++) {
        @Nonnull final Tensor input = new Tensor(features).set(featureNumber, 1);
        @Nullable final Tensor tensor = imageNetwork.eval(input).getData().get(0);
        TestUtil.renderToImages(tensor, true).forEach(img -> {
            log.out(log.image(img, ""));
        });
    }
    return this;
}

Example 4 with MeanSqLossLayer

use of com.simiacryptus.mindseye.layers.java.MeanSqLossLayer in project MindsEye by SimiaCryptus.

the class AutoencoderNetwork method train.

/**
 * Train autoencoder network . training parameters.
 *
 * @return the autoencoder network . training parameters
 */
@Nonnull
public AutoencoderNetwork.TrainingParameters train() {
    return new AutoencoderNetwork.TrainingParameters() {

        @Nonnull
        @Override
        public SimpleLossNetwork getTrainingNetwork() {
            @Nonnull final PipelineNetwork student = new PipelineNetwork();
            student.add(encoder);
            student.add(decoder);
            return new SimpleLossNetwork(student, new MeanSqLossLayer());
        }

        @Nonnull
        @Override
        protected TrainingMonitor wrap(@Nonnull final TrainingMonitor monitor) {
            return new TrainingMonitor() {

                @Override
                public void log(final String msg) {
                    monitor.log(msg);
                }

                @Override
                public void onStepComplete(final Step currentPoint) {
                    inputNoise.shuffle();
                    encodedNoise.shuffle(StochasticComponent.random.get().nextLong());
                    monitor.onStepComplete(currentPoint);
                }
            };
        }
    };
}

Example 5 with MeanSqLossLayer

use of com.simiacryptus.mindseye.layers.java.MeanSqLossLayer in project MindsEye by SimiaCryptus.

the class TrainingTester method train.

private List<StepRecord> train(@Nonnull NotebookOutput log, @Nonnull BiFunction<NotebookOutput, Trainable, List<StepRecord>> opt, @Nonnull Layer layer, @Nonnull Tensor[][] data, @Nonnull boolean... mask) {
    try {
        int inputs = data[0].length;
        @Nonnull final PipelineNetwork network = new PipelineNetwork(inputs);
        network.wrap(new MeanSqLossLayer(), network.add(layer, IntStream.range(0, inputs - 1).mapToObj(i -> network.getInput(i)).toArray(i -> new DAGNode[i])), network.getInput(inputs - 1));
        @Nonnull ArrayTrainable trainable = new ArrayTrainable(data, network);
        if (0 < mask.length)
            trainable.setMask(mask);
        List<StepRecord> history;
        try {
            history = opt.apply(log, trainable);
            if (history.stream().mapToDouble(x -> x.fitness).min().orElse(1) > 1e-5) {
                if (!network.isFrozen()) {
                    log.p("This training apply resulted in the following configuration:");
                    log.code(() -> {
                        return network.state().stream().map(Arrays::toString).reduce((a, b) -> a + "\n" + b).orElse("");
                    });
                }
                if (0 < mask.length) {
                    log.p("And regressed input:");
                    log.code(() -> {
                        return Arrays.stream(data).flatMap(x -> Arrays.stream(x)).limit(1).map(x -> x.prettyPrint()).reduce((a, b) -> a + "\n" + b).orElse("");
                    });
                }
                log.p("To produce the following output:");
                log.code(() -> {
                    Result[] array = ConstantResult.batchResultArray(pop(data));
                    @Nullable Result eval = layer.eval(array);
                    for (@Nonnull Result result : array) {
                        result.freeRef();
                        result.getData().freeRef();
                    }
                    TensorList tensorList = eval.getData();
                    eval.freeRef();
                    String str = tensorList.stream().limit(1).map(x -> {
                        String s = x.prettyPrint();
                        x.freeRef();
                        return s;
                    }).reduce((a, b) -> a + "\n" + b).orElse("");
                    tensorList.freeRef();
                    return str;
                });
            } else {
                log.p("Training Converged");
            }
        } finally {
            trainable.freeRef();
            network.freeRef();
        }
        return history;
    } finally {
        layer.freeRef();
        for (@Nonnull Tensor[] tensors : data) {
            for (@Nonnull Tensor tensor : tensors) {
                tensor.freeRef();
            }
        }
    }
}