public <T extends Number> CropAndResizeGradBoxes cropAndResizeGradBoxes(Operand<Float> grads, Operand<T> image, Operand<Float> boxes, Operand<Integer> boxInd, CropAndResizeGradBoxes.Options... options)
CropAndResizeGradBoxes operationgrads - A 4-D tensor of shape `[num_boxes, crop_height, crop_width, depth]`.image - A 4-D tensor of shape `[batch, image_height, image_width, depth]`.boxes - A 2-D tensor of shape `[num_boxes, 4]`. The `i`-th row of the tensorboxInd - A 1-D tensor of shape `[num_boxes]` with int32 values in `[0, batch)`.options - carries optional attributes valuesCropAndResizeGradBoxespublic ExtractJpegShape<Integer> extractJpegShape(Operand<String> contents)
ExtractJpegShape operationcontents - 0-D. The JPEG-encoded image.ExtractJpegShapepublic DecodeBmp decodeBmp(Operand<String> contents, DecodeBmp.Options... options)
DecodeBmp operationcontents - 0-D. The BMP-encoded image.options - carries optional attributes valuesDecodeBmppublic <T extends Number> RandomCrop<T> randomCrop(Operand<T> image, Operand<Long> size, RandomCrop.Options... options)
RandomCrop operationimage - 3-D of shape `[height, width, channels]`.size - 1-D of length 2 containing: `crop_height`, `crop_width`..options - carries optional attributes valuesRandomCroppublic DecodeJpeg decodeJpeg(Operand<String> contents, DecodeJpeg.Options... options)
DecodeJpeg operationcontents - 0-D. The JPEG-encoded image.options - carries optional attributes valuesDecodeJpegpublic <T extends Number> ResizeNearestNeighbor<T> resizeNearestNeighbor(Operand<T> images, Operand<Integer> size, ResizeNearestNeighbor.Options... options)
ResizeNearestNeighbor operationimages - 4-D with shape `[batch, height, width, channels]`.size - = A 1-D int32 Tensor of 2 elements: `new_height, new_width`. Theoptions - carries optional attributes valuesResizeNearestNeighborpublic <T extends Number> HsvToRgb<T> hsvToRgb(Operand<T> images)
HsvToRgb operationimages - 1-D or higher rank. HSV data to convert. Last dimension must be size 3.HsvToRgbpublic ExtractGlimpse extractGlimpse(Operand<Float> input, Operand<Integer> size, Operand<Float> offsets, ExtractGlimpse.Options... options)
ExtractGlimpse operationinput - A 4-D float tensor of shape `[batch_size, height, width, channels]`.size - A 1-D tensor of 2 elements containing the size of the glimpsesoffsets - A 2-D integer tensor of shape `[batch_size, 2]` containingoptions - carries optional attributes valuesExtractGlimpsepublic <T extends Number> ResizeBilinear resizeBilinear(Operand<T> images, Operand<Integer> size, ResizeBilinear.Options... options)
ResizeBilinear operationimages - 4-D with shape `[batch, height, width, channels]`.size - = A 1-D int32 Tensor of 2 elements: `new_height, new_width`. Theoptions - carries optional attributes valuesResizeBilinearpublic EncodeJpegVariableQuality encodeJpegVariableQuality(Operand<UInt8> images, Operand<Integer> quality)
EncodeJpegVariableQuality operationimages - Images to adjust. At least 3-D.quality - An int quality to encode to.EncodeJpegVariableQualitypublic <T extends Number> ResizeBicubic resizeBicubic(Operand<T> images, Operand<Integer> size, ResizeBicubic.Options... options)
ResizeBicubic operationimages - 4-D with shape `[batch, height, width, channels]`.size - = A 1-D int32 Tensor of 2 elements: `new_height, new_width`. Theoptions - carries optional attributes valuesResizeBicubicpublic <T extends Number> ExtractImagePatches<T> extractImagePatches(Operand<T> images, List<Long> ksizes, List<Long> strides, List<Long> rates, String padding)
ExtractImagePatches operationimages - 4-D Tensor with shape `[batch, in_rows, in_cols, depth]`.ksizes - The size of the sliding window for each dimension of `images`.strides - How far the centers of two consecutive patches are inrates - Must be: `[1, rate_rows, rate_cols, 1]`. This is thepadding - The type of padding algorithm to use.ExtractImagePatchespublic DecodeGif decodeGif(Operand<String> contents)
DecodeGif operationcontents - 0-D. The GIF-encoded image.DecodeGifpublic <T extends Number> EncodePng encodePng(Operand<T> image, EncodePng.Options... options)
EncodePng operationimage - 3-D with shape `[height, width, channels]`.options - carries optional attributes valuesEncodePngpublic <T extends Number> AdjustContrast<T> adjustContrast(Operand<T> images, Operand<Float> contrastFactor)
AdjustContrast operationimages - Images to adjust. At least 3-D.contrastFactor - A float multiplier for adjusting contrast.AdjustContrastpublic <T extends Number> CropAndResizeGradImage<T> cropAndResizeGradImage(Operand<Float> grads, Operand<Float> boxes, Operand<Integer> boxInd, Operand<Integer> imageSize, Class<T> T, CropAndResizeGradImage.Options... options)
CropAndResizeGradImage operationgrads - A 4-D tensor of shape `[num_boxes, crop_height, crop_width, depth]`.boxes - A 2-D tensor of shape `[num_boxes, 4]`. The `i`-th row of the tensorboxInd - A 1-D tensor of shape `[num_boxes]` with int32 values in `[0, batch)`.imageSize - A 1-D tensor with value `[batch, image_height, image_width, depth]`T - options - carries optional attributes valuesCropAndResizeGradImagepublic DecodePng<UInt8> decodePng(Operand<String> contents, DecodePng.Options... options)
DecodePng operationcontents - 0-D. The PNG-encoded image.options - carries optional attributes valuesDecodePngpublic <T extends Number> ExtractJpegShape<T> extractJpegShape(Operand<String> contents, Class<T> outputType)
ExtractJpegShape operationcontents - 0-D. The JPEG-encoded image.outputType - (Optional) The output type of the operation (int32 or int64).ExtractJpegShapepublic <T extends Number> CropAndResize cropAndResize(Operand<T> image, Operand<Float> boxes, Operand<Integer> boxInd, Operand<Integer> cropSize, CropAndResize.Options... options)
CropAndResize operationimage - A 4-D tensor of shape `[batch, image_height, image_width, depth]`.boxes - A 2-D tensor of shape `[num_boxes, 4]`. The `i`-th row of the tensorboxInd - A 1-D tensor of shape `[num_boxes]` with int32 values in `[0, batch)`.cropSize - A 1-D tensor of 2 elements, `size = [crop_height, crop_width]`. Alloptions - carries optional attributes valuesCropAndResizepublic <T extends Number> AdjustSaturation<T> adjustSaturation(Operand<T> images, Operand<Float> scale)
AdjustSaturation operationimages - Images to adjust. At least 3-D.scale - A float scale to add to the saturation.AdjustSaturationpublic EncodeJpeg encodeJpeg(Operand<UInt8> image, EncodeJpeg.Options... options)
EncodeJpeg operationimage - 3-D with shape `[height, width, channels]`.options - carries optional attributes valuesEncodeJpegpublic <T> QuantizedResizeBilinear<T> quantizedResizeBilinear(Operand<T> images, Operand<Integer> size, Operand<Float> min, Operand<Float> max, QuantizedResizeBilinear.Options... options)
QuantizedResizeBilinear operationimages - 4-D with shape `[batch, height, width, channels]`.size - = A 1-D int32 Tensor of 2 elements: `new_height, new_width`. Themin - max - options - carries optional attributes valuesQuantizedResizeBilinearpublic NonMaxSuppressionWithOverlaps nonMaxSuppressionWithOverlaps(Operand<Float> overlaps, Operand<Float> scores, Operand<Integer> maxOutputSize, Operand<Float> overlapThreshold, Operand<Float> scoreThreshold)
NonMaxSuppressionWithOverlaps operationoverlaps - A 2-D float tensor of shape `[num_boxes, num_boxes]` representingscores - A 1-D float tensor of shape `[num_boxes]` representing a singlemaxOutputSize - A scalar integer tensor representing the maximum number ofoverlapThreshold - A 0-D float tensor representing the threshold for deciding whetherscoreThreshold - A 0-D float tensor representing the threshold for deciding when to removeNonMaxSuppressionWithOverlapspublic <T extends Number> SampleDistortedBoundingBox<T> sampleDistortedBoundingBox(Operand<T> imageSize, Operand<Float> boundingBoxes, Operand<Float> minObjectCovered, SampleDistortedBoundingBox.Options... options)
SampleDistortedBoundingBox operationimageSize - 1-D, containing `[height, width, channels]`.boundingBoxes - 3-D with shape `[batch, N, 4]` describing the N bounding boxesminObjectCovered - The cropped area of the image must contain at least thisoptions - carries optional attributes valuesSampleDistortedBoundingBoxpublic <T extends Number,U extends Number> NonMaxSuppression nonMaxSuppression(Operand<T> boxes, Operand<T> scores, Operand<Integer> maxOutputSize, Operand<U> iouThreshold, Operand<U> scoreThreshold, NonMaxSuppression.Options... options)
NonMaxSuppression operationboxes - A 2-D float tensor of shape `[num_boxes, 4]`.scores - A 1-D float tensor of shape `[num_boxes]` representing a singlemaxOutputSize - A scalar integer tensor representing the maximum number ofiouThreshold - A 0-D float tensor representing the threshold for deciding whetherscoreThreshold - A 0-D float tensor representing the threshold for deciding when to removeoptions - carries optional attributes valuesNonMaxSuppressionpublic <T extends Number> ResizeArea resizeArea(Operand<T> images, Operand<Integer> size, ResizeArea.Options... options)
ResizeArea operationimages - 4-D with shape `[batch, height, width, channels]`.size - = A 1-D int32 Tensor of 2 elements: `new_height, new_width`. Theoptions - carries optional attributes valuesResizeAreapublic <T extends Number> DecodePng<T> decodePng(Operand<String> contents, Class<T> dtype, DecodePng.Options... options)
DecodePng operationcontents - 0-D. The PNG-encoded image.dtype - options - carries optional attributes valuesDecodePngpublic <T extends Number> RgbToHsv<T> rgbToHsv(Operand<T> images)
RgbToHsv operationimages - 1-D or higher rank. RGB data to convert. Last dimension must be size 3.RgbToHsvpublic DecodeAndCropJpeg decodeAndCropJpeg(Operand<String> contents, Operand<Integer> cropWindow, DecodeAndCropJpeg.Options... options)
DecodeAndCropJpeg operationcontents - 0-D. The JPEG-encoded image.cropWindow - 1-D. The crop window: [crop_y, crop_x, crop_height, crop_width].options - carries optional attributes valuesDecodeAndCropJpegpublic <T extends Number> AdjustHue<T> adjustHue(Operand<T> images, Operand<Float> delta)
AdjustHue operationimages - Images to adjust. At least 3-D.delta - A float delta to add to the hue.AdjustHuepublic <T extends Number> DrawBoundingBoxes<T> drawBoundingBoxes(Operand<T> images, Operand<Float> boxes)
DrawBoundingBoxes operationimages - 4-D with shape `[batch, height, width, depth]`. A batch of images.boxes - 3-D with shape `[batch, num_bounding_boxes, 4]` containing boundingDrawBoundingBoxesCopyright © 2015–2019. All rights reserved.