Examples with ArrayTrainable com.simiacryptus.mindseye.eval.ArrayTrainable used on opensource projects

Example 11 with ArrayTrainable

use of com.simiacryptus.mindseye.eval.ArrayTrainable 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 12 with ArrayTrainable

use of com.simiacryptus.mindseye.eval.ArrayTrainable 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 13 with ArrayTrainable

use of com.simiacryptus.mindseye.eval.ArrayTrainable 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();
            }
        }
    }
}

Example 14 with ArrayTrainable

use of com.simiacryptus.mindseye.eval.ArrayTrainable 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();
}

Example 15 with ArrayTrainable

use of com.simiacryptus.mindseye.eval.ArrayTrainable in project MindsEye by SimiaCryptus.

the class SimpleGradientDescentTest 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 ArrayList<Tensor[]> trainingList = new ArrayList<>(Arrays.stream(trainingData).collect(Collectors.toList()));
        Collections.shuffle(trainingList);
        @Nonnull final Tensor[][] randomSelection = trainingList.subList(0, 10000).toArray(new Tensor[][] {});
        @Nonnull final Trainable trainable = new ArrayTrainable(randomSelection, supervisedNetwork);
        return new IterativeTrainer(trainable).setMonitor(monitor).setTimeout(3, TimeUnit.MINUTES).setMaxIterations(500).runAndFree();
    });
}