You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@opennlp.apache.org by ma...@apache.org on 2023/07/26 11:27:47 UTC
[opennlp] 01/01: improves existing JavaDoc of opennlp.dl component/package
This is an automated email from the ASF dual-hosted git repository.
mawiesne pushed a commit to branch OPENNLP-1506_Enhance_JavaDoc_in_opennlp.dl_package
in repository https://gitbox.apache.org/repos/asf/opennlp.git
commit dda901d75589fd99a12a8019eca2e4d1c27169a5
Author: Martin Wiesner <ma...@hs-heilbronn.de>
AuthorDate: Wed Jul 26 13:27:38 2023 +0200
improves existing JavaDoc of opennlp.dl component/package
---
.../src/main/java/opennlp/dl/AbstractDL.java | 13 ++++-----
.../opennlp/dl/doccat/DocumentCategorizerDL.java | 20 +++++++++-----
.../AverageClassificationScoringStrategy.java | 6 +++--
.../java/opennlp/dl/namefinder/NameFinderDL.java | 31 ++++++++++++++++++++--
.../java/opennlp/dl/vectors/SentenceVectorsDL.java | 14 +++++-----
5 files changed, 59 insertions(+), 25 deletions(-)
diff --git a/opennlp-dl/src/main/java/opennlp/dl/AbstractDL.java b/opennlp-dl/src/main/java/opennlp/dl/AbstractDL.java
index 2d22a359..7d891bea 100644
--- a/opennlp-dl/src/main/java/opennlp/dl/AbstractDL.java
+++ b/opennlp-dl/src/main/java/opennlp/dl/AbstractDL.java
@@ -46,27 +46,24 @@ public abstract class AbstractDL {
protected Map<String, Integer> vocab;
/**
- * Loads a vocabulary file from disk.
+ * Loads a vocabulary {@link File} from disk.
+ *
* @param vocabFile The vocabulary file.
* @return A map of vocabulary words to integer IDs.
- * @throws IOException Thrown if the vocabulary file cannot be opened and read.
+ *
+ * @throws IOException Thrown if the vocabulary file cannot be opened or read.
*/
public Map<String, Integer> loadVocab(final File vocabFile) throws IOException {
final Map<String, Integer> vocab = new HashMap<>();
-
final AtomicInteger counter = new AtomicInteger(0);
try (Stream<String> lines = Files.lines(Path.of(vocabFile.getPath()))) {
- lines.forEach(line -> {
- vocab.put(line, counter.getAndIncrement());
- });
-
+ lines.forEach(line -> vocab.put(line, counter.getAndIncrement()));
}
return vocab;
-
}
}
diff --git a/opennlp-dl/src/main/java/opennlp/dl/doccat/DocumentCategorizerDL.java b/opennlp-dl/src/main/java/opennlp/dl/doccat/DocumentCategorizerDL.java
index 28733c88..b4f5caa5 100644
--- a/opennlp-dl/src/main/java/opennlp/dl/doccat/DocumentCategorizerDL.java
+++ b/opennlp-dl/src/main/java/opennlp/dl/doccat/DocumentCategorizerDL.java
@@ -48,6 +48,10 @@ import opennlp.tools.tokenize.WordpieceTokenizer;
/**
* An implementation of {@link DocumentCategorizer} that performs document classification
* using ONNX models.
+ *
+ * @see DocumentCategorizer
+ * @see InferenceOptions
+ * @see ClassificationScoringStrategy
*/
public class DocumentCategorizerDL extends AbstractDL implements DocumentCategorizer {
@@ -58,16 +62,20 @@ public class DocumentCategorizerDL extends AbstractDL implements DocumentCategor
private final InferenceOptions inferenceOptions;
/**
- * Creates a new document categorizer using ONNX models.
- * @param modelFile The ONNX modelFile file.
- * @param vocabFile The modelFile's vocabulary file.
+ * Instantiates a {@link DocumentCategorizer document categorizer} using ONNX models.
+ *
+ * @param model The ONNX model file.
+ * @param vocabulary The model file's vocabulary file.
* @param categories The categories.
* @param classificationScoringStrategy Implementation of {@link ClassificationScoringStrategy} used
* to calculate the classification scores given the score of each
* individual document part.
* @param inferenceOptions {@link InferenceOptions} to control the inference.
+ *
+ * @throws OrtException Thrown if the {@code model} cannot be loaded.
+ * @throws IOException Thrown if errors occurred loading the {@code model} or {@code vocabulary}.
*/
- public DocumentCategorizerDL(File modelFile, File vocabFile, Map<Integer, String> categories,
+ public DocumentCategorizerDL(File model, File vocabulary, Map<Integer, String> categories,
ClassificationScoringStrategy classificationScoringStrategy,
InferenceOptions inferenceOptions)
throws IOException, OrtException {
@@ -79,8 +87,8 @@ public class DocumentCategorizerDL extends AbstractDL implements DocumentCategor
sessionOptions.addCUDA(inferenceOptions.getGpuDeviceId());
}
- this.session = env.createSession(modelFile.getPath(), sessionOptions);
- this.vocab = loadVocab(vocabFile);
+ this.session = env.createSession(model.getPath(), sessionOptions);
+ this.vocab = loadVocab(vocabulary);
this.tokenizer = new WordpieceTokenizer(vocab.keySet());
this.categories = categories;
this.classificationScoringStrategy = classificationScoringStrategy;
diff --git a/opennlp-dl/src/main/java/opennlp/dl/doccat/scoring/AverageClassificationScoringStrategy.java b/opennlp-dl/src/main/java/opennlp/dl/doccat/scoring/AverageClassificationScoringStrategy.java
index b9b2f620..50c5825f 100644
--- a/opennlp-dl/src/main/java/opennlp/dl/doccat/scoring/AverageClassificationScoringStrategy.java
+++ b/opennlp-dl/src/main/java/opennlp/dl/doccat/scoring/AverageClassificationScoringStrategy.java
@@ -20,8 +20,10 @@ package opennlp.dl.doccat.scoring;
import java.util.List;
/**
- * Calculates the document classification scores by averaging the scores for
- * all individual parts of a document.
+ * A {@link ClassificationScoringStrategy} which calculates the document classification scores
+ * by averaging the scores for all individual parts of a document.
+ *
+ * @see ClassificationScoringStrategy
*/
public class AverageClassificationScoringStrategy implements ClassificationScoringStrategy {
diff --git a/opennlp-dl/src/main/java/opennlp/dl/namefinder/NameFinderDL.java b/opennlp-dl/src/main/java/opennlp/dl/namefinder/NameFinderDL.java
index 803ece32..3cbf0e2a 100644
--- a/opennlp-dl/src/main/java/opennlp/dl/namefinder/NameFinderDL.java
+++ b/opennlp-dl/src/main/java/opennlp/dl/namefinder/NameFinderDL.java
@@ -18,6 +18,7 @@
package opennlp.dl.namefinder;
import java.io.File;
+import java.io.IOException;
import java.nio.LongBuffer;
import java.util.Arrays;
import java.util.HashMap;
@@ -43,6 +44,9 @@ import opennlp.tools.util.Span;
/**
* An implementation of {@link TokenNameFinder} that uses ONNX models.
+ *
+ * @see TokenNameFinder
+ * @see InferenceOptions
*/
public class NameFinderDL extends AbstractDL implements TokenNameFinder {
@@ -56,16 +60,39 @@ public class NameFinderDL extends AbstractDL implements TokenNameFinder {
private final Map<Integer, String> ids2Labels;
private final InferenceOptions inferenceOptions;
+ /**
+ * Instantiates a {@link TokenNameFinder name finder} using ONNX models.
+ *
+ * @param model The ONNX model file.
+ * @param vocabulary The model file's vocabulary file.
+ * @param ids2Labels The mapping of ids to labels.
+ * @param sentenceDetector The {@link SentenceDetector} to be used.
+ *
+ * @throws OrtException Thrown if the {@code model} cannot be loaded.
+ * @throws IOException Thrown if errors occurred loading the {@code model} or {@code vocabulary}.
+ */
public NameFinderDL(File model, File vocabulary, Map<Integer, String> ids2Labels,
- SentenceDetector sentenceDetector) throws Exception {
+ SentenceDetector sentenceDetector) throws IOException, OrtException {
this(model, vocabulary, ids2Labels, new InferenceOptions(), sentenceDetector);
}
+ /**
+ * Instantiates a {@link TokenNameFinder name finder} using ONNX models.
+ *
+ * @param model The ONNX model file.
+ * @param vocabulary The model file's vocabulary file.
+ * @param ids2Labels The mapping of ids to labels.
+ * @param inferenceOptions {@link InferenceOptions} to control the inference.
+ * @param sentenceDetector The {@link SentenceDetector} to be used.
+ *
+ * @throws OrtException Thrown if the {@code model} cannot be loaded.
+ * @throws IOException Thrown if errors occurred loading the {@code model} or {@code vocabulary}.
+ */
public NameFinderDL(File model, File vocabulary, Map<Integer, String> ids2Labels,
InferenceOptions inferenceOptions,
- SentenceDetector sentenceDetector) throws Exception {
+ SentenceDetector sentenceDetector) throws IOException, OrtException {
this.env = OrtEnvironment.getEnvironment();
diff --git a/opennlp-dl/src/main/java/opennlp/dl/vectors/SentenceVectorsDL.java b/opennlp-dl/src/main/java/opennlp/dl/vectors/SentenceVectorsDL.java
index b50cbe98..805b4118 100644
--- a/opennlp-dl/src/main/java/opennlp/dl/vectors/SentenceVectorsDL.java
+++ b/opennlp-dl/src/main/java/opennlp/dl/vectors/SentenceVectorsDL.java
@@ -28,8 +28,6 @@ import ai.onnxruntime.OnnxTensor;
import ai.onnxruntime.OrtEnvironment;
import ai.onnxruntime.OrtException;
import ai.onnxruntime.OrtSession;
-import org.slf4j.Logger;
-import org.slf4j.LoggerFactory;
import opennlp.dl.AbstractDL;
import opennlp.dl.Tokens;
@@ -42,14 +40,14 @@ import opennlp.tools.tokenize.WordpieceTokenizer;
*/
public class SentenceVectorsDL extends AbstractDL {
- private static final Logger logger = LoggerFactory.getLogger(SentenceVectorsDL.class);
-
/**
- * Creates an instance of the class.
+ * Instantiates a {@link SentenceVectorsDL sentence detector} using ONNX models.
+ *
* @param model The file name of a sentence vectors ONNX model.
* @param vocabulary The file name of the vocabulary file for the model.
- * @throws OrtException Thrown if the model cannot be loaded.
- * @throws IOException Thrown if the vocabulary file cannot be loaded.
+ *
+ * @throws OrtException Thrown if the {@code model} cannot be loaded.
+ * @throws IOException Thrown if errors occurred loading the {@code model} or {@code vocabulary}.
*/
public SentenceVectorsDL(final File model, final File vocabulary)
throws OrtException, IOException {
@@ -63,7 +61,9 @@ public class SentenceVectorsDL extends AbstractDL {
/**
* Generates vectors given a sentence.
+ *
* @param sentence The input sentence.
+ *
* @throws OrtException Thrown if an error occurs during inference.
*/
public float[] getVectors(final String sentence) throws OrtException {