Java 如何获得文本段落dl4j神经网络
我正在深入学习4J,但不知道如何从神经网络中获得向量分类的文本段落 我只能得到分类率 这是我的代码:Java 如何获得文本段落dl4j神经网络,java,deep-learning,dl4j,Java,Deep Learning,Dl4j,我正在深入学习4J,但不知道如何从神经网络中获得向量分类的文本段落 我只能得到分类率 这是我的代码: public static void main(String[] args) throws Exception { ClassPathResource resource = new ClassPathResource("paravec/recortes"); LabelAwareIterator iterator = new FileLabelAwareIterator.Bu
public static void main(String[] args) throws Exception {
ClassPathResource resource = new ClassPathResource("paravec/recortes");
LabelAwareIterator iterator = new FileLabelAwareIterator.Builder()
.addSourceFolder(resource.getFile()).build();
TokenizerFactory t = new DefaultTokenizerFactory();
t.setTokenPreProcessor(new CommonPreprocessor());
ParagraphVectors paragraphVectors = new ParagraphVectors.Builder()
.learningRate(0.025).minLearningRate(0.001).batchSize(1000)
.epochs(10).iterate(iterator).trainWordVectors(true)
.tokenizerFactory(t).build();
paragraphVectors.fit();
ClassPathResource unlabeledResource = new ClassPathResource(
"paravec/caderno");
FileLabelAwareIterator unlabeledIterator = new FileLabelAwareIterator.Builder()
.addSourceFolder(unlabeledResource.getFile()).build();
MeansBuilder meansBuilder = new MeansBuilder(
(InMemoryLookupTable<VocabWord>) paragraphVectors
.getLookupTable(),
t);
LabelSeeker seeker = new LabelSeeker(iterator.getLabelsSource()
.getLabels(),
(InMemoryLookupTable<VocabWord>) paragraphVectors
.getLookupTable());
while (unlabeledIterator.hasNextDocument()) {
LabelledDocument document = unlabeledIterator.nextDocument();
//how to get text paragraph?
INDArray documentAsCentroid = meansBuilder
.documentAsVector(document);
}
}
publicstaticvoidmain(字符串[]args)引发异常{
ClassPathResource资源=新的ClassPathResource(“paravec/recortes”);
LabelAwareIterator迭代器=新文件LabelAwareIterator.Builder()
.addSourceFolder(resource.getFile()).build();
TokenizerFactory t=新的DefaultTokenizerFactory();
t、 setTokenPreProcessor(新的CommonPreprocessor());
ParagraphVectors ParagraphVectors=新的ParagraphVectors.Builder()
.学习率(0.025).最小学习率(0.001).批量大小(1000)
.epochs(10).iterate(迭代器).trainWordVectors(true)
.tokenizerFactory(t).build();
paragraphVectors.fit();
ClassPathResource unlabeledResource=新的ClassPathResource(
“paravec/caderno”);
FileLabelAwareIterator unlabeledIterator=新建FileLabelAwareIterator.Builder()
.addSourceFolder(unlabeledResource.getFile()).build();
MeansBuilder MeansBuilder=新MeansBuilder(
(InMemoryLookupTable)段落向量
.getLookupTable(),
t) );
LabelSeeker-seeker=新的LabelSeeker(迭代器.getLabelsSource()
.getLabels(),
(InMemoryLookupTable)段落向量
.getLookupTable());
while(未标记的迭代器.hasNextDocument()){
LabelledDocument文档=未标记的迭代器.nextDocument();
//如何获取文本段落?
INDArray documentAsCentroid=meansBuilder
.文件部门(文件);
}
}
谢谢!
Renan.请加入Gitter上的社区!请加入Gitter上的社区!