def graph_fn():
t1 = tf.constant([1], dtype=tf.int32)
tt1 = shape_utils.pad_or_clip_tensor(t1, tf.constant(2))
t2 = tf.constant([[0.1, 0.2]], dtype=tf.float32)
tt2 = shape_utils.pad_or_clip_tensor(t2, tf.constant(2))
t3 = tf.constant([1, 2, 3], dtype=tf.int32)
tt3 = shape_utils.clip_tensor(t3, tf.constant(2))
t4 = tf.constant([[0.1, 0.2], [0.2, 0.4], [0.5, 0.8]], dtype=tf.float32)
tt4 = shape_utils.clip_tensor(t4, tf.constant(2))
return tt1, tt2, tt3, tt4
def graph_fn():
t1 = tf.constant([1], dtype=tf.int32)
tt1 = shape_utils.pad_or_clip_tensor(t1, 2)
t2 = tf.constant([[0.1, 0.2]], dtype=tf.float32)
tt2 = shape_utils.pad_or_clip_tensor(t2, 2)
t3 = tf.constant([1, 2, 3], dtype=tf.int32)
tt3 = shape_utils.clip_tensor(t3, 2)
t4 = tf.constant([[0.1, 0.2], [0.2, 0.4], [0.5, 0.8]], dtype=tf.float32)
tt4 = shape_utils.clip_tensor(t4, 2)
self.assertEqual(2, tt1.get_shape()[0])
self.assertEqual(2, tt2.get_shape()[0])
self.assertEqual(2, tt3.get_shape()[0])
self.assertEqual(2, tt4.get_shape()[0])
return tt1, tt2, tt3, tt4
def _per_batch_gather_padding(args):
"""Returns proposal_boxes_result, proposal_score_result and validation.
Args:
args[0]: boxes. A float tensor with shape
[num_proposals, 4] representing the (potentially zero
padded) proposal boxes for all images in the batch.
the format is such as [x1,y2,x2,y2]
args[1]: scores. A float tensor with shape
[num_proposals, num_class] representing the (potentially zero
added) proposal boxes for all images in the batch.
args[2]: keep. A bool tensor with shape
[num_proposals, 1] representing the coordination needing to
keep with true.
args[3]: max_number. A int tensor with shape
[,] representing the kept proposal's number with padding zeros
Returns:
proposal_boxes_result: A float tensor with shape
[max_number, 4] representing the (potentially zero
padded) proposal boxes for all images in the batch.
proposal_score_result: A float tensor with shape
[max_number, num_class] representing the (potentially zero
padded) proposal boxes for all images in the batch.
"""
boxes = args[0]
scores = args[1]
keep = args[2]
if proposal_classes is not None:
classes = args[3]
result_indice = tf.where(keep)
result_indice = tf.squeeze(result_indice, axis=-1)
boxes_result = tf.gather(boxes, result_indice)
boxes_result = shape_utils.pad_or_clip_tensor(
boxes_result, max_numbers)
score_result = tf.gather(scores, result_indice)
score_result = shape_utils.pad_or_clip_tensor(
score_result, max_numbers)
result = [boxes_result, score_result]
if proposal_classes is not None:
class_result = tf.gather(classes, result_indice)
class_result = shape_utils.pad_or_clip_tensor(
class_result, max_numbers)
result.append(class_result)
return result
def test_pad_or_clip_tensor_using_tensor_input(self):
t1 = tf.constant([1], dtype=tf.int32)
tt1 = shape_utils.pad_or_clip_tensor(t1, tf.constant(2))
t2 = tf.constant([[0.1, 0.2]], dtype=tf.float32)
tt2 = shape_utils.pad_or_clip_tensor(t2, tf.constant(2))
t3 = tf.constant([1, 2, 3], dtype=tf.int32)
tt3 = shape_utils.clip_tensor(t3, tf.constant(2))
t4 = tf.constant([[0.1, 0.2], [0.2, 0.4], [0.5, 0.8]], dtype=tf.float32)
tt4 = shape_utils.clip_tensor(t4, tf.constant(2))
with self.test_session() as sess:
tt1_result, tt2_result, tt3_result, tt4_result = sess.run(
[tt1, tt2, tt3, tt4])
self.assertAllEqual([1, 0], tt1_result)
self.assertAllClose([[0.1, 0.2], [0, 0]], tt2_result)
self.assertAllEqual([1, 2], tt3_result)
self.assertAllClose([[0.1, 0.2], [0.2, 0.4]], tt4_result)
def pad_or_clip_box_list(boxlist, num_boxes, scope=None):
"""Pads or clips all fields of a BoxList.
Args:
boxlist: A BoxList with arbitrary of number of boxes.
num_boxes: First num_boxes in boxlist are kept.
The fields are zero-padded if num_boxes is bigger than the
actual number of boxes.
scope: name scope.
Returns:
BoxList with all fields padded or clipped.
"""
with tf.name_scope(scope, 'PadOrClipBoxList'):
subboxlist = box_list.BoxList(
shape_utils.pad_or_clip_tensor(boxlist.get(), num_boxes))
for field in boxlist.get_extra_fields():
subfield = shape_utils.pad_or_clip_tensor(boxlist.get_field(field),
num_boxes)
subboxlist.add_field(field, subfield)
return subboxlist
def pad_or_clip_box_list(boxlist, num_boxes, scope=None):
"""Pads or clips all fields of a BoxList.
Args:
boxlist: A BoxList with arbitrary of number of boxes.
num_boxes: First num_boxes in boxlist are kept.
The fields are zero-padded if num_boxes is bigger than the
actual number of boxes.
scope: name scope.
Returns:
BoxList with all fields padded or clipped.
"""
with tf.name_scope(scope, 'PadOrClipBoxList'):
subboxlist = box_list.BoxList(shape_utils.pad_or_clip_tensor(
boxlist.get(), num_boxes))
for field in boxlist.get_extra_fields():
subfield = shape_utils.pad_or_clip_tensor(
boxlist.get_field(field), num_boxes)
subboxlist.add_field(field, subfield)
return subboxlist
def score_filter(self, boxes, scores, score_thresh=0.5, max_detections=8192):
from object_detection.utils import shape_utils
if scores.shape.ndims != 2:
raise ValueError('scores field must be of rank 2')
if boxes.shape.ndims != 3:
raise ValueError('boxes must be of rank 3.')
if boxes.shape[2].value != 5:
raise ValueError('boxes must be of shape [batch, anchors, 5].')
with tf.name_scope('ScoreFilter'):
per_image_boxes_list = tf.unstack(boxes)
per_image_scores_list = tf.unstack(scores)
detection_boxes_list = []
detection_scores_list = []
detection_classes_list = []
num_detections_list = []
for (per_image_boxes, per_image_scores
) in zip(per_image_boxes_list, per_image_scores_list):
greater_indexes = tf.cast(tf.reshape(
tf.where(tf.greater(per_image_scores, score_thresh)),
[-1]), tf.int32)
filterd_boxes = tf.gather(per_image_boxes, greater_indexes)
filterd_scores = tf.gather(per_image_scores, greater_indexes)
pad_boxes = shape_utils.pad_or_clip_tensor(filterd_boxes, max_detections)
pad_scores = shape_utils.pad_or_clip_tensor(filterd_scores, max_detections)
num_detections_list.append(tf.to_float(tf.shape(greater_indexes)[0]))
detection_boxes_list.append(pad_boxes)
detection_scores_list.append(pad_scores)
detection_classes_list.append(tf.ones_like(pad_scores))
det_dict = {
'detection_boxes': tf.stack(detection_boxes_list),
'detection_scores': tf.stack(detection_scores_list),
'detection_classes': tf.stack(detection_classes_list),
'num_detections': tf.stack(num_detections_list)
}
return det_dict
