1

我正在使用 deeplearning4j 并且不明白如何从神经网络中获取分类向量的文本段落。

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.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);



    }
}

谢谢!雷南。

4

0 回答 0