Examples with FeedForwardLayer org.deeplearning4j.nn.conf.layers.FeedForwardLayer used on opensource projects

Example 1 with FeedForwardLayer

use of org.deeplearning4j.nn.conf.layers.FeedForwardLayer in project deeplearning4j by deeplearning4j.

the class ComputationGraph method summary.

/**
     * String detailing the architecture of the computation graph.
     * Vertices are printed in a topological sort order.
     * Columns are Vertex Names with layer/vertex type, nIn, nOut, Total number of parameters and the Shapes of the parameters
     * And the inputs to the vertex
     * Will also give information about frozen layers/vertices, if any.
     * @return Summary as a string
     */
public String summary() {
    String ret = "\n";
    ret += StringUtils.repeat("=", 140);
    ret += "\n";
    ret += String.format("%-40s%-15s%-15s%-30s %s\n", "VertexName (VertexType)", "nIn,nOut", "TotalParams", "ParamsShape", "Vertex Inputs");
    ret += StringUtils.repeat("=", 140);
    ret += "\n";
    int frozenParams = 0;
    for (int currVertexIdx : topologicalOrder) {
        GraphVertex current = vertices[currVertexIdx];
        String name = current.getVertexName();
        String[] classNameArr = current.getClass().toString().split("\\.");
        String className = classNameArr[classNameArr.length - 1];
        String connections = "-";
        if (!current.isInputVertex()) {
            connections = configuration.getVertexInputs().get(name).toString();
        }
        String paramCount = "-";
        String in = "-";
        String out = "-";
        String paramShape = "-";
        if (current.hasLayer()) {
            Layer currentLayer = ((LayerVertex) current).getLayer();
            classNameArr = currentLayer.getClass().getName().split("\\.");
            className = classNameArr[classNameArr.length - 1];
            paramCount = String.valueOf(currentLayer.numParams());
            if (currentLayer.numParams() > 0) {
                paramShape = "";
                in = String.valueOf(((FeedForwardLayer) currentLayer.conf().getLayer()).getNIn());
                out = String.valueOf(((FeedForwardLayer) currentLayer.conf().getLayer()).getNOut());
                Set<String> paraNames = currentLayer.conf().getLearningRateByParam().keySet();
                for (String aP : paraNames) {
                    String paramS = ArrayUtils.toString(currentLayer.paramTable().get(aP).shape());
                    paramShape += aP + ":" + paramS + ", ";
                }
                paramShape = paramShape.subSequence(0, paramShape.lastIndexOf(",")).toString();
            }
            if (currentLayer instanceof FrozenLayer) {
                frozenParams += currentLayer.numParams();
                classNameArr = ((FrozenLayer) currentLayer).getInsideLayer().getClass().getName().split("\\.");
                className = "Frozen " + classNameArr[classNameArr.length - 1];
            }
        }
        ret += String.format("%-40s%-15s%-15s%-30s %s", name + " (" + className + ")", in + "," + out, paramCount, paramShape, connections);
        ret += "\n";
    }
    ret += StringUtils.repeat("-", 140);
    ret += String.format("\n%30s %d", "Total Parameters: ", params().length());
    ret += String.format("\n%30s %d", "Trainable Parameters: ", params().length() - frozenParams);
    ret += String.format("\n%30s %d", "Frozen Parameters: ", frozenParams);
    ret += "\n";
    ret += StringUtils.repeat("=", 140);
    ret += "\n";
    return ret;
}

Example 2 with FeedForwardLayer

use of org.deeplearning4j.nn.conf.layers.FeedForwardLayer in project deeplearning4j by deeplearning4j.

the class SparkDl4jMultiLayer method fitLabeledPoint.

/**
     * Fit a MultiLayerNetwork using Spark MLLib LabeledPoint instances.
     * This will convert the labeled points to the internal DL4J data format and train the model on that
     *
     * @param rdd the rdd to fitDataSet
     * @return the multi layer network that was fitDataSet
     */
public MultiLayerNetwork fitLabeledPoint(JavaRDD<LabeledPoint> rdd) {
    int nLayers = network.getLayerWiseConfigurations().getConfs().size();
    FeedForwardLayer ffl = (FeedForwardLayer) network.getLayerWiseConfigurations().getConf(nLayers - 1).getLayer();
    JavaRDD<DataSet> ds = MLLibUtil.fromLabeledPoint(sc, rdd, ffl.getNOut());
    return fit(ds);
}

Example 3 with FeedForwardLayer

use of org.deeplearning4j.nn.conf.layers.FeedForwardLayer in project deeplearning4j by deeplearning4j.

the class SparkDl4jLayer method fit.

/**
     * Fit the layer based on the specified org.deeplearning4j.spark context text file
     * @param path the path to the text file
     * @param labelIndex the index of the label
     * @param recordReader the record reader
     * @return the fit layer
     */
public Layer fit(String path, int labelIndex, RecordReader recordReader) {
    FeedForwardLayer ffLayer = (FeedForwardLayer) conf.getLayer();
    JavaRDD<String> lines = sc.textFile(path);
    // gotta map this to a Matrix/INDArray
    JavaRDD<DataSet> points = lines.map(new RecordReaderFunction(recordReader, labelIndex, ffLayer.getNOut()));
    return fitDataSet(points);
}

Example 4 with FeedForwardLayer

use of org.deeplearning4j.nn.conf.layers.FeedForwardLayer in project deeplearning4j by deeplearning4j.

the class TrainModule method getLayerInfoTable.

private String[][] getLayerInfoTable(int layerIdx, TrainModuleUtils.GraphInfo gi, I18N i18N, boolean noData, StatsStorage ss, String wid) {
    List<String[]> layerInfoRows = new ArrayList<>();
    layerInfoRows.add(new String[] { i18N.getMessage("train.model.layerinfotable.layerName"), gi.getVertexNames().get(layerIdx) });
    layerInfoRows.add(new String[] { i18N.getMessage("train.model.layerinfotable.layerType"), "" });
    if (!noData) {
        Persistable p = ss.getStaticInfo(currentSessionID, StatsListener.TYPE_ID, wid);
        if (p != null) {
            StatsInitializationReport initReport = (StatsInitializationReport) p;
            String configJson = initReport.getModelConfigJson();
            String modelClass = initReport.getModelClassName();
            //TODO error handling...
            String layerType = "";
            Layer layer = null;
            NeuralNetConfiguration nnc = null;
            if (modelClass.endsWith("MultiLayerNetwork")) {
                MultiLayerConfiguration conf = MultiLayerConfiguration.fromJson(configJson);
                //-1 because of input
                int confIdx = layerIdx - 1;
                if (confIdx >= 0) {
                    nnc = conf.getConf(confIdx);
                    layer = nnc.getLayer();
                } else {
                    //Input layer
                    layerType = "Input";
                }
            } else if (modelClass.endsWith("ComputationGraph")) {
                ComputationGraphConfiguration conf = ComputationGraphConfiguration.fromJson(configJson);
                String vertexName = gi.getVertexNames().get(layerIdx);
                Map<String, GraphVertex> vertices = conf.getVertices();
                if (vertices.containsKey(vertexName) && vertices.get(vertexName) instanceof LayerVertex) {
                    LayerVertex lv = (LayerVertex) vertices.get(vertexName);
                    nnc = lv.getLayerConf();
                    layer = nnc.getLayer();
                } else if (conf.getNetworkInputs().contains(vertexName)) {
                    layerType = "Input";
                } else {
                    GraphVertex gv = conf.getVertices().get(vertexName);
                    if (gv != null) {
                        layerType = gv.getClass().getSimpleName();
                    }
                }
            } else if (modelClass.endsWith("VariationalAutoencoder")) {
                layerType = gi.getVertexTypes().get(layerIdx);
                Map<String, String> map = gi.getVertexInfo().get(layerIdx);
                for (Map.Entry<String, String> entry : map.entrySet()) {
                    layerInfoRows.add(new String[] { entry.getKey(), entry.getValue() });
                }
            }
            if (layer != null) {
                layerType = getLayerType(layer);
            }
            if (layer != null) {
                String activationFn = null;
                if (layer instanceof FeedForwardLayer) {
                    FeedForwardLayer ffl = (FeedForwardLayer) layer;
                    layerInfoRows.add(new String[] { i18N.getMessage("train.model.layerinfotable.layerNIn"), String.valueOf(ffl.getNIn()) });
                    layerInfoRows.add(new String[] { i18N.getMessage("train.model.layerinfotable.layerSize"), String.valueOf(ffl.getNOut()) });
                    activationFn = layer.getActivationFn().toString();
                }
                int nParams = layer.initializer().numParams(nnc);
                layerInfoRows.add(new String[] { i18N.getMessage("train.model.layerinfotable.layerNParams"), String.valueOf(nParams) });
                if (nParams > 0) {
                    WeightInit wi = layer.getWeightInit();
                    String str = wi.toString();
                    if (wi == WeightInit.DISTRIBUTION) {
                        str += layer.getDist();
                    }
                    layerInfoRows.add(new String[] { i18N.getMessage("train.model.layerinfotable.layerWeightInit"), str });
                    Updater u = layer.getUpdater();
                    String us = (u == null ? "" : u.toString());
                    layerInfoRows.add(new String[] { i18N.getMessage("train.model.layerinfotable.layerUpdater"), us });
                //TODO: Maybe L1/L2, dropout, updater-specific values etc
                }
                if (layer instanceof ConvolutionLayer || layer instanceof SubsamplingLayer) {
                    int[] kernel;
                    int[] stride;
                    int[] padding;
                    if (layer instanceof ConvolutionLayer) {
                        ConvolutionLayer cl = (ConvolutionLayer) layer;
                        kernel = cl.getKernelSize();
                        stride = cl.getStride();
                        padding = cl.getPadding();
                    } else {
                        SubsamplingLayer ssl = (SubsamplingLayer) layer;
                        kernel = ssl.getKernelSize();
                        stride = ssl.getStride();
                        padding = ssl.getPadding();
                        activationFn = null;
                        layerInfoRows.add(new String[] { i18N.getMessage("train.model.layerinfotable.layerSubsamplingPoolingType"), ssl.getPoolingType().toString() });
                    }
                    layerInfoRows.add(new String[] { i18N.getMessage("train.model.layerinfotable.layerCnnKernel"), Arrays.toString(kernel) });
                    layerInfoRows.add(new String[] { i18N.getMessage("train.model.layerinfotable.layerCnnStride"), Arrays.toString(stride) });
                    layerInfoRows.add(new String[] { i18N.getMessage("train.model.layerinfotable.layerCnnPadding"), Arrays.toString(padding) });
                }
                if (activationFn != null) {
                    layerInfoRows.add(new String[] { i18N.getMessage("train.model.layerinfotable.layerActivationFn"), activationFn });
                }
            }
            layerInfoRows.get(1)[1] = layerType;
        }
    }
    return layerInfoRows.toArray(new String[layerInfoRows.size()][0]);
}

Example 5 with FeedForwardLayer

use of org.deeplearning4j.nn.conf.layers.FeedForwardLayer in project deeplearning4j by deeplearning4j.

the class MultiLayerNetwork method summary.

/**
     * String detailing the architecture of the multilayernetwork.
     * Columns are LayerIndex with layer type, nIn, nOut, Total number of parameters and the Shapes of the parameters
     * Will also give information about frozen layers, if any.
     * @return Summary as a string
     */
public String summary() {
    String ret = "\n";
    ret += StringUtils.repeat("=", 140);
    ret += "\n";
    ret += String.format("%-40s%-15s%-15s%-30s\n", "LayerName (LayerType)", "nIn,nOut", "TotalParams", "ParamsShape");
    ret += StringUtils.repeat("=", 140);
    ret += "\n";
    int frozenParams = 0;
    for (Layer currentLayer : layers) {
        String name = String.valueOf(currentLayer.getIndex());
        String paramShape = "-";
        String in = "-";
        String out = "-";
        String[] classNameArr = currentLayer.getClass().getName().split("\\.");
        String className = classNameArr[classNameArr.length - 1];
        String paramCount = String.valueOf(currentLayer.numParams());
        if (currentLayer.numParams() > 0) {
            paramShape = "";
            in = String.valueOf(((FeedForwardLayer) currentLayer.conf().getLayer()).getNIn());
            out = String.valueOf(((FeedForwardLayer) currentLayer.conf().getLayer()).getNOut());
            Set<String> paraNames = currentLayer.conf().getLearningRateByParam().keySet();
            for (String aP : paraNames) {
                String paramS = ArrayUtils.toString(currentLayer.paramTable().get(aP).shape());
                paramShape += aP + ":" + paramS + ", ";
            }
            paramShape = paramShape.subSequence(0, paramShape.lastIndexOf(",")).toString();
        }
        if (currentLayer instanceof FrozenLayer) {
            frozenParams += currentLayer.numParams();
            classNameArr = ((FrozenLayer) currentLayer).getInsideLayer().getClass().getName().split("\\.");
            className = "Frozen " + classNameArr[classNameArr.length - 1];
        }
        ret += String.format("%-40s%-15s%-15s%-30s", name + " (" + className + ")", in + "," + out, paramCount, paramShape);
        ret += "\n";
    }
    ret += StringUtils.repeat("-", 140);
    ret += String.format("\n%30s %d", "Total Parameters: ", params().length());
    ret += String.format("\n%30s %d", "Trainable Parameters: ", params().length() - frozenParams);
    ret += String.format("\n%30s %d", "Frozen Parameters: ", frozenParams);
    ret += "\n";
    ret += StringUtils.repeat("=", 140);
    ret += "\n";
    return ret;
}