tensorflow::ops::ExtractGlimpse

#include <image_ops.h>

Extracts a glimpse from the input tensor.

Summary

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.

Args:

  • scope: A Scope object
  • 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.

Optional attributes (see Attrs):

  • 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: indicates if the offset coordinates are normalized.
  • uniform_noise: indicates if the noise should be generated using a uniform distribution or a Gaussian distribution.
  • 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.

Returns:

  • Output: A tensor representing the glimpses [batch_size, glimpse_height, glimpse_width, channels].

Constructors and Destructors

ExtractGlimpse(const ::tensorflow::Scope & scope, ::tensorflow::Input input, ::tensorflow::Input size, ::tensorflow::Input offsets)
ExtractGlimpse(const ::tensorflow::Scope & scope, ::tensorflow::Input input, ::tensorflow::Input size, ::tensorflow::Input offsets, const ExtractGlimpse::Attrs & attrs)

Public attributes

glimpse
operation

Public functions

node() const
::tensorflow::Node *
operator::tensorflow::Input() const
operator::tensorflow::Output() const

Public static functions

Centered(bool x)
Noise(StringPiece x)
Normalized(bool x)
UniformNoise(bool x)

Structs

tensorflow::ops::ExtractGlimpse::Attrs

Optional attribute setters for ExtractGlimpse.

Public attributes

glimpse

::tensorflow::Output glimpse

operation

Operation operation

Public functions

ExtractGlimpse

 ExtractGlimpse(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input,
  ::tensorflow::Input size,
  ::tensorflow::Input offsets
)

ExtractGlimpse

 ExtractGlimpse(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input input,
  ::tensorflow::Input size,
  ::tensorflow::Input offsets,
  const ExtractGlimpse::Attrs & attrs
)

node

::tensorflow::Node * node() const 

operator::tensorflow::Input

 operator::tensorflow::Input() const 

operator::tensorflow::Output

 operator::tensorflow::Output() const 

Public static functions

Centered

Attrs Centered(
  bool x
)

Noise

Attrs Noise(
  StringPiece x
)

Normalized

Attrs Normalized(
  bool x
)

UniformNoise

Attrs UniformNoise(
  bool x
)