Function distorted_bounding_box_crop

timm/data/tf_preprocessing.py:32–81

Generates cropped_image using one of the bboxes randomly distorted. See `tf.image.sample_distorted_bounding_box` for more documentation. Args: image_bytes: `Tensor` of binary image data. bbox: `Tensor` of bounding boxes arranged `[1, num_boxes, coords]` where each coo

(image_bytes,
                                bbox,
                                min_object_covered=0.1,
                                aspect_ratio_range=(0.75, 1.33),
                                area_range=(0.05, 1.0),
                                max_attempts=100,
                                scope=None)

def distorted_bounding_box_crop(image_bytes,
                                bbox,
                                min_object_covered=0.1,
                                aspect_ratio_range=(0.75, 1.33),
                                area_range=(0.05, 1.0),
                                max_attempts=100,
                                scope=None):
    """Generates cropped_image using one of the bboxes randomly distorted.

    See `tf.image.sample_distorted_bounding_box` for more documentation.

    Args:
      image_bytes: `Tensor` of binary image data.
      bbox: `Tensor` of bounding boxes arranged `[1, num_boxes, coords]`
          where each coordinate is [0, 1) and the coordinates are arranged
          as `[ymin, xmin, ymax, xmax]`. If num_boxes is 0 then use the whole
          image.
      min_object_covered: An optional `float`. Defaults to `0.1`. The cropped
          area of the image must contain at least this fraction of any bounding
          box supplied.
      aspect_ratio_range: An optional list of `float`s. The cropped area of the
          image must have an aspect ratio = width / height within this range.
      area_range: An optional list of `float`s. The cropped area of the image
          must contain a fraction of the supplied image within in this range.
      max_attempts: An optional `int`. Number of attempts at generating a cropped
          region of the image of the specified constraints. After `max_attempts`
          failures, return the entire image.
      scope: Optional `str` for name scope.
    Returns:
      cropped image `Tensor`
    """
    with tf.name_scope(scope, 'distorted_bounding_box_crop', [image_bytes, bbox]):
        shape = tf.image.extract_jpeg_shape(image_bytes)
        sample_distorted_bounding_box = tf.image.sample_distorted_bounding_box(
            shape,
            bounding_boxes=bbox,
            min_object_covered=min_object_covered,
            aspect_ratio_range=aspect_ratio_range,
            area_range=area_range,
            max_attempts=max_attempts,
            use_image_if_no_bounding_boxes=True)
        bbox_begin, bbox_size, _ = sample_distorted_bounding_box

        # Crop the image to the specified bounding box.
        offset_y, offset_x, _ = tf.unstack(bbox_begin)
        target_height, target_width, _ = tf.unstack(bbox_size)
        crop_window = tf.stack([offset_y, offset_x, target_height, target_width])
        image = tf.image.decode_and_crop_jpeg(image_bytes, crop_window, channels=3)

        return image


def _at_least_x_are_equal(a, b, x):