Seglink代码之二 数据增强 distorted_bounding_box_crop

def distorted_bounding_box_crop(image,
                                labels,
                                bboxes,
                                xs, ys, 
                                min_object_covered,
                                aspect_ratio_range,
                                area_range,
                                max_attempts = 200,
                                scope=None):
    """Generates cropped_image using a one of the bboxes randomly distorted.

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

    Args:
        image: 3-D Tensor of image (it will be converted to floats in [0, 1]).
        bbox: 2-D float Tensor of bounding boxes arranged [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 it would 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 `floats`. The cropped area of the
            image must have an aspect ratio = width / height within this range.
        area_range: An optional list of `floats`. 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 scope for name_scope.
    Returns:
        A tuple, a 3-D Tensor cropped_image and the distorted bbox
    """
    with tf.name_scope(scope, 'distorted_bounding_box_crop', [image, bboxes, xs, ys]):
        # Each bounding box has shape [1, num_boxes, box coords] and
        # the coordinates are ordered [ymin, xmin, ymax, xmax].
        # distort_bbox reference
        bbox_begin, bbox_size, distort_bbox = tf.image.sample_distorted_bounding_box(
                tf.shape(image),
                bounding_boxes=tf.expand_dims(bboxes, 0),
                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)
        distort_bbox = distort_bbox[0, 0]

        # Crop the image to the specified bounding box.
        cropped_image = tf.slice(image, bbox_begin, bbox_size)
        # Restore the shape since the dynamic slice loses 3rd dimension.
        cropped_image.set_shape([None, None, 3])

        # Update bounding boxes: resize and filter out.
        # distort_bbox　其实就是一个reference
        bboxes, xs, ys = tfe.bboxes_resize(distort_bbox, bboxes, xs, ys)
        labels, bboxes, xs, ys = tfe.bboxes_filter_overlap(labels, bboxes, xs, ys, 
                                                threshold=BBOX_CROP_OVERLAP, assign_negative = False)
        return cropped_image, labels, bboxes, xs, ys, distort_bbox



def bboxes_resize(bbox_ref, bboxes, xs, ys, name=None):
    """Resize bounding boxes based on a reference bounding box,
    assuming that the latter is [0, 0, 1, 1] after transform. Useful for
    updating a collection of boxes after cropping an image.
    """
    # Tensors inputs.
    # boxes [y, x, h, w]
    # bbox_ref　这是crop_image相对于原图的比例
    # bboxes 这是bbox相对于原图的比例
    # xs, ys是由bbox生成的，一样～

    with tf.name_scope(name, 'bboxes_resize'):
        h_ref = bbox_ref[2] - bbox_ref[0]
        w_ref = bbox_ref[3] - bbox_ref[1]


        # Translate.
        v = tf.stack([bbox_ref[0], bbox_ref[1], bbox_ref[0], bbox_ref[1]])
        bboxes = bboxes - v
        xs = xs - bbox_ref[1]
        ys = ys - bbox_ref[0]



        # Scale.
        s = tf.stack([h_ref, w_ref, h_ref, w_ref])
        #tf.global_variables_initializer()
        #s = tf.Session()

        #c = s.run(bboxes)
        bboxes = bboxes / s
        xs = xs / w_ref;
        ys = ys / h_ref;

        return bboxes, xs, ys