Package ai.djl.basicdataset.cv.classification

Class Cifar10

  • All Implemented Interfaces:
    ai.djl.training.dataset.Dataset
    public final class Cifar10
extends ai.djl.training.dataset.ArrayDataset
    CIFAR10 image classification dataset from https://www.cs.toronto.edu/~kriz/cifar.html.

    It consists of 60,000 32x32 color images with 10 classes. It can train in a few hours with a GPU.

    Each sample is an image (in 3-D NDArray) with shape (32, 32, 3).

    • Nested Class Summary

      Nested Classes 
      Modifier and Type Class Description
      static class  Cifar10.Builder
      A builder to construct a Cifar10.

      • Nested classes/interfaces inherited from class ai.djl.training.dataset.RandomAccessDataset

        ai.djl.training.dataset.RandomAccessDataset.BaseBuilder<T extends ai.djl.training.dataset.RandomAccessDataset.BaseBuilder<T>>

      • Nested classes/interfaces inherited from interface ai.djl.training.dataset.Dataset

        ai.djl.training.dataset.Dataset.Usage

    • Field Summary

      Fields 
      Modifier and Type Field Description
      static int IMAGE_HEIGHT  
      static int IMAGE_WIDTH  
      static float[] NORMALIZE_MEAN  
      static float[] NORMALIZE_STD  

      • Fields inherited from class ai.djl.training.dataset.ArrayDataset

        data, labels

      • Fields inherited from class ai.djl.training.dataset.RandomAccessDataset

        dataBatchifier, device, labelBatchifier, limit, pipeline, prefetchNumber, sampler, targetPipeline

    • Method Summary

      All Methods Static Methods Instance Methods Concrete Methods 
      Modifier and Type Method Description
      static Cifar10.Builder builder()
      Creates a builder to build a Cifar10.
      void prepare​(ai.djl.util.Progress progress)

      • Methods inherited from class ai.djl.training.dataset.ArrayDataset

        availableSize, get, getByIndices, getByRange, getData, newSubDataset, newSubDataset

      • Methods inherited from class ai.djl.training.dataset.RandomAccessDataset

        getData, getData, getData, randomSplit, size, subDataset, subDataset, subDataset, subDataset, toArray

      • Methods inherited from class java.lang.Object

        clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

      • Methods inherited from interface ai.djl.training.dataset.Dataset

        matchingTranslatorOptions, prepare

    • Field Detail

      • NORMALIZE_MEAN

        public static final float[] NORMALIZE_MEAN

      • NORMALIZE_STD

        public static final float[] NORMALIZE_STD

    • Method Detail

      • builder

        public static Cifar10.Builder builder()
        Creates a builder to build a Cifar10.
        Returns:
        a new builder

      • prepare

        public void prepare​(ai.djl.util.Progress progress)
             throws java.io.IOException
        Specified by:
        prepare in interface ai.djl.training.dataset.Dataset
        Overrides:
        prepare in class ai.djl.training.dataset.ArrayDataset
        Throws:
        java.io.IOException