本文整理汇总了Java中org.deeplearning4j.models.embeddings.loader.WordVectorSerializer.readParagraphVectors方法的典型用法代码示例。如果您正苦于以下问题：Java WordVectorSerializer.readParagraphVectors方法的具体用法？Java WordVectorSerializer.readParagraphVectors怎么用？Java WordVectorSerializer.readParagraphVectors使用的例子？那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类org.deeplearning4j.models.embeddings.loader.WordVectorSerializer的用法示例。
在下文中一共展示了WordVectorSerializer.readParagraphVectors方法的4个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Java代码示例。
示例1: start
import org.deeplearning4j.models.embeddings.loader.WordVectorSerializer; //导入方法依赖的package包/类
public void start() throws Exception {
if (serializeFile().exists()) {
try {
log.info("Loading from " + serializeFile().getAbsolutePath());
paragraphVectors = WordVectorSerializer.readParagraphVectors(serializeFile());
} catch (Exception e) {
log.debug(e.getMessage(), e);
makeParagraphVectors();
}
} else {
makeParagraphVectors();
}
}
示例2: loadParagraphVectors
import org.deeplearning4j.models.embeddings.loader.WordVectorSerializer; //导入方法依赖的package包/类
private static ParagraphVectors loadParagraphVectors() {
ParagraphVectors paragraphVectors = null;
try {
paragraphVectors = WordVectorSerializer.readParagraphVectors((PARAGRAPHVECTORMODELPATH));
TokenizerFactory t = new DefaultTokenizerFactory();
t.setTokenPreProcessor(new CommonPreprocessor());
paragraphVectors.setTokenizerFactory(t);
paragraphVectors.getConfiguration().setIterations(10); // please note, we set iterations to 1 here, just to speedup inference
} catch (IOException e) {
e.printStackTrace();
}
return paragraphVectors;
}
示例3: testParaVecSerialization1
import org.deeplearning4j.models.embeddings.loader.WordVectorSerializer; //导入方法依赖的package包/类
@Test
public void testParaVecSerialization1() throws Exception {
VectorsConfiguration configuration = new VectorsConfiguration();
configuration.setIterations(14123);
configuration.setLayersSize(156);
INDArray syn0 = Nd4j.rand(100, configuration.getLayersSize());
INDArray syn1 = Nd4j.rand(100, configuration.getLayersSize());
AbstractCache<VocabWord> cache = new AbstractCache.Builder<VocabWord>().build();
for (int i = 0; i < 100; i++) {
VocabWord word = new VocabWord((float) i, "word_" + i);
List<Integer> points = new ArrayList<>();
List<Byte> codes = new ArrayList<>();
int num = org.apache.commons.lang3.RandomUtils.nextInt(1, 20);
for (int x = 0; x < num; x++) {
points.add(org.apache.commons.lang3.RandomUtils.nextInt(1, 100000));
codes.add(org.apache.commons.lang3.RandomUtils.nextBytes(10)[0]);
}
if (RandomUtils.nextInt(10) < 3) {
word.markAsLabel(true);
}
word.setIndex(i);
word.setPoints(points);
word.setCodes(codes);
cache.addToken(word);
cache.addWordToIndex(i, word.getLabel());
}
InMemoryLookupTable<VocabWord> lookupTable =
(InMemoryLookupTable<VocabWord>) new InMemoryLookupTable.Builder<VocabWord>()
.vectorLength(configuration.getLayersSize()).cache(cache).build();
lookupTable.setSyn0(syn0);
lookupTable.setSyn1(syn1);
ParagraphVectors originalVectors =
new ParagraphVectors.Builder(configuration).vocabCache(cache).lookupTable(lookupTable).build();
File tempFile = File.createTempFile("paravec", "tests");
tempFile.deleteOnExit();
WordVectorSerializer.writeParagraphVectors(originalVectors, tempFile);
ParagraphVectors restoredVectors = WordVectorSerializer.readParagraphVectors(tempFile);
InMemoryLookupTable<VocabWord> restoredLookupTable =
(InMemoryLookupTable<VocabWord>) restoredVectors.getLookupTable();
AbstractCache<VocabWord> restoredVocab = (AbstractCache<VocabWord>) restoredVectors.getVocab();
assertEquals(restoredLookupTable.getSyn0(), lookupTable.getSyn0());
assertEquals(restoredLookupTable.getSyn1(), lookupTable.getSyn1());
for (int i = 0; i < cache.numWords(); i++) {
assertEquals(cache.elementAtIndex(i).isLabel(), restoredVocab.elementAtIndex(i).isLabel());
assertEquals(cache.wordAtIndex(i), restoredVocab.wordAtIndex(i));
assertEquals(cache.elementAtIndex(i).getElementFrequency(),
restoredVocab.elementAtIndex(i).getElementFrequency(), 0.1f);
List<Integer> originalPoints = cache.elementAtIndex(i).getPoints();
List<Integer> restoredPoints = restoredVocab.elementAtIndex(i).getPoints();
assertEquals(originalPoints.size(), restoredPoints.size());
for (int x = 0; x < originalPoints.size(); x++) {
assertEquals(originalPoints.get(x), restoredPoints.get(x));
}
List<Byte> originalCodes = cache.elementAtIndex(i).getCodes();
List<Byte> restoredCodes = restoredVocab.elementAtIndex(i).getCodes();
assertEquals(originalCodes.size(), restoredCodes.size());
for (int x = 0; x < originalCodes.size(); x++) {
assertEquals(originalCodes.get(x), restoredCodes.get(x));
}
}
}
示例4: testBiggerParavecLoader
import org.deeplearning4j.models.embeddings.loader.WordVectorSerializer; //导入方法依赖的package包/类
@Ignore
@Test
public void testBiggerParavecLoader() throws Exception {
ParagraphVectors vectors =
WordVectorSerializer.readParagraphVectors("C:\\Users\\raver\\Downloads\\10kNews.zip");
}