本文整理了Java中org.deeplearning4j.nn.multilayer.MultiLayerNetwork.getLayerWiseConfigurations()
方法的一些代码示例,展示了MultiLayerNetwork.getLayerWiseConfigurations()
的具体用法。这些代码示例主要来源于Github
/Stackoverflow
/Maven
等平台,是从一些精选项目中提取出来的代码,具有较强的参考意义,能在一定程度帮忙到你。MultiLayerNetwork.getLayerWiseConfigurations()
方法的具体详情如下:
包路径:org.deeplearning4j.nn.multilayer.MultiLayerNetwork
类名称:MultiLayerNetwork
方法名:getLayerWiseConfigurations
暂无
代码示例来源:origin: deeplearning4j/dl4j-examples
public static void saveModel(FileSystem fs, Model model ) throws Exception{
String json = null;
if (model instanceof MultiLayerNetwork) {
json = ((MultiLayerNetwork)model).getLayerWiseConfigurations().toJson();
} else if (model instanceof ComputationGraph) {
json = ((ComputationGraph)model).getConfiguration().toJson();
}
byte [] byts = json.getBytes();
FSDataOutputStream out = fs.create(new Path(modelPath));
out.write(byts);
out.hsync();
fs.close();
}
}
代码示例来源:origin: de.datexis/texoo-core
public MultiLayerConfiguration getLayerConfiguration() {
if(net == null) return null;
else if(net instanceof MultiLayerNetwork) return ((MultiLayerNetwork) net).getLayerWiseConfigurations();
else return null;
}
代码示例来源:origin: org.deeplearning4j/deeplearning4j-nn
/**
* Prints the configuration
*/
public void printConfiguration() {
StringBuilder sb = new StringBuilder();
int count = 0;
for (NeuralNetConfiguration conf : getLayerWiseConfigurations().getConfs()) {
sb.append(" Layer " + count++ + " conf " + conf);
}
log.info(sb.toString());
}
代码示例来源:origin: CampagneLaboratory/variationanalysis
protected static void save(MultiLayerNetwork net, String confOut, String paramOut, String updaterOut) throws IOException {
String confJSON = net.getLayerWiseConfigurations().toJson();
INDArray params = net.params();
Updater updater = net.getUpdater();
FileUtils.writeStringToFile(new File(confOut), confJSON, "UTF-8");
try (DataOutputStream dos = new DataOutputStream(new BufferedOutputStream(Files.newOutputStream(Paths.get(paramOut))))) {
Nd4j.write(params, dos);
}
try (ObjectOutputStream oos = new ObjectOutputStream(new BufferedOutputStream(new FileOutputStream(new File(updaterOut))))) {
oos.writeObject(updater);
}
}
代码示例来源:origin: org.deeplearning4j/deeplearning4j-nn
/**
* Multilayer Network to tweak for transfer learning
* @param origModel
*/
public Builder(MultiLayerNetwork origModel) {
this.origModel = origModel;
this.origConf = origModel.getLayerWiseConfigurations().clone();
this.inputPreProcessors = origConf.getInputPreProcessors();
}
代码示例来源:origin: apache/opennlp-sandbox
/**
* Zips the current state of the model and writes it stream
* @param stream stream to write
* @throws IOException
*/
public void saveModel(OutputStream stream) throws IOException {
try (ZipOutputStream zipOut = new ZipOutputStream(new BufferedOutputStream(stream))) {
// Write out manifest
zipOut.putNextEntry(new ZipEntry(MANIFEST));
String comments = "Created-By:" + System.getenv("USER") + " at " + new Date().toString()
+ "\nModel-Version: " + VERSION
+ "\nModel-Schema:" + MODEL_NAME;
manifest.store(zipOut, comments);
zipOut.closeEntry();
// Write out the network
zipOut.putNextEntry(new ZipEntry(NETWORK));
byte[] jModel = network.getLayerWiseConfigurations().toJson().getBytes();
zipOut.write(jModel);
zipOut.closeEntry();
//Write out the network coefficients
zipOut.putNextEntry(new ZipEntry(WEIGHTS));
Nd4j.write(network.params(), new DataOutputStream(zipOut));
zipOut.closeEntry();
// Write out vectors
zipOut.putNextEntry(new ZipEntry(GLOVES));
gloves.writeOut(zipOut, false);
zipOut.closeEntry();
zipOut.finish();
}
}
代码示例来源:origin: org.deeplearning4j/deeplearning4j-nn
/**
* Calculate activation from previous layer including pre processing where necessary
*
* @param curr the current layer
* @param input the input
* @return the activation from the previous layer
*/
public INDArray activationFromPrevLayer(int curr, INDArray input, boolean training) {
if (getLayerWiseConfigurations().getInputPreProcess(curr) != null)
input = getLayerWiseConfigurations().getInputPreProcess(curr).preProcess(input, getInputMiniBatchSize());
INDArray ret = layers[curr].activate(input, training);
return ret;
}
代码示例来源:origin: org.deeplearning4j/deeplearning4j-nn
/**
* Compute input linear transformation (z) from previous layer
* Apply pre processing transformation where necessary
*
* @param curr the current layer
* @param input the input
* @param training training or test mode
* @return the activation from the previous layer
*/
public INDArray zFromPrevLayer(int curr, INDArray input, boolean training) {
if (getLayerWiseConfigurations().getInputPreProcess(curr) != null)
input = getLayerWiseConfigurations().getInputPreProcess(curr).preProcess(input, input.size(0));
INDArray ret = layers[curr].preOutput(input, training);
return ret;
}
代码示例来源:origin: org.deeplearning4j/arbiter-deeplearning4j
earlyStoppingConfiguration, nEpochs);
} else {
dl4jConfiguration = new DL4JConfiguration(((MultiLayerNetwork) m).getLayerWiseConfigurations(),
earlyStoppingConfiguration, nEpochs);
代码示例来源:origin: org.deeplearning4j/deeplearning4j-nn
@Override
public INDArray preOutput(INDArray x) {
INDArray lastLayerActivation = x;
for (int i = 0; i < layers.length - 1; i++) {
if (getLayerWiseConfigurations().getInputPreProcess(i) != null)
lastLayerActivation = getLayerWiseConfigurations().getInputPreProcess(i).preProcess(lastLayerActivation,
getInputMiniBatchSize());
lastLayerActivation = layers[i].activate(lastLayerActivation);
}
if (getLayerWiseConfigurations().getInputPreProcess(layers.length - 1) != null)
lastLayerActivation = getLayerWiseConfigurations().getInputPreProcess(layers.length - 1)
.preProcess(lastLayerActivation, getInputMiniBatchSize());
return layers[layers.length - 1].preOutput(lastLayerActivation);
}
代码示例来源:origin: org.deeplearning4j/deeplearning4j-nn
/**
* Compute activations from input to output of the output layer
*
* @return the list of activations for each layer
*/
public List<INDArray> feedForward(INDArray input) {
if (input == null)
throw new IllegalStateException("Unable to perform feed forward; no input found");
else if (this.getLayerWiseConfigurations().getInputPreProcess(0) != null)
setInput(getLayerWiseConfigurations().getInputPreProcess(0).preProcess(input, input.size(0)));
else
setInput(input);
return feedForward();
}
代码示例来源:origin: org.deeplearning4j/deeplearning4j-nn
if (getLayerWiseConfigurations().getInputPreProcess(i) != null)
currInput = getLayerWiseConfigurations().getInputPreProcess(i).preProcess(currInput, input.size(0));
if (layers[i] instanceof RecurrentLayer) {
currInput = ((RecurrentLayer) layers[i]).rnnActivateUsingStoredState(currInput, training,
代码示例来源:origin: org.deeplearning4j/deeplearning4j-nn
/**
* Compute activations from input to output of the output layer
*
* @return the list of activations for each layer
*/
public List<INDArray> computeZ(INDArray input, boolean training) {
if (input == null)
throw new IllegalStateException("Unable to perform feed forward; no input found");
else if (this.getLayerWiseConfigurations().getInputPreProcess(0) != null)
setInput(getLayerWiseConfigurations().getInputPreProcess(0).preProcess(input, getInputMiniBatchSize()));
else
setInput(input);
return computeZ(training);
}
代码示例来源:origin: org.deeplearning4j/deeplearning4j-nn
public static int getIterationCount(Model model) {
if (model instanceof MultiLayerNetwork) {
return ((MultiLayerNetwork) model).getLayerWiseConfigurations().getIterationCount();
} else if (model instanceof ComputationGraph) {
return ((ComputationGraph) model).getConfiguration().getIterationCount();
} else {
return model.conf().getIterationCount();
}
}
代码示例来源:origin: org.deeplearning4j/deeplearning4j-nn
public static void incrementIterationCount(Model model, int incrementBy) {
if (model instanceof MultiLayerNetwork) {
MultiLayerConfiguration conf = ((MultiLayerNetwork) model).getLayerWiseConfigurations();
conf.setIterationCount(conf.getIterationCount() + incrementBy);
} else if (model instanceof ComputationGraph) {
ComputationGraphConfiguration conf = ((ComputationGraph) model).getConfiguration();
conf.setIterationCount(conf.getIterationCount() + incrementBy);
} else {
model.conf().setIterationCount(model.conf().getIterationCount() + incrementBy);
}
}
代码示例来源:origin: sjsdfg/dl4j-tutorials
public static void main(String[] args) throws Exception {
//Define a simple MultiLayerNetwork:
MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
.weightInit(WeightInit.XAVIER)
.updater(new Nesterovs(0.01, 0.9))
.list()
.layer(0, new DenseLayer.Builder().nIn(4).nOut(3).activation(Activation.TANH).build())
.layer(1, new OutputLayer.Builder(LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD).activation(Activation.SOFTMAX).nIn(3).nOut(3).build())
.backprop(true).pretrain(false).build();
MultiLayerNetwork net = new MultiLayerNetwork(conf);
net.init();
//Save the model
File locationToSave = new File("model/MyMultiLayerNetwork.zip"); //Where to save the network. Note: the file is in .zip format - can be opened externally
/**
* 主要是用于保存模型的更新器信息
* 如果模型保存之后还打算继续训练,则进行保存 -> true 才能根据后面的数据进行增量更新
* 如果不打算继续训练 -> 模型定型之后,false
*/
boolean saveUpdater = true; //Updater: i.e., the state for Momentum, RMSProp, Adagrad etc. Save this if you want to train your network more in the future
ModelSerializer.writeModel(net, locationToSave, saveUpdater);
//Load the model
MultiLayerNetwork restored = ModelSerializer.restoreMultiLayerNetwork(locationToSave);
System.out.println("Saved and loaded parameters are equal: " + net.params().equals(restored.params()));
System.out.println("Saved and loaded configurations are equal: " + net.getLayerWiseConfigurations().equals(restored.getLayerWiseConfigurations()));
}
代码示例来源:origin: org.deeplearning4j/deeplearning4j-nn
IOutputLayer ol = (IOutputLayer) getOutputLayer();
INDArray olInput = activations.get(n - 1);
if (getLayerWiseConfigurations().getInputPreProcess(n - 1) != null) {
olInput = getLayerWiseConfigurations().getInputPreProcess(n - 1).preProcess(olInput, input.size(0));
代码示例来源:origin: org.deeplearning4j/deeplearning4j-nn
InputPreProcessor preProcessor = getLayerWiseConfigurations().getInputPreProcess(i);
代码示例来源:origin: rahul-raj/Deeplearning4J
System.out.println(restored.params()+" \n"+restored.getLayerWiseConfigurations());
INDArray output = customerLossPrediction.generateOutput(new File("test.csv"));
代码示例来源:origin: org.deeplearning4j/deeplearning4j-nn
private void initHelperMLN() {
if (applyFrozen) {
org.deeplearning4j.nn.api.Layer[] layers = origMLN.getLayers();
for (int i = frozenTill; i >= 0; i--) {
//unchecked?
layers[i] = new FrozenLayer(layers[i]);
}
origMLN.setLayers(layers);
}
for (int i = 0; i < origMLN.getnLayers(); i++) {
if (origMLN.getLayer(i) instanceof FrozenLayer) {
frozenInputLayer = i;
}
}
List<NeuralNetConfiguration> allConfs = new ArrayList<>();
for (int i = frozenInputLayer + 1; i < origMLN.getnLayers(); i++) {
allConfs.add(origMLN.getLayer(i).conf());
}
MultiLayerConfiguration c = origMLN.getLayerWiseConfigurations();
unFrozenSubsetMLN = new MultiLayerNetwork(new MultiLayerConfiguration.Builder().backprop(c.isBackprop())
.inputPreProcessors(c.getInputPreProcessors()).pretrain(c.isPretrain())
.backpropType(c.getBackpropType()).tBPTTForwardLength(c.getTbpttFwdLength())
.tBPTTBackwardLength(c.getTbpttBackLength()).confs(allConfs).build());
unFrozenSubsetMLN.init();
//copy over params
for (int i = frozenInputLayer + 1; i < origMLN.getnLayers(); i++) {
unFrozenSubsetMLN.getLayer(i - frozenInputLayer - 1).setParams(origMLN.getLayer(i).params());
}
//unFrozenSubsetMLN.setListeners(origMLN.getListeners());
}
内容来源于网络,如有侵权,请联系作者删除!