tensorflow::ops::SampleDistortedBoundingBox

#include <image_ops.h>

Generate a single randomly distorted bounding box for an image.

Summary

Bounding box annotations are often supplied in addition to ground-truth labels in image recognition or object localization tasks. A common technique for training such a system is to randomly distort an image while preserving its content, i.e. data augmentation. This Op outputs a randomly distorted localization of an object, i.e. bounding box, given an image_size, bounding_boxes and a series of constraints.

The output of this Op is a single bounding box that may be used to crop the original image. The output is returned as 3 tensors: begin, size and bboxes. The first 2 tensors can be fed directly into tf.slice to crop the image. The latter may be supplied to tf.image.draw_bounding_boxes to visualize what the bounding box looks like.

Bounding boxes are supplied and returned as [y_min, x_min, y_max, x_max]. The bounding box coordinates are floats in [0.0, 1.0] relative to the width and height of the underlying image.

For example,

# Generate a single distorted bounding box.
begin, size, bbox_for_draw = tf.image.sample_distorted_bounding_box(
    tf.shape(image),
    bounding_boxes=bounding_boxes)

# Draw the bounding box in an image summary.
image_with_box = tf.image.draw_bounding_boxes(tf.expand_dims(image, 0),
                                              bbox_for_draw)
tf.summary.image('images_with_box', image_with_box)

# Employ the bounding box to distort the image.
distorted_image = tf.slice(image, begin, size)

Note that if no bounding box information is available, setting use_image_if_no_bounding_boxes = true will assume there is a single implicit bounding box covering the whole image. If use_image_if_no_bounding_boxes is false and no bounding boxes are supplied, an error is raised.

Arguments:

• scope: A Scope object
• image_size: 1-D, containing [height, width, channels].
• bounding_boxes: 3-D with shape [batch, N, 4] describing the N bounding boxes associated with the image.

Optional attributes (see Attrs):

• seed: If either seed or seed2 are set to non-zero, the random number generator is seeded by the given seed. Otherwise, it is seeded by a random seed.
• seed2: A second seed to avoid seed collision.
• min_object_covered: The cropped area of the image must contain at least this fraction of any bounding box supplied. The value of this parameter should be non-negative. In the case of 0, the cropped area does not need to overlap any of the bounding boxes supplied.
• aspect_ratio_range: The cropped area of the image must have an aspect ratio = width / height within this range.
• area_range: The cropped area of the image must contain a fraction of the supplied image within this range.
• max_attempts: Number of attempts at generating a cropped region of the image of the specified constraints. After max_attempts failures, return the entire image.
• use_image_if_no_bounding_boxes: Controls behavior if no bounding boxes supplied. If true, assume an implicit bounding box covering the whole input. If false, raise an error.

Returns:

• Output begin: 1-D, containing [offset_height, offset_width, 0]. Provide as input to tf.slice.
• Output size: 1-D, containing [target_height, target_width, -1]. Provide as input to tf.slice.
• Output bboxes: 3-D with shape [1, 1, 4] containing the distorted bounding box. Provide as input to tf.image.draw_bounding_boxes.

Public attributes

::tensorflow::Output bboxes

::tensorflow::Output begin

Operation operation

::tensorflow::Output size

Public functions

 SampleDistortedBoundingBox(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input image_size,
  ::tensorflow::Input bounding_boxes
)

 SampleDistortedBoundingBox(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input image_size,
  ::tensorflow::Input bounding_boxes,
  const SampleDistortedBoundingBox::Attrs & attrs
)

Public static functions

Attrs AreaRange(
  const gtl::ArraySlice< float > & x
)

Attrs AspectRatioRange(
  const gtl::ArraySlice< float > & x
)

Attrs MaxAttempts(
  int64 x
)

Attrs MinObjectCovered(
  float x
)

Attrs Seed(
  int64 x
)

Attrs Seed2(
  int64 x
)

Attrs UseImageIfNoBoundingBoxes(
  bool x
)