protected void prepareFeats() { if (feats != null) return; final int numInstances = data.size(); feats = new double[numInstances][]; int index = 0; for (final T d : this.data) { feats[index++] = this.extractor.extractFeature(d).values; } }
protected void prepareFeats() { if (feats != null) return; final int numInstances = data.size(); feats = new double[numInstances][]; int index = 0; for (final T d : this.data) { feats[index++] = this.extractor.extractFeature(d).values; } }
public List<MixtureOfGaussians> extractGroupGaussians( UKBenchListDataset<IRecord<URL>> ukbenchObject) { List<MixtureOfGaussians> gaussians = new ArrayList<MixtureOfGaussians>(); int i = 0; for (IRecord<URL> imageURL : ukbenchObject) { MixtureOfGaussians gmm = gmmExtract.extractFeature(imageURL); gaussians.add(gmm); } return gaussians; }
public List<MixtureOfGaussians> extractGroupGaussians( UKBenchListDataset<IRecord<URL>> ukbenchObject) { List<MixtureOfGaussians> gaussians = new ArrayList<MixtureOfGaussians>(); int i = 0; for (IRecord<URL> imageURL : ukbenchObject) { MixtureOfGaussians gmm = gmmExtract.extractFeature(imageURL); gaussians.add(gmm); } return gaussians; }
Feature[] computeFeature(OBJECT object) { final FeatureVector feature = extractor.extractFeature(object); return LiblinearHelper.convert(feature, bias); }
@Override public FV extractFeature(OBJECT object) { return extractor.extractFeature(object).getFeatureVector(); }
@Override public void put(int id, DATA data) { index.put(id, extractor.extractFeature(data)); }
@Override public FEATURE get(int index) { return extractor.extractFeature(input.get(index)); }
double[] computeFeatureDense(OBJECT object) { final FeatureVector feature = extractor.extractFeature(object); return LiblinearHelper.convertDense(feature, bias); }
@Override public FV extractFeature(OBJECT object) { return extractor.extractFeature(object).getFeatureVector(); }
@Override public void train(final Annotated<OBJECT, ANNOTATION> annotated) { this.nn = null; this.features.add(this.extractor.extractFeature(annotated.getObject())); final Collection<ANNOTATION> anns = annotated.getAnnotations(); this.annotations.add(anns); this.annotationsSet.addAll(anns); }
@Override public List<ScoredAnnotation<ANNOTATION>> annotate(OBJECT object) { final FEATURE f = extractor.extractFeature(object); final List<ScoredAnnotation<ANNOTATION>> result = new ArrayList<ScoredAnnotation<ANNOTATION>>(); result.add(new ScoredAnnotation<ANNOTATION>(model.predict(f), 1)); return result; } }
@Override public FEATURE get(int index) { return extractor.extractFeature( data.get(indices.get(index)).getObject() ); }
@Override public FEATURE get(int index) { return extractor.extractFeature( data.get(selectedIndices.get(index)).getObject() ); }
@Override public DoubleFV extractFeature(T object) { return map.evaluate(inner.extractFeature(object).asDoubleFV()); } }
@Override public void train(List<? extends Annotated<OBJECT, ANNOTATION>> data) { final List<IndependentPair<FEATURE, ANNOTATION>> featureData = new ArrayList<IndependentPair<FEATURE, ANNOTATION>>(); for (final Annotated<OBJECT, ANNOTATION> a : data) { final FEATURE f = extractor.extractFeature(a.getObject()); for (final ANNOTATION ann : a.getAnnotations()) featureData.add(IndependentPair.pair(f, ann)); } model.estimate(featureData); }
@Override public List<ScoredAnnotation<ANNOTATION>> annotate(OBJECT object) { if (isInvalid) { batchAnnotator.train(featureCache.getDataset()); isInvalid = false; } return batchAnnotator.annotate(extractor.extractFeature(object)); } }
@Override public void train(Annotated<OBJECT, ANNOTATION> annotated) { final FEATURE fv = extractor.extractFeature(annotated.getObject()); featureCache.add(annotated.getAnnotations(), fv); isInvalid = true; }
@Override public List<ScoredAnnotation<ANNOTATION>> annotate(OBJECT object) { final FeatureVector feature = extractor.extractFeature(object); final Vector vec = VectorFactory.getDefault().copyArray(feature.asDoubleVector()); return mode.getAnnotations(categorizer, vec); } }
@Override public void train(Annotated<OBJECT, ANNOTATION> annotated) { final FeatureVector feature = extractor.extractFeature(annotated.getObject()); final Vector vec = VectorFactory.getDefault().copyArray(feature.asDoubleVector()); for (final ANNOTATION ann : annotated.getAnnotations()) { learner.update(categorizer, new DefaultInputOutputPair<Vector, ANNOTATION>(vec, ann)); } }