ResizeBilinearGrad

public final class ResizeBilinearGrad

Computes the gradient of bilinear interpolation.

Nested Classes

class ResizeBilinearGrad.Options Optional attributes for ResizeBilinearGrad  

Constants

String OP_NAME The name of this op, as known by TensorFlow core engine

Public Methods

static ResizeBilinearGrad.Options
alignCorners(Boolean alignCorners)
Output<T>
asOutput()
Returns the symbolic handle of the tensor.
static <T extends TNumber> ResizeBilinearGrad<T>
create(Scope scope, Operand<TFloat32> grads, Operand<T> originalImage, Options... options)
Factory method to create a class wrapping a new ResizeBilinearGrad operation.
static ResizeBilinearGrad.Options
halfPixelCenters(Boolean halfPixelCenters)
Output<T>
output()
4-D with shape `[batch, orig_height, orig_width, channels]`.

Inherited Methods

Constants

public static final String OP_NAME

The name of this op, as known by TensorFlow core engine

Constant Value: "ResizeBilinearGrad"

Public Methods

public static ResizeBilinearGrad.Options alignCorners (Boolean alignCorners)

Parameters
alignCorners If true, the centers of the 4 corner pixels of the input and grad tensors are aligned. Defaults to false.

public Output<T> asOutput ()

Returns the symbolic handle of the tensor.

Inputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.

public static ResizeBilinearGrad<T> create (Scope scope, Operand<TFloat32> grads, Operand<T> originalImage, Options... options)

Factory method to create a class wrapping a new ResizeBilinearGrad operation.

Parameters
scope current scope
grads 4-D with shape `[batch, height, width, channels]`.
originalImage 4-D with shape `[batch, orig_height, orig_width, channels]`, The image tensor that was resized.
options carries optional attributes values
Returns
  • a new instance of ResizeBilinearGrad

public static ResizeBilinearGrad.Options halfPixelCenters (Boolean halfPixelCenters)

public Output<T> output ()

4-D with shape `[batch, orig_height, orig_width, channels]`. Gradients with respect to the input image. Input image must have been float or double.