Type Members

1.  class BGRImage extends Image

   Represent a BGR image.

2.  class BGRImgCropper extends Transformer[LabeledBGRImage, LabeledBGRImage]

   Crop a cropWidth x cropHeight patch from an image.

   Crop a cropWidth x cropHeight patch from an image. The patch size should be less than the image size. There're two cropping methods: at random and from the center. The former is preferred for simple data augmentation during training while the later applies to validation or testing

3.  class BGRImgNormalizer extends Transformer[LabeledBGRImage, LabeledBGRImage]

   Normalize a BGR image.

   Normalize a BGR image. The normalize is per channel. Each pixel will minus mean value of the channel. Then divide std value of the channel.

4.  class BGRImgPixelNormalizer extends Transformer[LabeledBGRImage, LabeledBGRImage]

   Each pixel value of the input BGR Image sub the given mean value of the corresponding chanel

5.  class BGRImgRdmCropper extends Transformer[LabeledBGRImage, LabeledBGRImage]

   Random crop a specified area from the Image.

   Random crop a specified area from the Image. The result is also an image

6.  class BGRImgToBatch extends Transformer[LabeledBGRImage, MiniBatch[Float]]

   Convert a batch of labeled BGR images into a Mini-batch.

   Convert a batch of labeled BGR images into a Mini-batch.

   Notice: The totalBatch means a total batch size. In distributed environment, the batch should be divided by total core number

7.  class BGRImgToImageVector extends Transformer[LabeledBGRImage, DenseVector]

   Convert a BGR image to dense vector of spark mllib

8.  class BGRImgToLocalSeqFile extends Transformer[(LabeledBGRImage, String), String]

   Write a BGR image sequence into one or many hadoop sequence files.

9.  class BGRImgToSample extends Transformer[LabeledBGRImage, Sample[Float]]

   transform labeled bgr image to sample

10.  class BytesToBGRImg extends Transformer[ByteRecord, LabeledBGRImage]

    Convert a byte record to BGR image.

    Convert a byte record to BGR image. The format is, first 4 bytes is width, the next 4 bytes is height, and the last is pixels coming with BGR order.

11.  class BytesToGreyImg extends Transformer[ByteRecord, LabeledGreyImage]

    Convert byte records into grey image.

12.  class ColorJitter extends Transformer[LabeledBGRImage, LabeledBGRImage]

    Process an image with brightness, contrast, saturation in a random order

13.  sealed trait CropperMethod extends AnyRef

    Image crop method, e.g.

    Image crop method, e.g. random, center

14.  class GreyImage extends Image

    Represent a grey image

15.  class GreyImgCropper extends Transformer[LabeledGreyImage, LabeledGreyImage]

    Crop an area from a grey image.

    Crop an area from a grey image. The crop area width and height must be smaller than grey image width and height. The area position is random.

16.  class GreyImgNormalizer extends Transformer[LabeledGreyImage, LabeledGreyImage]

    Normalize a grey image.

    Normalize a grey image. Each pixel will minus mean and then divide std.

17.  class GreyImgToBatch extends Transformer[LabeledGreyImage, MiniBatch[Float]]

    Convert a batch of labeled grey images into a Mini-batch.

    Convert a batch of labeled grey images into a Mini-batch.

    Notice: The totalBatch means a total batch size. In distributed environment, the batch should be divided by total core number

18.  class GreyImgToSample extends Transformer[LabeledGreyImage, Sample[Float]]

    transform labeled grey image to sample

19.  class HFlip extends Transformer[LabeledBGRImage, LabeledBGRImage]

    Flip a image with a probability.

    Flip a image with a probability. The threshold higher, the less easier to flip the image.

20.  class LabeledBGRImage extends BGRImage with Label[Float]

    A BGR Image with label.

21.  class LabeledGreyImage extends GreyImage with Label[Float]

    A grey image with a float label

22.  class Lighting extends Transformer[LabeledBGRImage, LabeledBGRImage]

    Lighting noise for data augmentation

    Lighting noise for data augmentation

    Krizhevsky et al. proposed fancy PCA when training the famous Alex-Net in 2012 Fancy PCA alters the intensities of the RGB channels in training images For each training image, add the corresponding quantity to each RGB image pixel

23.  case class LocalLabeledImagePath(label: Float, p: Path) extends LocalImagePath with Label[Float] with Product with Serializable

    Represent a local file path of a image file with a float label

24.  class LocalResizeImgReader extends Transformer[LocalLabeledImagePath, LabeledBGRImage]

    Read BGR images from local given paths.

    Read BGR images from local given paths. After read the image, it will resize the images to the given width and height. Besides, it will also divide the pixel value by the given normalize value.

25.  class LocalResizeImgWithName extends Transformer[LocalLabeledImagePath, (LabeledBGRImage, String)]

    Read BGR images from local given paths.

    Read BGR images from local given paths. After read the image, it will resize the images to the given width and height. It will also divide the pixel value by the given normalize value. Besides, it will return the file name.

26.  class LocalScaleImgReader extends Transformer[LocalLabeledImagePath, LabeledBGRImage]

    Read BGR images from local given paths.

    Read BGR images from local given paths. After read the image, it will resize the shorted edge to the given scale to value and resize the other edge properly. It will also divide the pixel value by the given normalize value.

27.  class LocalScaleImgWithName extends Transformer[LocalLabeledImagePath, (LabeledBGRImage, String)]

    Read BGR images from given paths.

    Read BGR images from given paths. After read the image, it will resize the shorted edge to the given scale to value and resize the other edge properly. It will also divide the pixel value by the given normalize value. Besides, it will return the file name.

28.  class LocalSeqFileToBytes extends Transformer[LocalSeqFilePath, ByteRecord]

    Read byte records from local hadoop sequence files.

29.  class MTLabeledBGRImgToBatch[A] extends Transformer[A, MiniBatch[Float]]

    Multi-thread convert BGR images into Mini-Batch.

    Multi-thread convert BGR images into Mini-Batch.

    Note: the source iterator must be thread safe.