Package org.tensorflow.op.image

Class ResizeBilinear

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.image.ResizeBilinear

All Implemented Interfaces:

Op, Operand<java.lang.Float>

@Operator(group="image")
public final class ResizeBilinear
extends PrimitiveOp
implements Operand<java.lang.Float>

Resize `images` to `size` using bilinear interpolation.

Input images can be of different types but output images are always float.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	ResizeBilinear.Options	Optional attributes for ResizeBilinear

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method	Description
static ResizeBilinear.Options	alignCorners(java.lang.Boolean alignCorners)
Output<java.lang.Float>	asOutput()	Returns the symbolic handle of a tensor.
static <T extends java.lang.Number> ResizeBilinear	create(Scope scope, Operand<T> images, Operand<java.lang.Integer> size, ResizeBilinear.Options... options)	Factory method to create a class to wrap a new ResizeBilinear operation to the graph.
Output<java.lang.Float>	resizedImages()	4-D with shape `[batch, new_height, new_width, channels]`.

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Methods inherited from class org.tensorflow.op.PrimitiveOp

equals, hashCode, toString

Method Detail

create

public static <T extends java.lang.Number> ResizeBilinear create(Scope scope,
                                                                 Operand<T> images,
                                                                 Operand<java.lang.Integer> size,
                                                                 ResizeBilinear.Options... options)

Factory method to create a class to wrap a new ResizeBilinear operation to the graph.

Parameters:

scope - current graph scope

images - 4-D with shape `[batch, height, width, channels]`.

size - = A 1-D int32 Tensor of 2 elements: `new_height, new_width`. The new size for the images.

options - carries optional attributes values

Returns:

a new instance of ResizeBilinear

alignCorners

public static ResizeBilinear.Options alignCorners(java.lang.Boolean alignCorners)

Parameters:

alignCorners - If true, the centers of the 4 corner pixels of the input and output tensors are aligned, preserving the values at the corner pixels. Defaults to false.

resizedImages

public Output<java.lang.Float> resizedImages()

4-D with shape `[batch, new_height, new_width, channels]`.

asOutput

public Output<java.lang.Float> asOutput()

Description copied from interface: Operand

Returns the symbolic handle of a 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.

Specified by:

asOutput in interface Operand<java.lang.Float>

See Also:

OperationBuilder.addInput(Output)