Package org.tensorflow.op.image

Class ExtractGlimpse

java.lang.Object

org.tensorflow.op.PrimitiveOp

org.tensorflow.op.image.ExtractGlimpse

All Implemented Interfaces:

Op, Operand<java.lang.Float>

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

Extracts a glimpse from the input tensor.

Returns a set of windows called glimpses extracted at location `offsets` from the input tensor. If the windows only partially overlaps the inputs, the non overlapping areas will be filled with random noise.

The result is a 4-D tensor of shape `[batch_size, glimpse_height, glimpse_width, channels]`. The channels and batch dimensions are the same as that of the input tensor. The height and width of the output windows are specified in the `size` parameter.

The argument `normalized` and `centered` controls how the windows are built:

• If the coordinates are normalized but not centered, 0.0 and 1.0 correspond to the minimum and maximum of each height and width dimension.
• If the coordinates are both normalized and centered, they range from -1.0 to 1.0. The coordinates (-1.0, -1.0) correspond to the upper left corner, the lower right corner is located at (1.0, 1.0) and the center is at (0, 0).
• If the coordinates are not normalized they are interpreted as numbers of pixels.

Nested Class Summary

Nested Classes

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

Field Summary

Fields inherited from class org.tensorflow.op.PrimitiveOp

operation

Method Summary

Modifier and Type	Method	Description
Output<java.lang.Float>	asOutput()	Returns the symbolic handle of a tensor.
static ExtractGlimpse.Options	centered(java.lang.Boolean centered)
static ExtractGlimpse	create(Scope scope, Operand<java.lang.Float> input, Operand<java.lang.Integer> size, Operand<java.lang.Float> offsets, ExtractGlimpse.Options... options)	Factory method to create a class to wrap a new ExtractGlimpse operation to the graph.
Output<java.lang.Float>	glimpse()	A tensor representing the glimpses `[batch_size, glimpse_height, glimpse_width, channels]`.
static ExtractGlimpse.Options	normalized(java.lang.Boolean normalized)
static ExtractGlimpse.Options	uniformNoise(java.lang.Boolean uniformNoise)

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 ExtractGlimpse create(Scope scope,
                                    Operand<java.lang.Float> input,
                                    Operand<java.lang.Integer> size,
                                    Operand<java.lang.Float> offsets,
                                    ExtractGlimpse.Options... options)

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

Parameters:

scope - current graph scope

input - 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 glimpses to extract. The glimpse height must be specified first, following by the glimpse width.

offsets - A 2-D integer tensor of shape `[batch_size, 2]` containing the y, x locations of the center of each window.

options - carries optional attributes values

Returns:

a new instance of ExtractGlimpse

centered

public static ExtractGlimpse.Options centered(java.lang.Boolean centered)

Parameters:

centered - indicates if the offset coordinates are centered relative to the image, in which case the (0, 0) offset is relative to the center of the input images. If false, the (0,0) offset corresponds to the upper left corner of the input images.

normalized

public static ExtractGlimpse.Options normalized(java.lang.Boolean normalized)

Parameters:

normalized - indicates if the offset coordinates are normalized.

uniformNoise

public static ExtractGlimpse.Options uniformNoise(java.lang.Boolean uniformNoise)

Parameters:

uniformNoise - indicates if the noise should be generated using a uniform distribution or a Gaussian distribution.

glimpse

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

A tensor representing the glimpses `[batch_size, glimpse_height, glimpse_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)