def _transform_boxes_to_feature_coordinates(self, provided_boxes, true_image_shapes, resized_image_shape, instance_embedding): """Transforms normalzied boxes to feature map coordinates. Args: provided_boxes: A [batch, num_instances, 4] float tensor containing normalized bounding boxes. true_image_shapes: int32 tensor of shape [batch, 3] where each row is of the form [height, width, channels] indicating the shapes of true images in the resized images, as resized images can be padded with zeros. resized_image_shape: A 4D int32 tensor containing shapes of the preprocessed inputs (N, H, W, C). instance_embedding: A [batch, output_height, output_width, embedding_size] float tensor containing instance embeddings. Returns: A float tensor of size [batch, num_instances, 4] containing boxes whose coordinates have been transformed to the absolute output space of the feature extractor. """ # Input boxes must be normalized. shape_utils.assert_box_normalized(provided_boxes) # Transform the provided boxes to the absolute output space of the feature # extractor. height, width = (tf.shape(instance_embedding)[1], tf.shape(instance_embedding)[2]) resized_image_height = resized_image_shape[1] resized_image_width = resized_image_shape[2] def transform_boxes(elems): boxes_per_image, true_image_shape = elems blist = box_list.BoxList(boxes_per_image) # First transform boxes from image space to resized image space since # there may have paddings in the resized images. blist = box_list_ops.scale( blist, true_image_shape[0] / resized_image_height, true_image_shape[1] / resized_image_width) # Then transform boxes from resized image space (normalized) to the # feature map space (absolute). blist = box_list_ops.to_absolute_coordinates(blist, height, width, check_range=False) return blist.get() return tf.map_fn(transform_boxes, [provided_boxes, true_image_shapes], dtype=tf.float32)
def merge_boxes_with_multiple_labels(boxes, classes, confidences, num_classes, quantization_bins=10000): """Merges boxes with same coordinates and returns K-hot encoded classes. Args: boxes: A tf.float32 tensor with shape [N, 4] holding N boxes. Only normalized coordinates are allowed. classes: A tf.int32 tensor with shape [N] holding class indices. The class index starts at 0. confidences: A tf.float32 tensor with shape [N] holding class confidences. num_classes: total number of classes to use for K-hot encoding. quantization_bins: the number of bins used to quantize the box coordinate. Returns: merged_boxes: A tf.float32 tensor with shape [N', 4] holding boxes, where N' <= N. class_encodings: A tf.int32 tensor with shape [N', num_classes] holding K-hot encodings for the merged boxes. confidence_encodings: A tf.float32 tensor with shape [N', num_classes] holding encodings of confidences for the merged boxes. merged_box_indices: A tf.int32 tensor with shape [N'] holding original indices of the boxes. """ boxes_shape = tf.shape(boxes) classes_shape = tf.shape(classes) confidences_shape = tf.shape(confidences) box_class_shape_assert = shape_utils.assert_shape_equal_along_first_dimension( boxes_shape, classes_shape) box_confidence_shape_assert = ( shape_utils.assert_shape_equal_along_first_dimension( boxes_shape, confidences_shape)) box_dimension_assert = tf.assert_equal(boxes_shape[1], 4) box_normalized_assert = shape_utils.assert_box_normalized(boxes) with tf.control_dependencies([ box_class_shape_assert, box_confidence_shape_assert, box_dimension_assert, box_normalized_assert ]): quantized_boxes = tf.to_int64(boxes * (quantization_bins - 1)) ymin, xmin, ymax, xmax = tf.unstack(quantized_boxes, axis=1) hashcodes = ( ymin + xmin * quantization_bins + ymax * quantization_bins * quantization_bins + xmax * quantization_bins * quantization_bins * quantization_bins) unique_hashcodes, unique_indices = tf.unique(hashcodes) num_boxes = tf.shape(boxes)[0] num_unique_boxes = tf.shape(unique_hashcodes)[0] merged_box_indices = tf.unsorted_segment_min(tf.range(num_boxes), unique_indices, num_unique_boxes) merged_boxes = tf.gather(boxes, merged_box_indices) def map_box_encodings(i): """Produces box K-hot and score encodings for each class index.""" box_mask = tf.equal(unique_indices, i * tf.ones(num_boxes, dtype=tf.int32)) box_mask = tf.reshape(box_mask, [-1]) box_indices = tf.boolean_mask(classes, box_mask) box_confidences = tf.boolean_mask(confidences, box_mask) box_class_encodings = tf.sparse_to_dense(box_indices, [num_classes], 1, validate_indices=False) box_confidence_encodings = tf.sparse_to_dense( box_indices, [num_classes], box_confidences, validate_indices=False) return box_class_encodings, box_confidence_encodings class_encodings, confidence_encodings = tf.map_fn( map_box_encodings, tf.range(num_unique_boxes), back_prop=False, dtype=(tf.int32, tf.float32)) merged_boxes = tf.reshape(merged_boxes, [-1, 4]) class_encodings = tf.reshape(class_encodings, [-1, num_classes]) confidence_encodings = tf.reshape(confidence_encodings, [-1, num_classes]) merged_box_indices = tf.reshape(merged_box_indices, [-1]) return (merged_boxes, class_encodings, confidence_encodings, merged_box_indices)
K-hot encodings for the merged boxes. confidence_encodings: A tf.float32 tensor with shape [N', num_classes] holding encodings of confidences for the merged boxes. merged_box_indices: A tf.int32 tensor with shape [N'] holding original indices of the boxes. """ boxes_shape = tf.shape(boxes) classes_shape = tf.shape(classes) confidences_shape = tf.shape(confidences) box_class_shape_assert = shape_utils.assert_shape_equal_along_first_dimension( boxes_shape, classes_shape) box_confidence_shape_assert = ( shape_utils.assert_shape_equal_along_first_dimension( boxes_shape, confidences_shape)) box_dimension_assert = tf.assert_equal(boxes_shape[1], 4) box_normalized_assert = shape_utils.assert_box_normalized(boxes) with tf.control_dependencies( [box_class_shape_assert, box_confidence_shape_assert, box_dimension_assert, box_normalized_assert]): quantized_boxes = tf.to_int64(boxes * (quantization_bins - 1)) ymin, xmin, ymax, xmax = tf.unstack(quantized_boxes, axis=1) hashcodes = ( ymin + xmin * quantization_bins + ymax * quantization_bins * quantization_bins + xmax * quantization_bins * quantization_bins * quantization_bins) unique_hashcodes, unique_indices = tf.unique(hashcodes) num_boxes = tf.shape(boxes)[0] num_unique_boxes = tf.shape(unique_hashcodes)[0] merged_box_indices = tf.unsorted_segment_min(
def merge_boxes_with_multiple_labels(boxes, classes, confidences, num_classes, quantization_bins=10000): """Merges boxes with same coordinates and returns K-hot encoded classes. Args: boxes: A tf.float32 tensor with shape [N, 4] holding N boxes. Only normalized coordinates are allowed. classes: A tf.int32 tensor with shape [N] holding class indices. The class index starts at 0. confidences: A tf.float32 tensor with shape [N] holding class confidences. num_classes: total number of classes to use for K-hot encoding. quantization_bins: the number of bins used to quantize the box coordinate. Returns: merged_boxes: A tf.float32 tensor with shape [N', 4] holding boxes, where N' <= N. class_encodings: A tf.int32 tensor with shape [N', num_classes] holding K-hot encodings for the merged boxes. confidence_encodings: A tf.float32 tensor with shape [N', num_classes] holding encodings of confidences for the merged boxes. merged_box_indices: A tf.int32 tensor with shape [N'] holding original indices of the boxes. """ boxes_shape = tf.shape(boxes) classes_shape = tf.shape(classes) confidences_shape = tf.shape(confidences) box_class_shape_assert = shape_utils.assert_shape_equal_along_first_dimension( boxes_shape, classes_shape) box_confidence_shape_assert = ( shape_utils.assert_shape_equal_along_first_dimension( boxes_shape, confidences_shape)) box_dimension_assert = tf.assert_equal(boxes_shape[1], 4) box_normalized_assert = shape_utils.assert_box_normalized(boxes) with tf.control_dependencies( [box_class_shape_assert, box_confidence_shape_assert, box_dimension_assert, box_normalized_assert]): quantized_boxes = tf.to_int64(boxes * (quantization_bins - 1)) ymin, xmin, ymax, xmax = tf.unstack(quantized_boxes, axis=1) hashcodes = ( ymin + xmin * quantization_bins + ymax * quantization_bins * quantization_bins + xmax * quantization_bins * quantization_bins * quantization_bins) unique_hashcodes, unique_indices = tf.unique(hashcodes) num_boxes = tf.shape(boxes)[0] num_unique_boxes = tf.shape(unique_hashcodes)[0] merged_box_indices = tf.unsorted_segment_min( tf.range(num_boxes), unique_indices, num_unique_boxes) merged_boxes = tf.gather(boxes, merged_box_indices) def map_box_encodings(i): """Produces box K-hot and score encodings for each class index.""" box_mask = tf.equal( unique_indices, i * tf.ones(num_boxes, dtype=tf.int32)) box_mask = tf.reshape(box_mask, [-1]) box_indices = tf.boolean_mask(classes, box_mask) box_confidences = tf.boolean_mask(confidences, box_mask) box_class_encodings = tf.sparse_to_dense( box_indices, [num_classes], 1, validate_indices=False) box_confidence_encodings = tf.sparse_to_dense( box_indices, [num_classes], box_confidences, validate_indices=False) return box_class_encodings, box_confidence_encodings class_encodings, confidence_encodings = tf.map_fn( map_box_encodings, tf.range(num_unique_boxes), back_prop=False, dtype=(tf.int32, tf.float32)) merged_boxes = tf.reshape(merged_boxes, [-1, 4]) class_encodings = tf.reshape(class_encodings, [-1, num_classes]) confidence_encodings = tf.reshape(confidence_encodings, [-1, num_classes]) merged_box_indices = tf.reshape(merged_box_indices, [-1]) return (merged_boxes, class_encodings, confidence_encodings, merged_box_indices)