ExtractGlimpseV2

public final class ExtractGlimpseV2

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 Classes

class ExtractGlimpseV2.Options Optional attributes for ExtractGlimpseV2

Public Methods

Output <Float>
asOutput ()
Returns the symbolic handle of a tensor.
static ExtractGlimpseV2.Options
centered (Boolean centered)
static ExtractGlimpseV2
create ( Scope scope, Operand <Float> input, Operand <Integer> size, Operand <Float> offsets, Options... options)
Factory method to create a class wrapping a new ExtractGlimpseV2 operation.
Output <Float>
glimpse ()
A tensor representing the glimpses `[batch_size, glimpse_height, glimpse_width, channels]`.
static ExtractGlimpseV2.Options
noise (String noise)
static ExtractGlimpseV2.Options
normalized (Boolean normalized)
static ExtractGlimpseV2.Options
uniformNoise (Boolean uniformNoise)

Inherited Methods

Public Methods

public Output <Float> asOutput ()

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.

public static ExtractGlimpseV2.Options centered (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.

public static ExtractGlimpseV2 create ( Scope scope, Operand <Float> input, Operand <Integer> size, Operand <Float> offsets, Options... options)

Factory method to create a class wrapping a new ExtractGlimpseV2 operation.

Parameters
scope current 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 ExtractGlimpseV2

public Output <Float> glimpse ()

A tensor representing the glimpses `[batch_size, glimpse_height, glimpse_width, channels]`.

public static ExtractGlimpseV2.Options noise (String noise)

Parameters
noise indicates if the noise should `uniform`, `gaussian`, or `zero`. The default is `uniform` which means the noise type will be decided by `uniform_noise`.

public static ExtractGlimpseV2.Options normalized (Boolean normalized)

Parameters
normalized indicates if the offset coordinates are normalized.

public static ExtractGlimpseV2.Options uniformNoise (Boolean uniformNoise)

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