org.nd4j.autodiff.samediff.ops

Class SDImage

java.lang.Object

org.nd4j.autodiff.samediff.ops.SDOps

org.nd4j.autodiff.samediff.ops.SDImage

public class SDImage
extends SDOps

Author:

Alex Black

Field Summary

Fields inherited from class org.nd4j.autodiff.samediff.ops.SDOps

sd

Constructor Summary

Constructors

Constructor and Description
SDImage(SameDiff sameDiff)

Method Summary

Modifier and Type	Method and Description
SDVariable	cropAndResize(String name, SDVariable image, SDVariable cropBoxes, SDVariable boxIndices, SDVariable cropOutSize, CropAndResize.Method method, double extrapolationValue) Given an input image and some crop boxes, extract out the image subsets and resize them to the specified size.
SDVariable	extractImagePatches(String name, SDVariable image, int[] kSizes, int[] strides, int[] rates, boolean sameMode) Given an input image, extract out image patches (of size kSizes - h x w) and place them in the depth dimension.
SDVariable	nonMaxSuppression(String name, SDVariable boxes, SDVariable scores, SDVariable maxOutSize, SDVariable iouThreshold, SDVariable scoreThreshold)

Methods inherited from class org.nd4j.autodiff.samediff.ops.SDOps

f, updateVariableNameAndReference

Methods inherited from class java.lang.Object

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

Constructor Detail

SDImage

public SDImage(SameDiff sameDiff)

Method Detail

cropAndResize

public SDVariable cropAndResize(String name,
                                SDVariable image,
                                SDVariable cropBoxes,
                                SDVariable boxIndices,
                                SDVariable cropOutSize,
                                CropAndResize.Method method,
                                double extrapolationValue)

Given an input image and some crop boxes, extract out the image subsets and resize them to the specified size.

Parameters:

name - May be null. Name for the output variable.

image - Input image, with shape [batch, height, width, channels]

cropBoxes - Float32 crop, shape [numBoxes, 4] with values in range 0 to 1

boxIndices - Indices: which image (index to dimension 0) the cropBoxes belong to. Rank 1, shape [numBoxes]

cropOutSize - Output size for the images - int32, rank 1 with values [outHeight, outWidth]

method - Image resize method

extrapolationValue - Used for extrapolation, when applicable. 0.0 should be used for the default

Returns:

Cropped and resized images

extractImagePatches

public SDVariable extractImagePatches(String name,
                                      SDVariable image,
                                      @NonNull
                                      int[] kSizes,
                                      @NonNull
                                      int[] strides,
                                      @NonNull
                                      int[] rates,
                                      boolean sameMode)

Given an input image, extract out image patches (of size kSizes - h x w) and place them in the depth dimension.

Parameters:

name - Map be null. Name for the output variable

image - Input image to extract image patches from - shape [batch, height, width, channels]

kSizes - Kernel size - size of the image patches, [height, width]

strides - Stride in the input dimension for extracting image patches, [stride_height, stride_width]

rates - Usually [1,1]. Equivalent to dilation rate in dilated convolutions - how far apart the output pixels in the patches should be, in the input. A dilation of [a,b] means every ath pixel is taken along the height/rows dimension, and every bth pixel is take along the width/columns dimension

sameMode - Padding algorithm. If true: use Same padding

Returns:

The extracted image patches

nonMaxSuppression

public SDVariable nonMaxSuppression(String name,
                                    @NonNull
                                    SDVariable boxes,
                                    @NonNull
                                    SDVariable scores,
                                    @NonNull
                                    SDVariable maxOutSize,
                                    @NonNull
                                    SDVariable iouThreshold,
                                    @NonNull
                                    SDVariable scoreThreshold)