Examples with ParentPathLabelGenerator org.datavec.api.io.labels.ParentPathLabelGenerator used on opensource projects

Example 1 with ParentPathLabelGenerator

use of org.datavec.api.io.labels.ParentPathLabelGenerator in project deeplearning4j by deeplearning4j.

the class RecordReaderMultiDataSetIteratorTest method testImagesRRDMSI.

@Test
public void testImagesRRDMSI() throws Exception {
    File parentDir = Files.createTempDir();
    parentDir.deleteOnExit();
    String str1 = FilenameUtils.concat(parentDir.getAbsolutePath(), "Zico/");
    String str2 = FilenameUtils.concat(parentDir.getAbsolutePath(), "Ziwang_Xu/");
    File f1 = new File(str1);
    File f2 = new File(str2);
    f1.mkdirs();
    f2.mkdirs();
    writeStreamToFile(new File(FilenameUtils.concat(f1.getPath(), "Zico_0001.jpg")), new ClassPathResource("lfwtest/Zico/Zico_0001.jpg").getInputStream());
    writeStreamToFile(new File(FilenameUtils.concat(f2.getPath(), "Ziwang_Xu_0001.jpg")), new ClassPathResource("lfwtest/Ziwang_Xu/Ziwang_Xu_0001.jpg").getInputStream());
    int outputNum = 2;
    Random r = new Random(12345);
    ParentPathLabelGenerator labelMaker = new ParentPathLabelGenerator();
    ImageRecordReader rr1 = new ImageRecordReader(10, 10, 1, labelMaker);
    ImageRecordReader rr1s = new ImageRecordReader(5, 5, 1, labelMaker);
    rr1.initialize(new FileSplit(parentDir));
    rr1s.initialize(new FileSplit(parentDir));
    MultiDataSetIterator trainDataIterator = new RecordReaderMultiDataSetIterator.Builder(1).addReader("rr1", rr1).addReader("rr1s", rr1s).addInput("rr1", 0, 0).addInput("rr1s", 0, 0).addOutputOneHot("rr1s", 1, outputNum).build();
    //Now, do the same thing with ImageRecordReader, and check we get the same results:
    ImageRecordReader rr1_b = new ImageRecordReader(10, 10, 1, labelMaker);
    ImageRecordReader rr1s_b = new ImageRecordReader(5, 5, 1, labelMaker);
    rr1_b.initialize(new FileSplit(parentDir));
    rr1s_b.initialize(new FileSplit(parentDir));
    DataSetIterator dsi1 = new RecordReaderDataSetIterator(rr1_b, 1, 1, 2);
    DataSetIterator dsi2 = new RecordReaderDataSetIterator(rr1s_b, 1, 1, 2);
    for (int i = 0; i < 2; i++) {
        MultiDataSet mds = trainDataIterator.next();
        DataSet d1 = dsi1.next();
        DataSet d2 = dsi2.next();
        assertEquals(d1.getFeatureMatrix(), mds.getFeatures(0));
        assertEquals(d2.getFeatureMatrix(), mds.getFeatures(1));
        assertEquals(d1.getLabels(), mds.getLabels(0));
    }
}

Example 2 with ParentPathLabelGenerator

use of org.datavec.api.io.labels.ParentPathLabelGenerator in project deeplearning4j by deeplearning4j.

the class RecordReaderMultiDataSetIteratorTest method testImagesRRDMSI_Batched.

@Test
public void testImagesRRDMSI_Batched() throws Exception {
    File parentDir = Files.createTempDir();
    parentDir.deleteOnExit();
    String str1 = FilenameUtils.concat(parentDir.getAbsolutePath(), "Zico/");
    String str2 = FilenameUtils.concat(parentDir.getAbsolutePath(), "Ziwang_Xu/");
    File f1 = new File(str1);
    File f2 = new File(str2);
    f1.mkdirs();
    f2.mkdirs();
    writeStreamToFile(new File(FilenameUtils.concat(f1.getPath(), "Zico_0001.jpg")), new ClassPathResource("lfwtest/Zico/Zico_0001.jpg").getInputStream());
    writeStreamToFile(new File(FilenameUtils.concat(f2.getPath(), "Ziwang_Xu_0001.jpg")), new ClassPathResource("lfwtest/Ziwang_Xu/Ziwang_Xu_0001.jpg").getInputStream());
    int outputNum = 2;
    ParentPathLabelGenerator labelMaker = new ParentPathLabelGenerator();
    ImageRecordReader rr1 = new ImageRecordReader(10, 10, 1, labelMaker);
    ImageRecordReader rr1s = new ImageRecordReader(5, 5, 1, labelMaker);
    rr1.initialize(new FileSplit(parentDir));
    rr1s.initialize(new FileSplit(parentDir));
    MultiDataSetIterator trainDataIterator = new RecordReaderMultiDataSetIterator.Builder(2).addReader("rr1", rr1).addReader("rr1s", rr1s).addInput("rr1", 0, 0).addInput("rr1s", 0, 0).addOutputOneHot("rr1s", 1, outputNum).build();
    //Now, do the same thing with ImageRecordReader, and check we get the same results:
    ImageRecordReader rr1_b = new ImageRecordReader(10, 10, 1, labelMaker);
    ImageRecordReader rr1s_b = new ImageRecordReader(5, 5, 1, labelMaker);
    rr1_b.initialize(new FileSplit(parentDir));
    rr1s_b.initialize(new FileSplit(parentDir));
    DataSetIterator dsi1 = new RecordReaderDataSetIterator(rr1_b, 2, 1, 2);
    DataSetIterator dsi2 = new RecordReaderDataSetIterator(rr1s_b, 2, 1, 2);
    MultiDataSet mds = trainDataIterator.next();
    DataSet d1 = dsi1.next();
    DataSet d2 = dsi2.next();
    assertEquals(d1.getFeatureMatrix(), mds.getFeatures(0));
    assertEquals(d2.getFeatureMatrix(), mds.getFeatures(1));
    assertEquals(d1.getLabels(), mds.getLabels(0));
}

Example 3 with ParentPathLabelGenerator

use of org.datavec.api.io.labels.ParentPathLabelGenerator in project deeplearning4j by deeplearning4j.

the class TestDataVecDataSetFunctions method testDataVecDataSetFunction.

@Test
public void testDataVecDataSetFunction() throws Exception {
    JavaSparkContext sc = getContext();
    //Test Spark record reader functionality vs. local
    File f = new File("src/test/resources/imagetest/0/a.bmp");
    //Need this for Spark: can't infer without init call
    List<String> labelsList = Arrays.asList("0", "1");
    String path = f.getPath();
    String folder = path.substring(0, path.length() - 7);
    path = folder + "*";
    JavaPairRDD<String, PortableDataStream> origData = sc.binaryFiles(path);
    //4 images
    assertEquals(4, origData.count());
    ImageRecordReader rr = new ImageRecordReader(28, 28, 1, new ParentPathLabelGenerator());
    rr.setLabels(labelsList);
    org.datavec.spark.functions.RecordReaderFunction rrf = new org.datavec.spark.functions.RecordReaderFunction(rr);
    JavaRDD<List<Writable>> rdd = origData.map(rrf);
    JavaRDD<DataSet> data = rdd.map(new DataVecDataSetFunction(1, 2, false));
    List<DataSet> collected = data.collect();
    //Load normally (i.e., not via Spark), and check that we get the same results (order not withstanding)
    InputSplit is = new FileSplit(new File(folder), new String[] { "bmp" }, true);
    ImageRecordReader irr = new ImageRecordReader(28, 28, 1, new ParentPathLabelGenerator());
    irr.initialize(is);
    RecordReaderDataSetIterator iter = new RecordReaderDataSetIterator(irr, 1, 1, 2);
    List<DataSet> listLocal = new ArrayList<>(4);
    while (iter.hasNext()) {
        listLocal.add(iter.next());
    }
    //Compare:
    assertEquals(4, collected.size());
    assertEquals(4, listLocal.size());
    //Check that results are the same (order not withstanding)
    boolean[] found = new boolean[4];
    for (int i = 0; i < 4; i++) {
        int foundIndex = -1;
        DataSet ds = collected.get(i);
        for (int j = 0; j < 4; j++) {
            if (ds.equals(listLocal.get(j))) {
                if (foundIndex != -1)
                    //Already found this value -> suggests this spark value equals two or more of local version? (Shouldn't happen)
                    fail();
                foundIndex = j;
                if (found[foundIndex])
                    //One of the other spark values was equal to this one -> suggests duplicates in Spark list
                    fail();
                //mark this one as seen before
                found[foundIndex] = true;
            }
        }
    }
    int count = 0;
    for (boolean b : found) if (b)
        count++;
    //Expect all 4 and exactly 4 pairwise matches between spark and local versions
    assertEquals(4, count);
}