SampleDistortedBoundingBox

tensorflow C++ API

tensorflow::ops::SampleDistortedBoundingBox

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 animage_size, bounding_boxesand 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,sizeandbboxes. The first 2 tensors can be fed directly intotf.sliceto crop the image. The latter may be supplied totf.image.draw_bounding_boxesto 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,

```python 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.image_summary(‘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, settinguse_image_if_no_bounding_boxes = truewill assume there is a single implicit bounding box covering the whole image. Ifuse_image_if_no_bounding_boxesis 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 (seeAttrs):

seed: If eitherseedorseed2are set to non-zero, the random number generator is seeded by the givenseed. 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 in this range.
max_attempts: Number of attempts at generating a cropped region of the image of the specified constraints. After max_attemptsfailures, 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:

Outputbegin: 1-D, containing[offset_height, offset_width, 0]. Provide as input totf.slice.
Outputsize: 1-D, containing[target_height, target_width, -1]. Provide as input totf.slice.
Outputbboxes: 3-D with shape[1, 1, 4]containing the distorted bounding box. Provide as input totf.image.draw_bounding_boxes.

Constructor

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

Public attributes

tensorflow::Output begin.
tensorflow::Output size.
tensorflow::Output bboxes.