tf.image.generate_bounding_box_proposals

Generate bounding box proposals from encoded bounding boxes.

Args
scores A 4-D float Tensor of shape [num_images, height, width, num_achors] containing scores of the boxes for given anchors, can be unsorted.
bbox_deltas A 4-D float Tensor of shape [num_images, height, width, 4 x num_anchors] encoding boxes with respect to each anchor. Coordinates are given in the form [dy, dx, dh, dw].
image_info A 2-D float Tensor of shape [num_images, 5] containing image information Height, Width, Scale.
anchors A 2-D float Tensor of shape [num_anchors, 4] describing the anchor boxes. Boxes are formatted in the form [y1, x1, y2, x2].
nms_threshold A scalar float Tensor for non-maximal-suppression threshold. Defaults to 0.7.
pre_nms_topn A scalar int Tensor for the number of top scoring boxes to be used as input. Defaults to 6000.
min_size A scalar float Tensor. Any box that has a smaller size than min_size will be discarded. Defaults to 16.
post_nms_topn An integer. Maximum number of rois in the output.
name A name for this operation (optional).
Returns
rois Region of interest boxes sorted by their scores.
roi_probabilities scores of the ROI boxes in the ROIs' Tensor.

© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/versions/r2.4/api_docs/python/tf/image/generate_bounding_box_proposals