Organize BasicDatasets into folders (#518)

This divides them into the folders:
- cv
- cv.classification
- nlp
- tabular

Change-Id: Ic925c69caae628d95d33f010e62c14bdb5ae6d17

basicdataset/src/main/java/ai/djl/basicdataset/BananaDetection.java → basicdataset/src/main/java/ai/djl/basicdataset/cv/BananaDetection.java

@@ -10,9 +10,10 @@
  * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
  * and limitations under the License.
  */
-package ai.djl.basicdataset;
+package ai.djl.basicdataset.cv;
 
 import ai.djl.Application;
+import ai.djl.basicdataset.BasicDatasets;
 import ai.djl.modality.cv.Image;
 import ai.djl.modality.cv.ImageFactory;
 import ai.djl.modality.cv.transform.ToTensor;

basicdataset/src/main/java/ai/djl/basicdataset/CocoDetection.java → basicdataset/src/main/java/ai/djl/basicdataset/cv/CocoDetection.java

@@ -10,9 +10,10 @@
  * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
  * and limitations under the License.
  */
-package ai.djl.basicdataset;
+package ai.djl.basicdataset.cv;
 
 import ai.djl.Application.CV;
+import ai.djl.basicdataset.BasicDatasets;
 import ai.djl.modality.cv.Image;
 import ai.djl.modality.cv.ImageFactory;
 import ai.djl.modality.cv.transform.ToTensor;

basicdataset/src/main/java/ai/djl/basicdataset/CocoMetadata.java → basicdataset/src/main/java/ai/djl/basicdataset/cv/CocoMetadata.java

@@ -10,7 +10,7 @@
  * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
  * and limitations under the License.
  */
-package ai.djl.basicdataset;
+package ai.djl.basicdataset.cv;
 
 import com.google.gson.annotations.SerializedName;
 import java.util.List;

basicdataset/src/main/java/ai/djl/basicdataset/CocoUtils.java → basicdataset/src/main/java/ai/djl/basicdataset/cv/CocoUtils.java

@@ -10,7 +10,7 @@
  * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
  * and limitations under the License.
  */
-package ai.djl.basicdataset;
+package ai.djl.basicdataset.cv;
 
 import ai.djl.util.JsonUtils;
 import java.io.IOException;
@@ -121,11 +121,10 @@ public List<Long> getAnnotationIdByImageId(long imageId) {
     }
 
     /**
-     * Returns an {@link ai.djl.basicdataset.CocoMetadata.Annotation} that corresponds to a given
-     * annotation id.
+     * Returns an {@link CocoMetadata.Annotation} that corresponds to a given annotation id.
      *
      * @param annotationId the annotation id to retrieve an annotation for
-     * @return an {@link ai.djl.basicdataset.CocoMetadata.Annotation}
+     * @return an {@link CocoMetadata.Annotation}
      */
     public CocoMetadata.Annotation getAnnotationById(long annotationId) {
         return annotationMap.get(annotationId);

basicdataset/src/main/java/ai/djl/basicdataset/PikachuDetection.java → basicdataset/src/main/java/ai/djl/basicdataset/cv/PikachuDetection.java

@@ -10,9 +10,10 @@
  * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
  * and limitations under the License.
  */
-package ai.djl.basicdataset;
+package ai.djl.basicdataset.cv;
 
 import ai.djl.Application.CV;
+import ai.djl.basicdataset.BasicDatasets;
 import ai.djl.modality.cv.Image;
 import ai.djl.modality.cv.ImageFactory;
 import ai.djl.modality.cv.transform.ToTensor;

basicdataset/src/main/java/ai/djl/basicdataset/AbstractImageFolder.java → basicdataset/src/main/java/ai/djl/basicdataset/cv/classification/AbstractImageFolder.java

@@ -10,7 +10,7 @@
  * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
  * and limitations under the License.
  */
-package ai.djl.basicdataset;
+package ai.djl.basicdataset.cv.classification;
 
 import ai.djl.modality.cv.Image;
 import ai.djl.modality.cv.ImageFactory;
@@ -140,7 +140,6 @@ public abstract static class ImageFolderBuilder<T extends ImageFolderBuilder<T>>
         int maxDepth;
 
         protected ImageFolderBuilder() {
-            flag = Image.Flag.COLOR;
             maxDepth = 1;
         }
 

basicdataset/src/main/java/ai/djl/basicdataset/CaptchaDataset.java → basicdataset/src/main/java/ai/djl/basicdataset/cv/classification/CaptchaDataset.java

@@ -10,9 +10,10 @@
  * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
  * and limitations under the License.
  */
-package ai.djl.basicdataset;
+package ai.djl.basicdataset.cv.classification;
 
 import ai.djl.Application.CV;
+import ai.djl.basicdataset.BasicDatasets;
 import ai.djl.modality.cv.Image;
 import ai.djl.modality.cv.ImageFactory;
 import ai.djl.modality.cv.transform.ToTensor;
@@ -145,7 +146,7 @@ private String getUsagePath() {
         }
     }
 
-    /** A builder for a {@link ai.djl.basicdataset.CaptchaDataset}. */
+    /** A builder for a {@link CaptchaDataset}. */
     public static final class Builder extends BaseBuilder<Builder> {
 
         Repository repository;

basicdataset/src/main/java/ai/djl/basicdataset/Cifar10.java → basicdataset/src/main/java/ai/djl/basicdataset/cv/classification/Cifar10.java

@@ -10,9 +10,10 @@
  * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
  * and limitations under the License.
  */
-package ai.djl.basicdataset;
+package ai.djl.basicdataset.cv.classification;
 
 import ai.djl.Application.CV;
+import ai.djl.basicdataset.BasicDatasets;
 import ai.djl.engine.Engine;
 import ai.djl.modality.cv.transform.ToTensor;
 import ai.djl.ndarray.NDArray;

basicdataset/src/main/java/ai/djl/basicdataset/FashionMnist.java → basicdataset/src/main/java/ai/djl/basicdataset/cv/classification/FashionMnist.java

@@ -10,9 +10,10 @@
  * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
  * and limitations under the License.
  */
-package ai.djl.basicdataset;
+package ai.djl.basicdataset.cv.classification;
 
 import ai.djl.Application.CV;
+import ai.djl.basicdataset.BasicDatasets;
 import ai.djl.engine.Engine;
 import ai.djl.modality.cv.transform.ToTensor;
 import ai.djl.ndarray.NDArray;

basicdataset/src/main/java/ai/djl/basicdataset/cv/classification/ImageClassificationDataset.java

@@ -0,0 +1,93 @@
+/*
+ * Copyright 2021 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License"). You may not use this file except in compliance
+ * with the License. A copy of the License is located at
+ *
+ * http://aws.amazon.com/apache2.0/
+ *
+ * or in the "license" file accompanying this file. This file is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES
+ * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
+ * and limitations under the License.
+ */
+package ai.djl.basicdataset.cv.classification;
+
+import ai.djl.modality.cv.Image;
+import ai.djl.ndarray.NDList;
+import ai.djl.ndarray.NDManager;
+import ai.djl.training.dataset.RandomAccessDataset;
+import ai.djl.training.dataset.Record;
+import java.io.IOException;
+
+/**
+ * A helper to create {@link ai.djl.training.dataset.Dataset}s for {@link
+ * ai.djl.Application.CV#IMAGE_CLASSIFICATION}.
+ */
+public abstract class ImageClassificationDataset extends RandomAccessDataset {
+
+    Image.Flag flag;
+
+    /**
+     * Creates a new instance of {@link RandomAccessDataset} with the given necessary
+     * configurations.
+     *
+     * @param builder a builder with the necessary configurations
+     */
+    public ImageClassificationDataset(BaseBuilder<?> builder) {
+        super(builder);
+        this.flag = builder.flag;
+    }
+
+    /**
+     * Returns the image at the given index in the dataset.
+     *
+     * @param index the index (if the dataset is a list of data items)
+     * @return the image
+     * @throws IOException if the image could not be loaded
+     */
+    protected abstract Image getImage(long index) throws IOException;
+
+    /**
+     * Returns the class of the data item at the given index.
+     *
+     * @param index the index (if the dataset is a list of data items)
+     * @return the class number or the index into the list of classes of the desired class name
+     * @throws IOException if the data could not be loaded
+     */
+    protected abstract long getClassNumber(long index) throws IOException;
+
+    /** {@inheritDoc} */
+    @Override
+    public Record get(NDManager manager, long index) throws IOException {
+        NDList data = new NDList(getImage(index).toNDArray(manager, flag));
+        NDList label = new NDList(manager.create(getClassNumber(index)));
+        return new Record(data, label);
+    }
+
+    /**
+     * Used to build an {@link ImageClassificationDataset}.
+     *
+     * @param <T> the builder type
+     */
+    @SuppressWarnings("rawtypes")
+    public abstract static class BaseBuilder<T extends BaseBuilder<T>>
+            extends RandomAccessDataset.BaseBuilder<T> {
+
+        Image.Flag flag;
+
+        protected BaseBuilder() {
+            flag = Image.Flag.COLOR;
+        }
+
+        /**
+         * Sets the optional color mode flag.
+         *
+         * @param flag the color mode flag
+         * @return this builder
+         */
+        public T optFlag(Image.Flag flag) {
+            this.flag = flag;
+            return self();
+        }
+    }
+}

basicdataset/src/main/java/ai/djl/basicdataset/ImageFolder.java → basicdataset/src/main/java/ai/djl/basicdataset/cv/classification/ImageFolder.java

@@ -10,7 +10,7 @@
  * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
  * and limitations under the License.
  */
-package ai.djl.basicdataset;
+package ai.djl.basicdataset.cv.classification;
 
 import ai.djl.modality.cv.transform.ToTensor;
 import ai.djl.translate.Pipeline;

basicdataset/src/main/java/ai/djl/basicdataset/ImageNet.java → basicdataset/src/main/java/ai/djl/basicdataset/cv/classification/ImageNet.java

@@ -10,7 +10,7 @@
  * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
  * and limitations under the License.
  */
-package ai.djl.basicdataset;
+package ai.djl.basicdataset.cv.classification;
 
 import ai.djl.modality.cv.transform.ToTensor;
 import ai.djl.training.dataset.Dataset;

basicdataset/src/main/java/ai/djl/basicdataset/Mnist.java → basicdataset/src/main/java/ai/djl/basicdataset/cv/classification/Mnist.java

@@ -10,9 +10,10 @@
  * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
  * and limitations under the License.
  */
-package ai.djl.basicdataset;
+package ai.djl.basicdataset.cv.classification;
 
 import ai.djl.Application.CV;
+import ai.djl.basicdataset.BasicDatasets;
 import ai.djl.engine.Engine;
 import ai.djl.modality.cv.transform.ToTensor;
 import ai.djl.ndarray.NDArray;

basicdataset/src/main/java/ai/djl/basicdataset/cv/classification/package-info.java

@@ -0,0 +1,17 @@
+/*
+ * Copyright 2021 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License"). You may not use this file except in compliance
+ * with the License. A copy of the License is located at
+ *
+ * http://aws.amazon.com/apache2.0/
+ *
+ * or in the "license" file accompanying this file. This file is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES
+ * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
+ * and limitations under the License.
+ */
+
+/**
+ * Contains a library of built-in datasets for {@link ai.djl.Application.CV#IMAGE_CLASSIFICATION}.
+ */
+package ai.djl.basicdataset.cv.classification;

basicdataset/src/main/java/ai/djl/basicdataset/cv/package-info.java

@@ -0,0 +1,15 @@
+/*
+ * Copyright 2021 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License"). You may not use this file except in compliance
+ * with the License. A copy of the License is located at
+ *
+ * http://aws.amazon.com/apache2.0/
+ *
+ * or in the "license" file accompanying this file. This file is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES
+ * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
+ * and limitations under the License.
+ */
+
+/** Contains a library of built-in datasets for {@link ai.djl.Application.CV}. */
+package ai.djl.basicdataset.cv;

basicdataset/src/main/java/ai/djl/basicdataset/AmazonReview.java → basicdataset/src/main/java/ai/djl/basicdataset/nlp/AmazonReview.java

@@ -10,9 +10,11 @@
  * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
  * and limitations under the License.
  */
-package ai.djl.basicdataset;
+package ai.djl.basicdataset.nlp;
 
 import ai.djl.Application;
+import ai.djl.basicdataset.BasicDatasets;
+import ai.djl.basicdataset.tabular.CsvDataset;
 import ai.djl.repository.Artifact;
 import ai.djl.repository.MRL;
 import ai.djl.repository.Repository;

basicdataset/src/main/java/ai/djl/basicdataset/CookingStackExchange.java → basicdataset/src/main/java/ai/djl/basicdataset/nlp/CookingStackExchange.java

@@ -10,9 +10,11 @@
  * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
  * and limitations under the License.
  */
-package ai.djl.basicdataset;
+package ai.djl.basicdataset.nlp;
 
 import ai.djl.Application.NLP;
+import ai.djl.basicdataset.BasicDatasets;
+import ai.djl.basicdataset.RawDataset;
 import ai.djl.ndarray.NDManager;
 import ai.djl.repository.Artifact;
 import ai.djl.repository.MRL;

basicdataset/src/main/java/ai/djl/basicdataset/StanfordMovieReview.java → basicdataset/src/main/java/ai/djl/basicdataset/nlp/StanfordMovieReview.java

@@ -10,7 +10,7 @@
  * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
  * and limitations under the License.
  */
-package ai.djl.basicdataset;
+package ai.djl.basicdataset.nlp;
 
 import ai.djl.Application.NLP;
 import ai.djl.modality.nlp.embedding.EmbeddingException;

basicdataset/src/main/java/ai/djl/basicdataset/TatoebaEnglishFrenchDataset.java → basicdataset/src/main/java/ai/djl/basicdataset/nlp/TatoebaEnglishFrenchDataset.java

@@ -10,7 +10,7 @@
  * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
  * and limitations under the License.
  */
-package ai.djl.basicdataset;
+package ai.djl.basicdataset.nlp;
 
 import ai.djl.Application.NLP;
 import ai.djl.modality.nlp.embedding.EmbeddingException;

basicdataset/src/main/java/ai/djl/basicdataset/TextDataset.java → basicdataset/src/main/java/ai/djl/basicdataset/nlp/TextDataset.java

@@ -10,8 +10,9 @@
  * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
  * and limitations under the License.
  */
-package ai.djl.basicdataset;
+package ai.djl.basicdataset.nlp;
 
+import ai.djl.basicdataset.BasicDatasets;
 import ai.djl.basicdataset.utils.TextData;
 import ai.djl.basicdataset.utils.TextData.Configuration;
 import ai.djl.engine.Engine;

basicdataset/src/main/java/ai/djl/basicdataset/nlp/package-info.java

@@ -0,0 +1,15 @@
+/*
+ * Copyright 2021 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License"). You may not use this file except in compliance
+ * with the License. A copy of the License is located at
+ *
+ * http://aws.amazon.com/apache2.0/
+ *
+ * or in the "license" file accompanying this file. This file is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES
+ * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
+ * and limitations under the License.
+ */
+
+/** Contains a library of built-in datasets for {@link ai.djl.Application.NLP}. */
+package ai.djl.basicdataset.nlp;

basicdataset/src/main/java/ai/djl/basicdataset/AirfoilRandomAccess.java → basicdataset/src/main/java/ai/djl/basicdataset/tabular/AirfoilRandomAccess.java

@@ -10,9 +10,10 @@
  * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
  * and limitations under the License.
  */
-package ai.djl.basicdataset;
+package ai.djl.basicdataset.tabular;
 
 import ai.djl.Application;
+import ai.djl.basicdataset.BasicDatasets;
 import ai.djl.ndarray.NDList;
 import ai.djl.ndarray.NDManager;
 import ai.djl.ndarray.types.Shape;
@@ -54,8 +55,7 @@ public final class AirfoilRandomAccess extends CsvDataset {
     private Map<String, Float> std;
 
     /**
-     * Creates an instance of {@code RandomAccessDataset} with the arguments in {@link
-     * FashionMnist.Builder}.
+     * Creates an instance of {@code RandomAccessDataset} with the arguments in {@link Builder}.
      *
      * @param builder a builder with the required arguments
      */

basicdataset/src/main/java/ai/djl/basicdataset/AmesRandomAccess.java → basicdataset/src/main/java/ai/djl/basicdataset/tabular/AmesRandomAccess.java

@@ -10,9 +10,10 @@
  * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
  * and limitations under the License.
  */
-package ai.djl.basicdataset;
+package ai.djl.basicdataset.tabular;
 
 import ai.djl.Application.Tabular;
+import ai.djl.basicdataset.BasicDatasets;
 import ai.djl.repository.Artifact;
 import ai.djl.repository.MRL;
 import ai.djl.repository.Repository;